def mp_US_removal_rates(sensit_type, tile_id_list, run_date):
os.chdir(cn.docker_base_dir)
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
tile_id_list = uu.tile_list_s3(cn.FIA_regions_processed_dir)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script
download_dict = {
cn.gain_dir: [cn.pattern_gain],
cn.FIA_regions_processed_dir: [cn.pattern_FIA_regions_processed],
cn.FIA_forest_group_processed_dir:
[cn.pattern_FIA_forest_group_processed],
cn.age_cat_natrl_forest_US_dir: [cn.pattern_age_cat_natrl_forest_US]
}
# List of output directories and output file name patterns
output_dir_list = [
cn.annual_gain_AGC_BGC_natrl_forest_US_dir,
cn.stdev_annual_gain_AGC_BGC_natrl_forest_US_dir
]
output_pattern_list = [
cn.pattern_annual_gain_AGC_BGC_natrl_forest_US,
cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_US
]
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list, if AWS credentials are found
if uu.check_aws_creds():
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Table with US-specific removal rates
cmd = [
'aws', 's3', 'cp',
os.path.join(cn.gain_spreadsheet_dir, cn.table_US_removal_rate),
cn.docker_base_dir
]
uu.log_subprocess_output_full(cmd)
### To make the removal factor dictionaries
# Imports the table with the region-group-age AGC+BGC removal rates
gain_table = pd.read_excel("{}".format(cn.table_US_removal_rate),
sheet_name="US_rates_AGC+BGC")
# Converts gain table from wide to long, so each region-group-age category has its own row
gain_table_group_region_by_age = pd.melt(
gain_table,
id_vars=['FIA_region_code', 'forest_group_code'],
value_vars=['growth_young', 'growth_middle', 'growth_old'])
gain_table_group_region_by_age = gain_table_group_region_by_age.dropna()
# In the forest age category raster, each category has this value
age_dict = {
'growth_young': 1000,
'growth_middle': 2000,
'growth_old': 3000
}
# Creates a unique value for each forest group-region-age category in the table.
# Although these rates are applied to all standard gain model pixels at first, they are not ultimately used for
# pixels that have Hansen gain (see below).
gain_table_group_region_age = gain_table_group_region_by_age.replace(
{"variable": age_dict})
gain_table_group_region_age[
'age_cat'] = gain_table_group_region_age['variable'] * 10
gain_table_group_region_age['group_region_age_combined'] = gain_table_group_region_age['age_cat'] + \
gain_table_group_region_age['forest_group_code']*100 + \
gain_table_group_region_age['FIA_region_code']
# Converts the forest group-region-age codes and corresponding gain rates to a dictionary,
# where the key is the unique group-region-age code and the value is the AGB removal rate.
gain_table_group_region_age_dict = pd.Series(
gain_table_group_region_age.value.values,
index=gain_table_group_region_age.group_region_age_combined).to_dict()
uu.print_log(gain_table_group_region_age_dict)
# Creates a unique value for each forest group-region category using just young forest rates.
# These are assigned to Hansen gain pixels, which automatically get the young forest rate, regardless of the
# forest age category raster.
gain_table_group_region = gain_table_group_region_age.drop(
gain_table_group_region_age[
gain_table_group_region_age.age_cat != 10000].index)
gain_table_group_region['group_region_combined'] = gain_table_group_region['forest_group_code']*100 + \
gain_table_group_region['FIA_region_code']
# Converts the forest group-region codes and corresponding gain rates to a dictionary,
# where the key is the unique group-region code (youngest age category) and the value is the AGB removal rate.
gain_table_group_region_dict = pd.Series(
gain_table_group_region.value.values,
index=gain_table_group_region.group_region_combined).to_dict()
uu.print_log(gain_table_group_region_dict)
### To make the removal factor standard deviation dictionaries
# Converts gain table from wide to long, so each region-group-age category has its own row
stdev_table_group_region_by_age = pd.melt(
gain_table,
id_vars=['FIA_region_code', 'forest_group_code'],
value_vars=['SD_young', 'SD_middle', 'SD_old'])
stdev_table_group_region_by_age = stdev_table_group_region_by_age.dropna()
# In the forest age category raster, each category has this value
stdev_dict = {'SD_young': 1000, 'SD_middle': 2000, 'SD_old': 3000}
# Creates a unique value for each forest group-region-age category in the table.
# Although these rates are applied to all standard gain model pixels at first, they are not ultimately used for
# pixels that have Hansen gain (see below).
stdev_table_group_region_age = stdev_table_group_region_by_age.replace(
{"variable": stdev_dict})
stdev_table_group_region_age[
'age_cat'] = stdev_table_group_region_age['variable'] * 10
stdev_table_group_region_age['group_region_age_combined'] = stdev_table_group_region_age['age_cat'] + \
stdev_table_group_region_age['forest_group_code'] * 100 + \
stdev_table_group_region_age['FIA_region_code']
# Converts the forest group-region-age codes and corresponding gain rates to a dictionary,
# where the key is the unique group-region-age code and the value is the AGB removal rate.
stdev_table_group_region_age_dict = pd.Series(
stdev_table_group_region_age.value.values,
index=stdev_table_group_region_age.group_region_age_combined).to_dict(
)
uu.print_log(stdev_table_group_region_age_dict)
# Creates a unique value for each forest group-region category using just young forest rates.
# These are assigned to Hansen gain pixels, which automatically get the young forest rate, regardless of the
# forest age category raster.
stdev_table_group_region = stdev_table_group_region_age.drop(
stdev_table_group_region_age[
stdev_table_group_region_age.age_cat != 10000].index)
stdev_table_group_region['group_region_combined'] = stdev_table_group_region['forest_group_code'] * 100 + \
stdev_table_group_region['FIA_region_code']
# Converts the forest group-region codes and corresponding gain rates to a dictionary,
# where the key is the unique group-region code (youngest age category) and the value is the AGB removal rate.
stdev_table_group_region_dict = pd.Series(
stdev_table_group_region.value.values,
index=stdev_table_group_region.group_region_combined).to_dict()
uu.print_log(stdev_table_group_region_dict)
if cn.count == 96:
processes = 68 # 68 processors (only 16 tiles though) = 310 GB peak
else:
processes = 24
uu.print_log('US natural forest AGC+BGC removal rate max processors=',
processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(
US_removal_rates.US_removal_rate_calc,
gain_table_group_region_age_dict=gain_table_group_region_age_dict,
gain_table_group_region_dict=gain_table_group_region_dict,
stdev_table_group_region_age_dict=stdev_table_group_region_age_dict,
stdev_table_group_region_dict=stdev_table_group_region_dict,
output_pattern_list=output_pattern_list), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
#
# US_removal_rates.US_removal_rate_calc(tile_id,
# gain_table_group_region_age_dict,
# gain_table_group_region_dict,
# stdev_table_group_region_age_dict,
# stdev_table_group_region_dict,
# output_pattern_list)
# Uploads output tiles to s3
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
def mp_prep_other_inputs(tile_id_list, run_date):
os.chdir(cn.docker_base_dir)
sensit_type='std'
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model
tile_id_list = uu.create_combined_tile_list(cn.WHRC_biomass_2000_unmasked_dir,
cn.mangrove_biomass_2000_dir,
set3=cn.annual_gain_AGC_BGC_planted_forest_unmasked_dir
)
uu.print_log(tile_id_list)
uu.print_log("There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# List of output directories and output file name patterns
output_dir_list = [cn.climate_zone_processed_dir, cn.plant_pre_2000_processed_dir,
cn.drivers_processed_dir, cn.ifl_primary_processed_dir,
cn.annual_gain_AGC_natrl_forest_young_dir,
cn.stdev_annual_gain_AGC_natrl_forest_young_dir,
cn.annual_gain_AGC_BGC_natrl_forest_Europe_dir,
cn.stdev_annual_gain_AGC_BGC_natrl_forest_Europe_dir,
cn.FIA_forest_group_processed_dir,
cn.age_cat_natrl_forest_US_dir,
cn.FIA_regions_processed_dir]
output_pattern_list = [cn.pattern_climate_zone, cn.pattern_plant_pre_2000,
cn.pattern_drivers, cn.pattern_ifl_primary,
cn.pattern_annual_gain_AGC_natrl_forest_young,
cn.pattern_stdev_annual_gain_AGC_natrl_forest_young,
cn.pattern_annual_gain_AGC_BGC_natrl_forest_Europe,
cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_Europe,
cn.pattern_FIA_forest_group_processed,
cn.pattern_age_cat_natrl_forest_US,
cn.pattern_FIA_regions_processed]
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log("Changing output directory and file name pattern based on sensitivity analysis")
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type, output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Files to process: climate zone, IDN/MYS plantations before 2000, tree cover loss drivers, combine IFL and primary forest
uu.s3_file_download(os.path.join(cn.climate_zone_raw_dir, cn.climate_zone_raw), cn.docker_base_dir, sensit_type)
uu.s3_file_download(os.path.join(cn.plant_pre_2000_raw_dir, '{}.zip'.format(cn.pattern_plant_pre_2000_raw)), cn.docker_base_dir, sensit_type)
uu.s3_file_download(os.path.join(cn.drivers_raw_dir, '{}.zip'.format(cn.pattern_drivers_raw)), cn.docker_base_dir, sensit_type)
uu.s3_file_download(os.path.join(cn.annual_gain_AGC_BGC_natrl_forest_Europe_raw_dir, cn.name_annual_gain_AGC_BGC_natrl_forest_Europe_raw), cn.docker_base_dir, sensit_type)
uu.s3_file_download(os.path.join(cn.stdev_annual_gain_AGC_BGC_natrl_forest_Europe_raw_dir, cn.name_stdev_annual_gain_AGC_BGC_natrl_forest_Europe_raw), cn.docker_base_dir, sensit_type)
uu.s3_file_download(os.path.join(cn.FIA_regions_raw_dir, cn.name_FIA_regions_raw), cn.docker_base_dir, sensit_type)
uu.s3_file_download(os.path.join(cn.age_cat_natrl_forest_US_raw_dir, cn.name_age_cat_natrl_forest_US_raw), cn.docker_base_dir, sensit_type)
uu.s3_file_download(os.path.join(cn.FIA_forest_group_raw_dir, cn.name_FIA_forest_group_raw), cn.docker_base_dir, sensit_type)
# For some reason, using uu.s3_file_download or otherwise using AWSCLI as a subprocess doesn't work for this raster.
# Thus, using wget instead.
cmd = ['wget', '{}'.format(cn.annual_gain_AGC_natrl_forest_young_raw_URL), '-P', '{}'.format(cn.docker_base_dir)]
process = Popen(cmd, stdout=PIPE, stderr=STDOUT)
with process.stdout:
uu.log_subprocess_output(process.stdout)
uu.s3_file_download(cn.stdev_annual_gain_AGC_natrl_forest_young_raw_URL, cn.docker_base_dir, sensit_type)
cmd = ['aws', 's3', 'cp', cn.primary_raw_dir, cn.docker_base_dir, '--recursive']
uu.log_subprocess_output_full(cmd)
uu.s3_flexible_download(cn.ifl_dir, cn.pattern_ifl, cn.docker_base_dir, sensit_type, tile_id_list)
uu.print_log("Unzipping pre-2000 plantations...")
cmd = ['unzip', '-j', '{}.zip'.format(cn.pattern_plant_pre_2000_raw)]
uu.log_subprocess_output_full(cmd)
uu.print_log("Unzipping drivers...")
cmd = ['unzip', '-j', '{}.zip'.format(cn.pattern_drivers_raw)]
uu.log_subprocess_output_full(cmd)
# Creates tree cover loss driver tiles
source_raster = '{}.tif'.format(cn.pattern_drivers_raw)
out_pattern = cn.pattern_drivers
dt = 'Byte'
if cn.count == 96:
processes = 80 # 45 processors = 70 GB peak; 70 = 90 GB peak; 80 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating tree cover loss driver tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates young natural forest removal rate tiles
source_raster = cn.name_annual_gain_AGC_natrl_forest_young_raw
out_pattern = cn.pattern_annual_gain_AGC_natrl_forest_young
dt = 'float32'
if cn.count == 96:
processes = 80 # 32 processors = 210 GB peak; 60 = 370 GB peak; 80 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating young natural forest gain rate tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates young natural forest removal rate standard deviation tiles
source_raster = cn.name_stdev_annual_gain_AGC_natrl_forest_young_raw
out_pattern = cn.pattern_stdev_annual_gain_AGC_natrl_forest_young
dt = 'float32'
if cn.count == 96:
processes = 80 # 32 processors = 210 GB peak; 60 = 370 GB peak; 80 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating standard deviation for young natural forest removal rate tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates pre-2000 oil palm plantation tiles
if cn.count == 96:
processes = 80 # 45 processors = 100 GB peak; 80 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating pre-2000 oil palm plantation tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(prep_other_inputs.rasterize_pre_2000_plantations, tile_id_list)
pool.close()
pool.join()
# Creates climate zone tiles
if cn.count == 96:
processes = 80 # 45 processors = 230 GB peak (on second step); 80 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating climate zone tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(prep_other_inputs.create_climate_zone_tiles, tile_id_list)
pool.close()
pool.join()
# Creates European natural forest removal rate tiles
source_raster = cn.name_annual_gain_AGC_BGC_natrl_forest_Europe_raw
out_pattern = cn.pattern_annual_gain_AGC_BGC_natrl_forest_Europe
dt = 'float32'
if cn.count == 96:
processes = 60 # 32 processors = 60 GB peak; 60 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating European natural forest gain rate tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates European natural forest standard deviation of removal rate tiles
source_raster = cn.name_stdev_annual_gain_AGC_BGC_natrl_forest_Europe_raw
out_pattern = cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_Europe
dt = 'float32'
if cn.count == 96:
processes = 32 # 32 processors = 60 GB peak; 60 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating standard deviation for European natural forest gain rate tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates a vrt of the primary forests with nodata=0 from the continental primary forest rasters
uu.print_log("Creating vrt of humid tropial primary forest...")
primary_vrt = 'primary_2001.vrt'
os.system('gdalbuildvrt -srcnodata 0 {} *2001_primary.tif'.format(primary_vrt))
uu.print_log(" Humid tropical primary forest vrt created")
# Creates primary forest tiles
source_raster = primary_vrt
out_pattern = 'primary_2001'
dt = 'Byte'
if cn.count == 96:
processes = 45 # 45 processors = 650 GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating primary forest tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates a combined IFL/primary forest raster
# Uses very little memory since it's just file renaming
if cn.count == 96:
processes = 60 # 60 processors = 10 GB peak
else:
processes = int(cn.count/2)
uu.print_log("Assigning each tile to ifl2000 or primary forest with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(prep_other_inputs.create_combined_ifl_primary, tile_id_list)
pool.close()
pool.join()
# Creates forest age category tiles for US forests
source_raster = cn.name_age_cat_natrl_forest_US_raw
out_pattern = cn.pattern_age_cat_natrl_forest_US
dt = 'Byte'
if cn.count == 96:
processes = 70 # 32 processors = 35 GB peak; 70 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating US forest age category tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates forest groups for US forests
source_raster = cn.name_FIA_forest_group_raw
out_pattern = cn.pattern_FIA_forest_group_processed
dt = 'Byte'
if cn.count == 96:
processes = 80 # 32 processors = 25 GB peak; 80 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating US forest group tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
# Creates FIA regions for US forests
source_raster = cn.name_FIA_regions_raw
out_pattern = cn.pattern_FIA_regions_processed
dt = 'Byte'
if cn.count == 96:
processes = 70 # 32 processors = 35 GB peak; 70 = XXX GB peak
else:
processes = int(cn.count/2)
uu.print_log("Creating US forest region tiles with {} processors...".format(processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt), tile_id_list)
pool.close()
pool.join()
for output_pattern in [cn.pattern_annual_gain_AGC_natrl_forest_young, cn.pattern_stdev_annual_gain_AGC_natrl_forest_young]:
# For some reason I can't figure out, the young forest rasters (rate and stdev) have NaN values in some places where 0 (NoData)
# should be. These NaN values show up as values when the check_and_delete_if_empty function runs, making the tiles not
# deleted even if they have no data. However, the light version (which uses gdalinfo rather than rasterio masks) doesn't
# have this problem. So I'm forcing the young forest rates to and stdev to have their emptiness checked by the gdalinfo version.
if output_pattern in [cn.pattern_annual_gain_AGC_natrl_forest_young, cn.pattern_stdev_annual_gain_AGC_natrl_forest_young]:
processes = int(cn.count / 2)
uu.print_log("Checking for empty tiles of {0} pattern with {1} processors using light function...".format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.check_and_delete_if_empty_light, output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
if cn.count == 96:
processes = 50 # 60 processors = >730 GB peak (for European natural forest forest removal rates); 50 = XXX GB peak
uu.print_log("Checking for empty tiles of {0} pattern with {1} processors...".format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.check_and_delete_if_empty, output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
elif cn.count <= 2: # For local tests
processes = 1
uu.print_log("Checking for empty tiles of {0} pattern with {1} processors using light function...".format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.check_and_delete_if_empty_light, output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
else:
processes = int(cn.count / 2)
uu.print_log("Checking for empty tiles of {0} pattern with {1} processors...".format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.check_and_delete_if_empty, output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
uu.print_log('\n')
# Uploads output tiles to s3
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
def mp_calculate_gross_emissions(sensit_type,
tile_id_list,
emitted_pools,
run_date=None):
os.chdir(cn.docker_base_dir)
folder = cn.docker_base_dir
# If a full model run is specified, the correct set of tiles for the particular script is listed
# If the tile_list argument is an s3 folder, the list of tiles in it is created
if tile_id_list == 'all':
# List of tiles to run in the model
tile_id_list = uu.tile_list_s3(cn.AGC_emis_year_dir, sensit_type)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script
download_dict = {
cn.AGC_emis_year_dir: [cn.pattern_AGC_emis_year],
cn.BGC_emis_year_dir: [cn.pattern_BGC_emis_year],
cn.deadwood_emis_year_2000_dir: [cn.pattern_deadwood_emis_year_2000],
cn.litter_emis_year_2000_dir: [cn.pattern_litter_emis_year_2000],
cn.soil_C_emis_year_2000_dir: [cn.pattern_soil_C_emis_year_2000],
cn.peat_mask_dir: [cn.pattern_peat_mask],
cn.ifl_primary_processed_dir: [cn.pattern_ifl_primary],
cn.planted_forest_type_unmasked_dir:
[cn.pattern_planted_forest_type_unmasked],
cn.drivers_processed_dir: [cn.pattern_drivers],
cn.climate_zone_processed_dir: [cn.pattern_climate_zone],
cn.bor_tem_trop_processed_dir: [cn.pattern_bor_tem_trop_processed],
cn.burn_year_dir: [cn.pattern_burn_year]
}
# Special loss tiles for the Brazil and Mekong sensitivity analyses
if sensit_type == 'legal_Amazon_loss':
download_dict[cn.Brazil_annual_loss_processed_dir] = [
cn.pattern_Brazil_annual_loss_processed
]
elif sensit_type == 'Mekong_loss':
download_dict[cn.Mekong_loss_processed_dir] = [
cn.pattern_Mekong_loss_processed
]
else:
download_dict[cn.loss_dir] = [cn.pattern_loss]
# Checks the validity of the emitted_pools argument
if (emitted_pools not in ['soil_only', 'biomass_soil']):
uu.exception_log(
'Invalid pool input. Please choose soil_only or biomass_soil.')
# Checks if the correct c++ script has been compiled for the pool option selected
if emitted_pools == 'biomass_soil':
# Output file directories for biomass+soil. Must be in same order as output pattern directories.
output_dir_list = [
cn.gross_emis_commod_biomass_soil_dir,
cn.gross_emis_shifting_ag_biomass_soil_dir,
cn.gross_emis_forestry_biomass_soil_dir,
cn.gross_emis_wildfire_biomass_soil_dir,
cn.gross_emis_urban_biomass_soil_dir,
cn.gross_emis_no_driver_biomass_soil_dir,
cn.gross_emis_all_gases_all_drivers_biomass_soil_dir,
cn.gross_emis_co2_only_all_drivers_biomass_soil_dir,
cn.gross_emis_non_co2_all_drivers_biomass_soil_dir,
cn.gross_emis_nodes_biomass_soil_dir
]
output_pattern_list = [
cn.pattern_gross_emis_commod_biomass_soil,
cn.pattern_gross_emis_shifting_ag_biomass_soil,
cn.pattern_gross_emis_forestry_biomass_soil,
cn.pattern_gross_emis_wildfire_biomass_soil,
cn.pattern_gross_emis_urban_biomass_soil,
cn.pattern_gross_emis_no_driver_biomass_soil,
cn.pattern_gross_emis_all_gases_all_drivers_biomass_soil,
cn.pattern_gross_emis_co2_only_all_drivers_biomass_soil,
cn.pattern_gross_emis_non_co2_all_drivers_biomass_soil,
cn.pattern_gross_emis_nodes_biomass_soil
]
# Some sensitivity analyses have specific gross emissions scripts.
# The rest of the sensitivity analyses and the standard model can all use the same, generic gross emissions script.
if sensit_type in ['no_shifting_ag', 'convert_to_grassland']:
# if os.path.exists('../carbon-budget/emissions/cpp_util/calc_gross_emissions_{}.exe'.format(sensit_type)):
if os.path.exists('{0}/calc_gross_emissions_{1}.exe'.format(
cn.c_emis_compile_dst, sensit_type)):
uu.print_log(
"C++ for {} already compiled.".format(sensit_type))
else:
uu.exception_log(
'Must compile {} model C++...'.format(sensit_type))
else:
if os.path.exists('{0}/calc_gross_emissions_generic.exe'.format(
cn.c_emis_compile_dst)):
uu.print_log("C++ for generic emissions already compiled.")
else:
uu.exception_log('Must compile generic emissions C++...')
elif (emitted_pools == 'soil_only') & (sensit_type == 'std'):
if os.path.exists('{0}/calc_gross_emissions_soil_only.exe'.format(
cn.c_emis_compile_dst)):
uu.print_log("C++ for soil_only already compiled.")
# Output file directories for soil_only. Must be in same order as output pattern directories.
output_dir_list = [
cn.gross_emis_commod_soil_only_dir,
cn.gross_emis_shifting_ag_soil_only_dir,
cn.gross_emis_forestry_soil_only_dir,
cn.gross_emis_wildfire_soil_only_dir,
cn.gross_emis_urban_soil_only_dir,
cn.gross_emis_no_driver_soil_only_dir,
cn.gross_emis_all_gases_all_drivers_soil_only_dir,
cn.gross_emis_co2_only_all_drivers_soil_only_dir,
cn.gross_emis_non_co2_all_drivers_soil_only_dir,
cn.gross_emis_nodes_soil_only_dir
]
output_pattern_list = [
cn.pattern_gross_emis_commod_soil_only,
cn.pattern_gross_emis_shifting_ag_soil_only,
cn.pattern_gross_emis_forestry_soil_only,
cn.pattern_gross_emis_wildfire_soil_only,
cn.pattern_gross_emis_urban_soil_only,
cn.pattern_gross_emis_no_driver_soil_only,
cn.pattern_gross_emis_all_gases_all_drivers_soil_only,
cn.pattern_gross_emis_co2_only_all_drivers_soil_only,
cn.pattern_gross_emis_non_co2_all_drivers_soil_only,
cn.pattern_gross_emis_nodes_soil_only
]
else:
uu.exception_log('Must compile soil_only C++...')
else:
uu.exception_log('Pool and/or sensitivity analysis option not valid')
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, folder, sensit_type,
tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
uu.print_log(output_dir_list)
uu.print_log(output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# The C++ code expects certain tiles for every input 10x10.
# However, not all Hansen tiles have all of these inputs.
# This function creates "dummy" tiles for all Hansen tiles that currently have non-existent tiles.
# That way, the C++ script gets all the necessary input files.
# If it doesn't get the necessary inputs, it skips that tile.
uu.print_log("Making blank tiles for inputs that don't currently exist")
# All of the inputs that need to have dummy tiles made in order to match the tile list of the carbon emitted_pools
pattern_list = [
cn.pattern_planted_forest_type_unmasked, cn.pattern_peat_mask,
cn.pattern_ifl_primary, cn.pattern_drivers,
cn.pattern_bor_tem_trop_processed, cn.pattern_burn_year,
cn.pattern_climate_zone, cn.pattern_soil_C_emis_year_2000
]
# textfile that stores the names of the blank tiles that are created for processing.
# This will be iterated through to delete the tiles at the end of the script.
uu.create_blank_tile_txt()
for pattern in pattern_list:
pool = multiprocessing.Pool(processes=60) # 60 = 100 GB peak
pool.map(
partial(uu.make_blank_tile,
pattern=pattern,
folder=folder,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for pattern in pattern_list:
# for tile in tile_id_list:
# uu.make_blank_tile(tile, pattern, folder, sensit_type)
# Calculates gross emissions for each tile
# count/4 uses about 390 GB on a r4.16xlarge spot machine.
# processes=18 uses about 440 GB on an r4.16xlarge spot machine.
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 15 # 15 processors = XXX GB peak
else:
processes = 19 # 17 = 650 GB peak; 18 = 677 GB peak; 19 = 714 GB peak
else:
processes = 9
uu.print_log('Gross emissions max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(calculate_gross_emissions.calc_emissions,
emitted_pools=emitted_pools,
sensit_type=sensit_type,
folder=folder), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile in tile_id_list:
# calculate_gross_emissions.calc_emissions(tile, emitted_pools, sensit_type, folder)
# Print the list of blank created tiles, delete the tiles, and delete their text file
uu.list_and_delete_blank_tiles()
for i in range(0, len(output_pattern_list)):
pattern = output_pattern_list[i]
uu.print_log("Adding metadata tags for pattern {}".format(pattern))
if cn.count == 96:
processes = 45 # 45 processors = XXX GB peak
else:
processes = 9
uu.print_log('Adding metadata tags max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(calculate_gross_emissions.add_metadata_tags,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# for tile_id in tile_id_list:
# calculate_gross_emissions.add_metadata_tags(tile_id, pattern, sensit_type)
# Uploads emissions to appropriate directory for the carbon emitted_pools chosen
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
def mp_annual_gain_rate_IPCC_defaults(sensit_type,
tile_id_list,
run_date=None):
os.chdir(cn.docker_base_dir)
pd.options.mode.chained_assignment = None
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model
tile_id_list = uu.tile_list_s3(cn.model_extent_dir, sensit_type)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script.
download_dict = {
cn.age_cat_IPCC_dir: [cn.pattern_age_cat_IPCC],
cn.cont_eco_dir: [cn.pattern_cont_eco_processed]
}
# List of output directories and output file name patterns
output_dir_list = [
cn.annual_gain_AGB_IPCC_defaults_dir,
cn.annual_gain_BGB_IPCC_defaults_dir,
cn.stdev_annual_gain_AGB_IPCC_defaults_dir
]
output_pattern_list = [
cn.pattern_annual_gain_AGB_IPCC_defaults,
cn.pattern_annual_gain_BGB_IPCC_defaults,
cn.pattern_stdev_annual_gain_AGB_IPCC_defaults
]
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type,
tile_id_list)
# Table with IPCC Table 4.9 default gain rates
cmd = [
'aws', 's3', 'cp',
os.path.join(cn.gain_spreadsheet_dir, cn.gain_spreadsheet),
cn.docker_base_dir
]
uu.log_subprocess_output_full(cmd)
### To make the removal factor dictionaries
# Special removal rate table for no_primary_gain sensitivity analysis: primary forests and IFLs have removal rate of 0
if sensit_type == 'no_primary_gain':
# Imports the table with the ecozone-continent codes and the carbon gain rates
gain_table = pd.read_excel("{}".format(cn.gain_spreadsheet),
sheet_name="natrl fores gain, no_prim_gain")
uu.print_log(
"Using no_primary_gain IPCC default rates for tile creation")
# All other analyses use the standard removal rates
else:
# Imports the table with the ecozone-continent codes and the biomass gain rates
gain_table = pd.read_excel(
"{}".format(cn.gain_spreadsheet),
sheet_name="natrl fores gain, for std model")
# Removes rows with duplicate codes (N. and S. America for the same ecozone)
gain_table_simplified = gain_table.drop_duplicates(subset='gainEcoCon',
keep='first')
# Converts gain table from wide to long, so each continent-ecozone-age category has its own row
gain_table_cont_eco_age = pd.melt(gain_table_simplified,
id_vars=['gainEcoCon'],
value_vars=[
'growth_primary',
'growth_secondary_greater_20',
'growth_secondary_less_20'
])
gain_table_cont_eco_age = gain_table_cont_eco_age.dropna()
# Creates a table that has just the continent-ecozone combinations for adding to the dictionary.
# These will be used whenever there is just a continent-ecozone pixel without a forest age pixel.
# Assigns removal rate of 0 when there's no age category.
gain_table_con_eco_only = gain_table_cont_eco_age
gain_table_con_eco_only = gain_table_con_eco_only.drop_duplicates(
subset='gainEcoCon', keep='first')
gain_table_con_eco_only['value'] = 0
gain_table_con_eco_only['cont_eco_age'] = gain_table_con_eco_only[
'gainEcoCon']
# Creates a code for each age category so that each continent-ecozone-age combo can have its own unique value
rate_age_dict = {
'growth_secondary_less_20': 10000,
'growth_secondary_greater_20': 20000,
'growth_primary': 30000
}
# Creates a unique value for each continent-ecozone-age category
gain_table_cont_eco_age = gain_table_cont_eco_age.replace(
{"variable": rate_age_dict})
gain_table_cont_eco_age['cont_eco_age'] = gain_table_cont_eco_age[
'gainEcoCon'] + gain_table_cont_eco_age['variable']
# Merges the table of just continent-ecozone codes and the table of continent-ecozone-age codes
gain_table_all_combos = pd.concat(
[gain_table_con_eco_only, gain_table_cont_eco_age])
# Converts the continent-ecozone-age codes and corresponding gain rates to a dictionary
gain_table_dict = pd.Series(
gain_table_all_combos.value.values,
index=gain_table_all_combos.cont_eco_age).to_dict()
# Adds a dictionary entry for where the ecozone-continent-age code is 0 (not in a continent)
gain_table_dict[0] = 0
# Adds a dictionary entry for each forest age code for pixels that have forest age but no continent-ecozone
for key, value in rate_age_dict.items():
gain_table_dict[value] = 0
# Converts all the keys (continent-ecozone-age codes) to float type
gain_table_dict = {
float(key): value
for key, value in gain_table_dict.items()
}
### To make the removal factor standard deviation dictionary
# Special removal rate table for no_primary_gain sensitivity analysis: primary forests and IFLs have removal rate of 0
if sensit_type == 'no_primary_gain':
# Imports the table with the ecozone-continent codes and the carbon gain rates
stdev_table = pd.read_excel(
"{}".format(cn.gain_spreadsheet),
sheet_name="natrl fores stdv, no_prim_gain")
uu.print_log(
"Using no_primary_gain IPCC default standard deviations for tile creation"
)
# All other analyses use the standard removal rates
else:
# Imports the table with the ecozone-continent codes and the biomass gain rate standard deviations
stdev_table = pd.read_excel(
"{}".format(cn.gain_spreadsheet),
sheet_name="natrl fores stdv, for std model")
# Removes rows with duplicate codes (N. and S. America for the same ecozone)
stdev_table_simplified = stdev_table.drop_duplicates(subset='gainEcoCon',
keep='first')
# Converts gain table from wide to long, so each continent-ecozone-age category has its own row
stdev_table_cont_eco_age = pd.melt(stdev_table_simplified,
id_vars=['gainEcoCon'],
value_vars=[
'stdev_primary',
'stdev_secondary_greater_20',
'stdev_secondary_less_20'
])
stdev_table_cont_eco_age = stdev_table_cont_eco_age.dropna()
# Creates a table that has just the continent-ecozone combinations for adding to the dictionary.
# These will be used whenever there is just a continent-ecozone pixel without a forest age pixel.
# Assigns removal rate of 0 when there's no age category.
stdev_table_con_eco_only = stdev_table_cont_eco_age
stdev_table_con_eco_only = stdev_table_con_eco_only.drop_duplicates(
subset='gainEcoCon', keep='first')
stdev_table_con_eco_only['value'] = 0
stdev_table_con_eco_only['cont_eco_age'] = stdev_table_con_eco_only[
'gainEcoCon']
# Creates a code for each age category so that each continent-ecozone-age combo can have its own unique value
stdev_age_dict = {
'stdev_secondary_less_20': 10000,
'stdev_secondary_greater_20': 20000,
'stdev_primary': 30000
}
# Creates a unique value for each continent-ecozone-age category
stdev_table_cont_eco_age = stdev_table_cont_eco_age.replace(
{"variable": stdev_age_dict})
stdev_table_cont_eco_age['cont_eco_age'] = stdev_table_cont_eco_age[
'gainEcoCon'] + stdev_table_cont_eco_age['variable']
# Merges the table of just continent-ecozone codes and the table of continent-ecozone-age codes
stdev_table_all_combos = pd.concat(
[stdev_table_con_eco_only, stdev_table_cont_eco_age])
# Converts the continent-ecozone-age codes and corresponding gain rates to a dictionary
stdev_table_dict = pd.Series(
stdev_table_all_combos.value.values,
index=stdev_table_all_combos.cont_eco_age).to_dict()
# Adds a dictionary entry for where the ecozone-continent-age code is 0 (not in a continent)
stdev_table_dict[0] = 0
# Adds a dictionary entry for each forest age code for pixels that have forest age but no continent-ecozone
for key, value in stdev_age_dict.items():
stdev_table_dict[value] = 0
# Converts all the keys (continent-ecozone-age codes) to float type
stdev_table_dict = {
float(key): value
for key, value in stdev_table_dict.items()
}
# This configuration of the multiprocessing call is necessary for passing multiple arguments to the main function
# It is based on the example here: http://spencerimp.blogspot.com/2015/12/python-multiprocess-with-multiple.html
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 24 # 24 processors = 590 GB peak
else:
processes = 30 # 30 processors = 725 GB peak
else:
processes = 2
uu.print_log('Annual gain rate natural forest max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(annual_gain_rate_IPCC_defaults.annual_gain_rate,
sensit_type=sensit_type,
gain_table_dict=gain_table_dict,
stdev_table_dict=stdev_table_dict,
output_pattern_list=output_pattern_list), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
#
# annual_gain_rate_IPCC_defaults.annual_gain_rate(tile_id, sensit_type,
# gain_table_dict, stdev_table_dict, output_pattern_list)
# Uploads output tiles to s3
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
def mp_gain_year_count_all_forest_types(sensit_type, tile_id_list, run_date = None, no_upload = True):
os.chdir(cn.docker_base_dir)
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# No point in making gain year count tiles for tiles that don't have annual removals
tile_id_list = uu.tile_list_s3(cn.annual_gain_AGC_all_types_dir, sensit_type)
uu.print_log(tile_id_list)
uu.print_log("There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script. 'true'/'false' says whether the input directory and pattern should be
# changed for a sensitivity analysis. This does not need to change based on what run is being done;
# this assignment should be true for all sensitivity analyses and the standard model.
download_dict = {
cn.gain_dir: [cn.pattern_gain],
cn.model_extent_dir: [cn.pattern_model_extent]
}
# Adds the correct loss tile to the download dictionary depending on the model run
if sensit_type == 'legal_Amazon_loss':
download_dict[cn.Brazil_annual_loss_processed_dir] = [cn.pattern_Brazil_annual_loss_processed]
elif sensit_type == 'Mekong_loss':
download_dict[cn.Mekong_loss_processed_dir] = [cn.pattern_Mekong_loss_processed]
else:
download_dict[cn.loss_dir] = [cn.pattern_loss]
output_dir_list = [cn.gain_year_count_dir]
output_pattern_list = [cn.pattern_gain_year_count]
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list, if AWS credentials are found
if uu.check_aws_creds():
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log("Changing output directory and file name pattern based on sensitivity analysis")
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type, output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Creates a single filename pattern to pass to the multiprocessor call
pattern = output_pattern_list[0]
# Creates gain year count tiles using only pixels that had only loss
# count/3 maxes out at about 300 GB
if cn.count == 96:
processes = 90 # 66 = 310 GB peak; 75 = 380 GB peak; 90 = 480 GB peak
else:
processes = int(cn.count/2)
uu.print_log('Gain year count loss only pixels max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_loss_only,
sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
if cn.count == 96:
processes = 90 # 66 = 330 GB peak; 75 = 380 GB peak; 90 = 530 GB peak
else:
processes = int(cn.count/2)
uu.print_log('Gain year count gain only pixels max processors=', processes)
pool = multiprocessing.Pool(processes)
if sensit_type == 'maxgain':
# Creates gain year count tiles using only pixels that had only gain
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_gain_only_maxgain,
sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
if sensit_type == 'legal_Amazon_loss':
uu.print_log("Gain-only pixels do not apply to legal_Amazon_loss sensitivity analysis. Skipping this step.")
else:
# Creates gain year count tiles using only pixels that had only gain
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_gain_only_standard,
sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
# Creates gain year count tiles using only pixels that had neither loss nor gain pixels
if cn.count == 96:
processes = 90 # 66 = 360 GB peak; 88 = 430 GB peak; 90 = 510 GB peak
else:
processes = int(cn.count/2)
uu.print_log('Gain year count no change pixels max processors=', processes)
pool = multiprocessing.Pool(processes)
if sensit_type == 'legal_Amazon_loss':
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_no_change_legal_Amazon_loss,
sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
else:
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_no_change_standard,
sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
if cn.count == 96:
processes = 90 # 66 = 370 GB peak; 88 = 430 GB peak; 90 = 550 GB peak
else:
processes = int(cn.count/2)
uu.print_log('Gain year count loss & gain pixels max processors=', processes)
pool = multiprocessing.Pool(processes)
if sensit_type == 'maxgain':
# Creates gain year count tiles using only pixels that had only gain
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_loss_and_gain_maxgain,
sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
else:
# Creates gain year count tiles using only pixels that had only gain
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_loss_and_gain_standard,
sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
# Combines the four above gain year count tiles for each Hansen tile into a single output tile
if cn.count == 96:
processes = 84 # 28 processors = 220 GB peak; 62 = 470 GB peak; 78 = 600 GB peak; 80 = 620 GB peak; 84 = XXX GB peak
elif cn.count < 4:
processes = 1
else:
processes = int(cn.count/4)
uu.print_log('Gain year count gain merge all combos max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(partial(gain_year_count_all_forest_types.create_gain_year_count_merge,
pattern=pattern, sensit_type=sensit_type, no_upload=no_upload), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# gain_year_count_all_forest_types.create_gain_year_count_loss_only(tile_id, no_upload)
#
# for tile_id in tile_id_list:
# if sensit_type == 'maxgain':
# gain_year_count_all_forest_types.create_gain_year_count_gain_only_maxgain(tile_id, no_upload)
# else:
# gain_year_count_all_forest_types.create_gain_year_count_gain_only_standard(tile_id, no_upload)
#
# for tile_id in tile_id_list:
# gain_year_count_all_forest_types.create_gain_year_count_no_change_standard(tile_id, no_upload)
#
# for tile_id in tile_id_list:
# if sensit_type == 'maxgain':
# gain_year_count_all_forest_types.create_gain_year_count_loss_and_gain_maxgain(tile_id, no_upload)
# else:
# gain_year_count_all_forest_types.create_gain_year_count_loss_and_gain_standard(tile_id, no_upload)
#
# for tile_id in tile_id_list:
# gain_year_count_all_forest_types.create_gain_year_count_merge(tile_id, pattern, sensit_type, no_upload)
# If no_upload flag is not activated, output is uploaded
if not no_upload:
# Intermediate output tiles for checking outputs
uu.upload_final_set(output_dir_list[0], "growth_years_loss_only")
uu.upload_final_set(output_dir_list[0], "growth_years_gain_only")
uu.upload_final_set(output_dir_list[0], "growth_years_no_change")
uu.upload_final_set(output_dir_list[0], "growth_years_loss_and_gain")
# This is the final output used later in the model
uu.upload_final_set(output_dir_list[0], output_pattern_list[0])
def main():
no_upload = False
sensit_type = "legal_Amazon_loss"
# Create the output log
uu.initiate_log()
os.chdir(cn.docker_base_dir)
Brazil_stages = ['all', 'create_forest_extent', 'create_loss']
# The argument for what kind of model run is being done: standard conditions or a sensitivity analysis run
parser = argparse.ArgumentParser(
description=
'Create tiles of forest extent in legal Amazon in 2000 and annual loss according to PRODES'
)
parser.add_argument(
'--stages',
'-s',
required=True,
help=
'Stages of creating Brazil legal Amazon-specific gross cumulative removals. Options are {}'
.format(Brazil_stages))
parser.add_argument(
'--run_through',
'-r',
required=True,
help=
'Options: true or false. true: run named stage and following stages. false: run only named stage.'
)
args = parser.parse_args()
stage_input = args.stages
run_through = args.run_through
# Checks the validity of the two arguments. If either one is invalid, the script ends.
if (stage_input not in Brazil_stages):
uu.exception_log(
no_upload, 'Invalid stage selection. Please provide a stage from',
Brazil_stages)
else:
pass
if (run_through not in ['true', 'false']):
uu.exception_log(
no_upload,
'Invalid run through option. Please enter true or false.')
else:
pass
actual_stages = uu.analysis_stages(Brazil_stages, stage_input, run_through,
sensit_type)
uu.print_log(actual_stages)
# By definition, this script is for US-specific removals
sensit_type = 'legal_Amazon_loss'
# List of output directories and output file name patterns
master_output_dir_list = [
cn.Brazil_forest_extent_2000_processed_dir,
cn.Brazil_annual_loss_processed_dir
]
master_output_pattern_list = [
cn.pattern_Brazil_forest_extent_2000_processed,
cn.pattern_Brazil_annual_loss_processed
]
# Creates forest extent 2000 raster from multiple PRODES forest extent rasters
###NOTE: Didn't redo this for model v1.2.0, so I don't know if it still works.
if 'create_forest_extent' in actual_stages:
uu.print_log('Creating forest extent tiles')
# List of tiles that could be run. This list is only used to create the FIA region tiles if they don't already exist.
tile_id_list = uu.tile_list_s3(cn.WHRC_biomass_2000_unmasked_dir)
# tile_id_list = ["00N_000E", "00N_050W", "00N_060W", "00N_010E", "00N_020E", "00N_030E", "00N_040E", "10N_000E", "10N_010E", "10N_010W", "10N_020E", "10N_020W"] # test tiles
# tile_id_list = ['50N_130W'] # test tiles
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
# Downloads input rasters and lists them
uu.s3_folder_download(cn.Brazil_forest_extent_2000_raw_dir,
cn.docker_base_dir, sensit_type)
raw_forest_extent_inputs = glob.glob(
'*_AMZ_warped_*tif') # The list of tiles to merge
# Gets the resolution of a more recent PRODES raster, which has a higher resolution. The merged output matches that.
raw_forest_extent_input_2019 = glob.glob('*2019_AMZ_warped_*tif')
prodes_2019 = gdal.Open(raw_forest_extent_input_2019[0])
transform_2019 = prodes_2019.GetGeoTransform()
pixelSizeX = transform_2019[1]
pixelSizeY = -transform_2019[5]
uu.print_log(pixelSizeX)
uu.print_log(pixelSizeY)
# This merges all six rasters together, so it takes a lot of memory and time. It seems to repeatedly max out
# at about 300 GB as it progresses abot 15% each time; then the memory drops back to 0 and slowly increases.
cmd = [
'gdal_merge.py', '-o',
'{}.tif'.format(cn.pattern_Brazil_forest_extent_2000_merged),
'-co', 'COMPRESS=LZW', '-a_nodata', '0', '-n', '0', '-ot', 'Byte',
'-ps', '{}'.format(pixelSizeX), '{}'.format(pixelSizeY),
raw_forest_extent_inputs[0], raw_forest_extent_inputs[1],
raw_forest_extent_inputs[2], raw_forest_extent_inputs[3],
raw_forest_extent_inputs[4], raw_forest_extent_inputs[5]
]
uu.log_subprocess_output_full(cmd)
# Uploads the merged forest extent raster to s3 for future reference
uu.upload_final_set(cn.Brazil_forest_extent_2000_merged_dir,
cn.pattern_Brazil_forest_extent_2000_merged)
# Creates legal Amazon extent 2000 tiles
source_raster = '{}.tif'.format(
cn.pattern_Brazil_forest_extent_2000_merged)
out_pattern = cn.pattern_Brazil_forest_extent_2000_processed
dt = 'Byte'
pool = multiprocessing.Pool(int(cn.count / 2))
pool.map(
partial(uu.mp_warp_to_Hansen,
source_raster=source_raster,
out_pattern=out_pattern,
dt=dt,
no_upload=no_upload), tile_id_list)
# Checks if each tile has data in it. Only tiles with data are uploaded.
upload_dir = master_output_dir_list[0]
pattern = master_output_pattern_list[0]
pool = multiprocessing.Pool(cn.count - 5)
pool.map(
partial(uu.check_and_upload,
upload_dir=upload_dir,
pattern=pattern), tile_id_list)
# Creates annual loss raster for 2001-2019 from multiples PRODES rasters
if 'create_loss' in actual_stages:
uu.print_log('Creating annual PRODES loss tiles')
tile_id_list = uu.tile_list_s3(
cn.Brazil_forest_extent_2000_processed_dir)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
# Downloads input rasters and lists them
cmd = [
'aws', 's3', 'cp', cn.Brazil_annual_loss_raw_dir, '.',
'--recursive'
]
uu.log_subprocess_output_full(cmd)
uu.print_log(
"Input loss rasters downloaded. Getting resolution of recent raster..."
)
# Gets the resolution of the more recent PRODES raster, which has a higher resolution. The merged output matches that.
raw_forest_extent_input_2019 = glob.glob('Prodes2019_*tif')
prodes_2019 = gdal.Open(raw_forest_extent_input_2019[0])
transform_2019 = prodes_2019.GetGeoTransform()
pixelSizeX = transform_2019[1]
pixelSizeY = -transform_2019[5]
uu.print_log(" Recent raster resolution: {0} by {1}".format(
pixelSizeX, pixelSizeY))
# This merges both loss rasters together, so it takes a lot of memory and time. It seems to max out
# at about 180 GB, then go back to 0.
# This took about 8 minutes.
uu.print_log(
"Merging input loss rasters into a composite for all years...")
cmd = [
'gdal_merge.py', '-o',
'{}.tif'.format(cn.pattern_Brazil_annual_loss_merged), '-co',
'COMPRESS=LZW', '-a_nodata', '0', '-n', '0', '-ot', 'Byte', '-ps',
'{}'.format(pixelSizeX), '{}'.format(pixelSizeY),
'Prodes2019_annual_loss_2008_2019.tif',
'Prodes2014_annual_loss_2001_2007.tif'
]
uu.log_subprocess_output_full(cmd)
uu.print_log(" Loss rasters combined into composite")
# Uploads the merged loss raster to s3 for future reference
uu.upload_final_set(cn.Brazil_annual_loss_merged_dir,
cn.pattern_Brazil_annual_loss_merged)
# Creates annual loss 2001-2015 tiles
uu.print_log("Warping composite PRODES loss to Hansen tiles...")
source_raster = '{}.tif'.format(cn.pattern_Brazil_annual_loss_merged)
out_pattern = cn.pattern_Brazil_annual_loss_processed
dt = 'Byte'
pool = multiprocessing.Pool(int(cn.count / 2))
pool.map(
partial(uu.mp_warp_to_Hansen,
source_raster=source_raster,
out_pattern=out_pattern,
dt=dt,
no_upload=no_upload), tile_id_list)
uu.print_log(" PRODES composite loss raster warped to Hansen tiles")
# Checks if each tile has data in it. Only tiles with data are uploaded.
# In practice, every Amazon tile has loss in it but I figured I'd do this just to be thorough.
upload_dir = master_output_dir_list[1]
pattern = master_output_pattern_list[1]
pool = multiprocessing.Pool(cn.count - 5)
pool.map(
partial(uu.check_and_upload,
upload_dir=upload_dir,
pattern=pattern), tile_id_list)
# Creates forest age category tiles
if 'forest_age_category' in actual_stages:
uu.print_log('Creating forest age category tiles')
# Files to download for this script.
download_dict = {
cn.Brazil_annual_loss_processed_dir:
[cn.pattern_Brazil_annual_loss_processed],
cn.gain_dir: [cn.pattern_gain],
cn.WHRC_biomass_2000_non_mang_non_planted_dir:
[cn.pattern_WHRC_biomass_2000_non_mang_non_planted],
cn.planted_forest_type_unmasked_dir:
[cn.pattern_planted_forest_type_unmasked],
cn.mangrove_biomass_2000_dir: [cn.pattern_mangrove_biomass_2000],
cn.Brazil_forest_extent_2000_processed_dir:
[cn.pattern_Brazil_forest_extent_2000_processed]
}
tile_id_list = uu.tile_list_s3(
cn.Brazil_forest_extent_2000_processed_dir)
# tile_id_list = ['00N_050W']
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
stage_output_dir_list = uu.alter_dirs(sensit_type,
master_output_dir_list)
stage_output_pattern_list = uu.alter_patterns(
sensit_type, master_output_pattern_list)
output_pattern = stage_output_pattern_list[2]
# This configuration of the multiprocessing call is necessary for passing multiple arguments to the main function
# It is based on the example here: http://spencerimp.blogspot.com/2015/12/python-multiprocess-with-multiple.html
# With processes=30, peak usage was about 350 GB using WHRC AGB.
# processes=26 maxes out above 480 GB for biomass_swap, so better to use fewer than that.
pool = multiprocessing.Pool(int(cn.count / 2))
pool.map(
partial(legal_AMZ_loss.legal_Amazon_forest_age_category,
sensit_type=sensit_type,
output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
#
# legal_AMZ_loss.legal_Amazon_forest_age_category(tile_id, sensit_type, output_pattern)
# Uploads output from this stage
uu.upload_final_set(stage_output_dir_list[2],
stage_output_pattern_list[2])
# Creates tiles of the number of years of removals
if 'gain_year_count' in actual_stages:
uu.print_log('Creating gain year count tiles for natural forest')
# Files to download for this script.
download_dict = {
cn.Brazil_annual_loss_processed_dir:
[cn.pattern_Brazil_annual_loss_processed],
cn.gain_dir: [cn.pattern_gain],
cn.WHRC_biomass_2000_non_mang_non_planted_dir:
[cn.pattern_WHRC_biomass_2000_non_mang_non_planted],
cn.planted_forest_type_unmasked_dir:
[cn.pattern_planted_forest_type_unmasked],
cn.mangrove_biomass_2000_dir: [cn.pattern_mangrove_biomass_2000],
cn.Brazil_forest_extent_2000_processed_dir:
[cn.pattern_Brazil_forest_extent_2000_processed]
}
tile_id_list = uu.tile_list_s3(
cn.Brazil_forest_extent_2000_processed_dir)
# tile_id_list = ['00N_050W']
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
stage_output_dir_list = uu.alter_dirs(sensit_type,
master_output_dir_list)
stage_output_pattern_list = uu.alter_patterns(
sensit_type, master_output_pattern_list)
output_pattern = stage_output_pattern_list[3]
pool = multiprocessing.Pool(int(cn.count / 3))
pool.map(
partial(
legal_AMZ_loss.legal_Amazon_create_gain_year_count_loss_only,
sensit_type=sensit_type), tile_id_list)
pool.map(
partial(
legal_AMZ_loss.legal_Amazon_create_gain_year_count_no_change,
sensit_type=sensit_type), tile_id_list)
pool.map(
partial(legal_AMZ_loss.
legal_Amazon_create_gain_year_count_loss_and_gain_standard,
sensit_type=sensit_type), tile_id_list)
pool = multiprocessing.Pool(
int(cn.count / 8)
) # count/5 uses more than 160GB of memory. count/8 uses about 120GB of memory.
pool.map(
partial(legal_AMZ_loss.legal_Amazon_create_gain_year_count_merge,
output_pattern=output_pattern), tile_id_list)
# # For single processor use
# for tile_id in tile_id_list:
# legal_AMZ_loss.legal_Amazon_create_gain_year_count_loss_only(tile_id, sensit_type)
#
# for tile_id in tile_id_list:
# legal_AMZ_loss.legal_Amazon_create_gain_year_count_no_change(tile_id, sensit_type)
#
# for tile_id in tile_id_list:
# legal_AMZ_loss.legal_Amazon_create_gain_year_count_loss_and_gain_standard(tile_id, sensit_type)
#
# for tile_id in tile_id_list:
# legal_AMZ_loss.legal_Amazon_create_gain_year_count_merge(tile_id, output_pattern)
# Intermediate output tiles for checking outputs
uu.upload_final_set(stage_output_dir_list[3], "growth_years_loss_only")
uu.upload_final_set(stage_output_dir_list[3], "growth_years_gain_only")
uu.upload_final_set(stage_output_dir_list[3], "growth_years_no_change")
uu.upload_final_set(stage_output_dir_list[3],
"growth_years_loss_and_gain")
# Uploads output from this stage
uu.upload_final_set(stage_output_dir_list[3],
stage_output_pattern_list[3])
# Creates tiles of annual AGB and BGB gain rate for non-mangrove, non-planted forest using the standard model
# removal function
if 'annual_removals' in actual_stages:
uu.print_log('Creating annual removals for natural forest')
# Files to download for this script.
download_dict = {
cn.age_cat_IPCC_dir: [cn.pattern_age_cat_IPCC],
cn.cont_eco_dir: [cn.pattern_cont_eco_processed],
cn.plant_pre_2000_processed_dir: [cn.pattern_plant_pre_2000]
}
tile_id_list = uu.tile_list_s3(
cn.Brazil_forest_extent_2000_processed_dir)
# tile_id_list = ['00N_050W']
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
# If the model run isn't the standard one, the output directory and file names are changed.
# This adapts just the relevant items in the output directory and pattern lists (annual removals).
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
stage_output_dir_list = uu.alter_dirs(sensit_type,
master_output_dir_list[4:6])
stage_output_pattern_list = uu.alter_patterns(
sensit_type, master_output_pattern_list[4:6])
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# Table with IPCC Table 4.9 default gain rates
cmd = [
'aws', 's3', 'cp',
os.path.join(cn.gain_spreadsheet_dir, cn.gain_spreadsheet),
cn.docker_base_dir
]
# Solution for adding subprocess output to log is from https://stackoverflow.com/questions/21953835/run-subprocess-and-print-output-to-logging
process = Popen(cmd, stdout=PIPE, stderr=STDOUT)
with process.stdout:
uu.log_subprocess_output(process.stdout)
pd.options.mode.chained_assignment = None
# Imports the table with the ecozone-continent codes and the carbon gain rates
gain_table = pd.read_excel(
"{}".format(cn.gain_spreadsheet),
sheet_name="natrl fores gain, for std model")
# Removes rows with duplicate codes (N. and S. America for the same ecozone)
gain_table_simplified = gain_table.drop_duplicates(subset='gainEcoCon',
keep='first')
# Converts gain table from wide to long, so each continent-ecozone-age category has its own row
gain_table_cont_eco_age = pd.melt(gain_table_simplified,
id_vars=['gainEcoCon'],
value_vars=[
'growth_primary',
'growth_secondary_greater_20',
'growth_secondary_less_20'
])
gain_table_cont_eco_age = gain_table_cont_eco_age.dropna()
# Creates a table that has just the continent-ecozone combinations for adding to the dictionary.
# These will be used whenever there is just a continent-ecozone pixel without a forest age pixel.
# Assigns removal rate of 0 when there's no age category.
gain_table_con_eco_only = gain_table_cont_eco_age
gain_table_con_eco_only = gain_table_con_eco_only.drop_duplicates(
subset='gainEcoCon', keep='first')
gain_table_con_eco_only['value'] = 0
gain_table_con_eco_only['cont_eco_age'] = gain_table_con_eco_only[
'gainEcoCon']
# Creates a code for each age category so that each continent-ecozone-age combo can have its own unique value
age_dict = {
'growth_primary': 10000,
'growth_secondary_greater_20': 20000,
'growth_secondary_less_20': 30000
}
# Creates a unique value for each continent-ecozone-age category
gain_table_cont_eco_age = gain_table_cont_eco_age.replace(
{"variable": age_dict})
gain_table_cont_eco_age['cont_eco_age'] = gain_table_cont_eco_age[
'gainEcoCon'] + gain_table_cont_eco_age['variable']
# Merges the table of just continent-ecozone codes and the table of continent-ecozone-age codes
gain_table_all_combos = pd.concat(
[gain_table_con_eco_only, gain_table_cont_eco_age])
# Converts the continent-ecozone-age codes and corresponding gain rates to a dictionary
gain_table_dict = pd.Series(
gain_table_all_combos.value.values,
index=gain_table_all_combos.cont_eco_age).to_dict()
# Adds a dictionary entry for where the ecozone-continent-age code is 0 (not in a continent)
gain_table_dict[0] = 0
# Adds a dictionary entry for each forest age code for pixels that have forest age but no continent-ecozone
for key, value in age_dict.items():
gain_table_dict[value] = 0
# Converts all the keys (continent-ecozone-age codes) to float type
gain_table_dict = {
float(key): value
for key, value in gain_table_dict.items()
}
uu.print_log(gain_table_dict)
# This configuration of the multiprocessing call is necessary for passing multiple arguments to the main function
# It is based on the example here: http://spencerimp.blogspot.com/2015/12/python-multiprocess-with-multiple.html
# processes=24 peaks at about 440 GB of memory on an r4.16xlarge machine
output_pattern_list = stage_output_pattern_list
pool = multiprocessing.Pool(int(cn.count / 2))
pool.map(
partial(annual_gain_rate_natrl_forest.annual_gain_rate,
sensit_type=sensit_type,
gain_table_dict=gain_table_dict,
output_pattern_list=output_pattern_list), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile in tile_id_list:
#
# annual_gain_rate_natrl_forest.annual_gain_rate(tile, sensit_type, gain_table_dict, stage_output_pattern_list)
# Uploads outputs from this stage
for i in range(0, len(stage_output_dir_list)):
uu.upload_final_set(stage_output_dir_list[i],
stage_output_pattern_list[i])
# Creates tiles of cumulative AGCO2 and BGCO2 gain rate for non-mangrove, non-planted forest using the standard model
# removal function
if 'cumulative_removals' in actual_stages:
uu.print_log('Creating cumulative removals for natural forest')
# Files to download for this script.
download_dict = {
cn.annual_gain_AGB_IPCC_defaults_dir:
[cn.pattern_annual_gain_AGB_IPCC_defaults],
cn.annual_gain_BGB_natrl_forest_dir:
[cn.pattern_annual_gain_BGB_natrl_forest],
cn.gain_year_count_natrl_forest_dir:
[cn.pattern_gain_year_count_natrl_forest]
}
tile_id_list = uu.tile_list_s3(
cn.Brazil_forest_extent_2000_processed_dir)
# tile_id_list = ['00N_050W']
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
# If the model run isn't the standard one, the output directory and file names are changed.
# This adapts just the relevant items in the output directory and pattern lists (cumulative removals).
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
stage_output_dir_list = uu.alter_dirs(sensit_type,
master_output_dir_list[6:8])
stage_output_pattern_list = uu.alter_patterns(
sensit_type, master_output_pattern_list[6:8])
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# Calculates cumulative aboveground carbon gain in non-mangrove planted forests
output_pattern_list = stage_output_pattern_list
pool = multiprocessing.Pool(int(cn.count / 3))
pool.map(
partial(cumulative_gain_natrl_forest.cumulative_gain_AGCO2,
output_pattern_list=output_pattern_list,
sensit_type=sensit_type), tile_id_list)
# Calculates cumulative belowground carbon gain in non-mangrove planted forests
pool = multiprocessing.Pool(int(cn.count / 3))
pool.map(
partial(cumulative_gain_natrl_forest.cumulative_gain_BGCO2,
output_pattern_list=output_pattern_list,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# cumulative_gain_natrl_forest.cumulative_gain_AGCO2(tile_id, stage_output_pattern_list[0], sensit_type)
#
# for tile_id in tile_id_list:
# cumulative_gain_natrl_forest.cumulative_gain_BGCO2(tile_id, stage_output_pattern_list[1], sensit_type)
# Uploads outputs from this stage
for i in range(0, len(stage_output_dir_list)):
uu.upload_final_set(stage_output_dir_list[i],
stage_output_pattern_list[i])
# Creates tiles of annual gain rate and cumulative removals for all forest types (above + belowground)
if 'removals_merged' in actual_stages:
uu.print_log(
'Creating annual and cumulative removals for all forest types combined (above + belowground)'
)
# Files to download for this script
download_dict = {
cn.annual_gain_AGB_mangrove_dir:
[cn.pattern_annual_gain_AGB_mangrove],
cn.annual_gain_AGB_planted_forest_non_mangrove_dir:
[cn.pattern_annual_gain_AGB_planted_forest_non_mangrove],
cn.annual_gain_AGB_IPCC_defaults_dir:
[cn.pattern_annual_gain_AGB_IPCC_defaults],
cn.annual_gain_BGB_mangrove_dir:
[cn.pattern_annual_gain_BGB_mangrove],
cn.annual_gain_BGB_planted_forest_non_mangrove_dir:
[cn.pattern_annual_gain_BGB_planted_forest_non_mangrove],
cn.annual_gain_BGB_natrl_forest_dir:
[cn.pattern_annual_gain_BGB_natrl_forest],
cn.cumul_gain_AGCO2_mangrove_dir:
[cn.pattern_cumul_gain_AGCO2_mangrove],
cn.cumul_gain_AGCO2_planted_forest_non_mangrove_dir:
[cn.pattern_cumul_gain_AGCO2_planted_forest_non_mangrove],
cn.cumul_gain_AGCO2_natrl_forest_dir:
[cn.pattern_cumul_gain_AGCO2_natrl_forest],
cn.cumul_gain_BGCO2_mangrove_dir:
[cn.pattern_cumul_gain_BGCO2_mangrove],
cn.cumul_gain_BGCO2_planted_forest_non_mangrove_dir:
[cn.pattern_cumul_gain_BGCO2_planted_forest_non_mangrove],
cn.cumul_gain_BGCO2_natrl_forest_dir:
[cn.pattern_cumul_gain_BGCO2_natrl_forest]
}
tile_id_list = uu.tile_list_s3(
cn.Brazil_forest_extent_2000_processed_dir)
# tile_id_list = ['00N_050W']
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
# If the model run isn't the standard one, the output directory and file names are changed.
# This adapts just the relevant items in the output directory and pattern lists (cumulative removals).
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
stage_output_dir_list = uu.alter_dirs(sensit_type,
master_output_dir_list[8:10])
stage_output_pattern_list = uu.alter_patterns(
sensit_type, master_output_pattern_list[8:10])
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# For multiprocessing
output_pattern_list = stage_output_pattern_list
pool = multiprocessing.Pool(int(cn.count / 3))
pool.map(
partial(merge_cumulative_annual_gain_all_forest_types.gain_merge,
output_pattern_list=output_pattern_list,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# merge_cumulative_annual_gain_all_forest_types.gain_merge(tile_id, output_pattern_list, sensit_type)
# Uploads output tiles to s3
for i in range(0, len(stage_output_dir_list)):
uu.upload_final_set(stage_output_dir_list[i],
stage_output_pattern_list[i])
# Creates carbon emitted_pools in loss year
if 'carbon_pools' in actual_stages:
uu.print_log('Creating emissions year carbon emitted_pools')
# Specifies that carbon emitted_pools are created for loss year rather than in 2000
extent = 'loss'
# Files to download for this script
download_dict = {
cn.mangrove_biomass_2000_dir: [cn.pattern_mangrove_biomass_2000],
cn.cont_eco_dir: [cn.pattern_cont_eco_processed],
cn.bor_tem_trop_processed_dir: [cn.pattern_bor_tem_trop_processed],
cn.precip_processed_dir: [cn.pattern_precip],
cn.elevation_processed_dir: [cn.pattern_elevation],
cn.soil_C_full_extent_2000_dir:
[cn.pattern_soil_C_full_extent_2000],
cn.gain_dir: [cn.pattern_gain],
cn.cumul_gain_AGCO2_mangrove_dir:
[cn.pattern_cumul_gain_AGCO2_mangrove],
cn.cumul_gain_AGCO2_planted_forest_non_mangrove_dir:
[cn.pattern_cumul_gain_AGCO2_planted_forest_non_mangrove],
cn.cumul_gain_AGCO2_natrl_forest_dir:
[cn.pattern_cumul_gain_AGCO2_natrl_forest],
cn.annual_gain_AGB_mangrove_dir:
[cn.pattern_annual_gain_AGB_mangrove],
cn.annual_gain_AGB_planted_forest_non_mangrove_dir:
[cn.pattern_annual_gain_AGB_planted_forest_non_mangrove],
cn.annual_gain_AGB_IPCC_defaults_dir:
[cn.pattern_annual_gain_AGB_IPCC_defaults]
}
# Adds the correct AGB tiles to the download dictionary depending on the model run
if sensit_type == 'biomass_swap':
download_dict[cn.JPL_processed_dir] = [
cn.pattern_JPL_unmasked_processed
]
else:
download_dict[cn.WHRC_biomass_2000_unmasked_dir] = [
cn.pattern_WHRC_biomass_2000_unmasked
]
# Adds the correct loss tile to the download dictionary depending on the model run
if sensit_type == 'legal_Amazon_loss':
download_dict[cn.Brazil_annual_loss_processed_dir] = [
cn.pattern_Brazil_annual_loss_processed
]
else:
download_dict[cn.loss_dir] = ['']
tile_id_list = uu.tile_list_s3(
cn.Brazil_forest_extent_2000_processed_dir)
# tile_id_list = ['00N_050W']
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
stage_output_dir_list = uu.alter_dirs(
sensit_type, master_output_dir_list[10:16])
stage_output_pattern_list = uu.alter_patterns(
sensit_type, master_output_pattern_list[10:16])
# Table with IPCC Wetland Supplement Table 4.4 default mangrove gain rates
cmd = [
'aws', 's3', 'cp',
os.path.join(cn.gain_spreadsheet_dir, cn.gain_spreadsheet),
cn.docker_base_dir
]
# Solution for adding subprocess output to log is from https://stackoverflow.com/questions/21953835/run-subprocess-and-print-output-to-logging
process = Popen(cmd, stdout=PIPE, stderr=STDOUT)
with process.stdout:
uu.log_subprocess_output(process.stdout)
pd.options.mode.chained_assignment = None
# Imports the table with the ecozone-continent codes and the carbon gain rates
gain_table = pd.read_excel("{}".format(cn.gain_spreadsheet),
sheet_name="mangrove gain, for model")
# Removes rows with duplicate codes (N. and S. America for the same ecozone)
gain_table_simplified = gain_table.drop_duplicates(subset='gainEcoCon',
keep='first')
mang_BGB_AGB_ratio = create_carbon_pools.mangrove_pool_ratio_dict(
gain_table_simplified, cn.below_to_above_trop_dry_mang,
cn.below_to_above_trop_wet_mang, cn.below_to_above_subtrop_mang)
mang_deadwood_AGB_ratio = create_carbon_pools.mangrove_pool_ratio_dict(
gain_table_simplified, cn.deadwood_to_above_trop_dry_mang,
cn.deadwood_to_above_trop_wet_mang,
cn.deadwood_to_above_subtrop_mang)
mang_litter_AGB_ratio = create_carbon_pools.mangrove_pool_ratio_dict(
gain_table_simplified, cn.litter_to_above_trop_dry_mang,
cn.litter_to_above_trop_wet_mang, cn.litter_to_above_subtrop_mang)
if extent == 'loss':
uu.print_log(
"Creating tiles of emitted aboveground carbon (carbon 2000 + carbon accumulation until loss year)"
)
# 16 processors seems to use more than 460 GB-- I don't know exactly how much it uses because I stopped it at 460
# 14 processors maxes out at 410-415 GB
# Creates a single filename pattern to pass to the multiprocessor call
pattern = stage_output_pattern_list[0]
pool = multiprocessing.Pool(int(cn.count / 4))
pool.map(
partial(create_carbon_pools.create_emitted_AGC,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_emitted_AGC(tile_id, stage_output_pattern_list[0], sensit_type)
uu.upload_final_set(stage_output_dir_list[0],
stage_output_pattern_list[0])
elif extent == '2000':
uu.print_log("Creating tiles of aboveground carbon in 2000")
# 16 processors seems to use more than 460 GB-- I don't know exactly how much it uses because I stopped it at 460
# 14 processors maxes out at 415 GB
# Creates a single filename pattern to pass to the multiprocessor call
pattern = stage_output_pattern_list[0]
pool = multiprocessing.Pool(processes=14)
pool.map(
partial(create_carbon_pools.create_2000_AGC,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_2000_AGC(tile_id, output_pattern_list[0], sensit_type)
uu.upload_final_set(stage_output_dir_list[0],
stage_output_pattern_list[0])
else:
uu.exception_log(no_upload, "Extent argument not valid")
uu.print_log("Creating tiles of belowground carbon")
# 18 processors used between 300 and 400 GB memory, so it was okay on a r4.16xlarge spot machine
# Creates a single filename pattern to pass to the multiprocessor call
pattern = stage_output_pattern_list[1]
pool = multiprocessing.Pool(int(cn.count / 2))
pool.map(
partial(create_carbon_pools.create_BGC,
mang_BGB_AGB_ratio=mang_BGB_AGB_ratio,
extent=extent,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_BGC(tile_id, mang_BGB_AGB_ratio, extent, stage_output_pattern_list[1], sensit_type)
uu.upload_final_set(stage_output_dir_list[1],
stage_output_pattern_list[1])
uu.print_log("Creating tiles of deadwood carbon")
# processes=16 maxes out at about 430 GB
# Creates a single filename pattern to pass to the multiprocessor call
pattern = stage_output_pattern_list[2]
pool = multiprocessing.Pool(int(cn.count / 4))
pool.map(
partial(create_carbon_pools.create_deadwood,
mang_deadwood_AGB_ratio=mang_deadwood_AGB_ratio,
extent=extent,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_deadwood(tile_id, mang_deadwood_AGB_ratio, extent, stage_output_pattern_list[2], sensit_type)
uu.upload_final_set(stage_output_dir_list[2],
stage_output_pattern_list[2])
uu.print_log("Creating tiles of litter carbon")
# Creates a single filename pattern to pass to the multiprocessor call
pattern = stage_output_pattern_list[3]
pool = multiprocessing.Pool(int(cn.count / 4))
pool.map(
partial(create_carbon_pools.create_litter,
mang_litter_AGB_ratio=mang_litter_AGB_ratio,
extent=extent,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_litter(tile_id, mang_litter_AGB_ratio, extent, stage_output_pattern_list[3], sensit_type)
uu.upload_final_set(stage_output_dir_list[3],
stage_output_pattern_list[3])
if extent == 'loss':
uu.print_log("Creating tiles of soil carbon")
# Creates a single filename pattern to pass to the multiprocessor call
pattern = stage_output_pattern_list[4]
pool = multiprocessing.Pool(int(cn.count / 3))
pool.map(
partial(create_carbon_pools.create_soil,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_soil(tile_id, stage_output_pattern_list[4], sensit_type)
uu.upload_final_set(stage_output_dir_list[4],
stage_output_pattern_list[4])
elif extent == '2000':
uu.print_log("Skipping soil for 2000 carbon pool calculation")
else:
uu.exception_log(no_upload, "Extent argument not valid")
uu.print_log("Creating tiles of total carbon")
# I tried several different processor numbers for this. Ended up using 14 processors, which used about 380 GB memory
# at peak. Probably could've handled 16 processors on an r4.16xlarge machine but I didn't feel like taking the time to check.
# Creates a single filename pattern to pass to the multiprocessor call
pattern = stage_output_pattern_list[5]
pool = multiprocessing.Pool(int(cn.count / 4))
pool.map(
partial(create_carbon_pools.create_total_C,
extent=extent,
pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_total_C(tile_id, extent, stage_output_pattern_list[5], sensit_type)
uu.upload_final_set(stage_output_dir_list[5],
stage_output_pattern_list[5])
def mp_prep_other_inputs(tile_id_list, run_date, no_upload=None):
os.chdir(cn.docker_base_dir)
sensit_type = 'std'
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model
### BUG: THIS SHOULD ALSO INCLUDE cn.annual_gain_AGC_BGC_planted_forest_unmasked_dir IN ITS LIST
tile_id_list = uu.create_combined_tile_list(
cn.WHRC_biomass_2000_unmasked_dir,
cn.mangrove_biomass_2000_dir,
set3=cn.gain_dir)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
'''
Before processing the driver, it needs to be reprojected from Goode Homolosine to WGS84.
gdal_warp is producing a weird output, so I did it in ArcMap for the 2020 update,
with the output cell size being 0.01 x 0.01 degree and the method being nearest.
arcpy.ProjectRaster_management(in_raster="C:/GIS/Drivers of loss/2020_drivers__tif__from_Forrest_Follett_20210323/FinalClassification_2020_v2__from_Jimmy_MacCarthy_20210323.tif",
out_raster="C:/GIS/Drivers of loss/2020_drivers__tif__from_Forrest_Follett_20210323/Final_Classification_2020__reproj_nearest_0-005_0-005_deg__20210323.tif",
out_coor_system="GEOGCS['GCS_WGS_1984',DATUM['D_WGS_1984',SPHEROID['WGS_1984',6378137.0,298.257223563]],PRIMEM['Greenwich',0.0],UNIT['Degree',0.0174532925199433]]",
resampling_type="NEAREST", cell_size="0.005 0.005", geographic_transform="",
Registration_Point="",
in_coor_system="PROJCS['WGS_1984_Goode_Homolosine',GEOGCS['GCS_unknown',DATUM['D_WGS_1984',SPHEROID['WGS_1984',6378137.0,298.257223563]],PRIMEM['Greenwich',0.0],UNIT['Degree',0.0174532925199433]],PROJECTION['Goode_Homolosine'],PARAMETER['False_Easting',0.0],PARAMETER['False_Northing',0.0],PARAMETER['Central_Meridian',0.0],PARAMETER['Option',1.0],UNIT['Meter',1.0]]",
vertical="NO_VERTICAL")
'''
# List of output directories and output file name patterns
output_dir_list = [
# cn.climate_zone_processed_dir, cn.plant_pre_2000_processed_dir,
cn.drivers_processed_dir
# cn.ifl_primary_processed_dir,
# cn.annual_gain_AGC_natrl_forest_young_dir,
# cn.stdev_annual_gain_AGC_natrl_forest_young_dir,
# cn.annual_gain_AGC_BGC_natrl_forest_Europe_dir,
# cn.stdev_annual_gain_AGC_BGC_natrl_forest_Europe_dir,
# cn.FIA_forest_group_processed_dir,
# cn.age_cat_natrl_forest_US_dir,
# cn.FIA_regions_processed_dir
]
output_pattern_list = [
# cn.pattern_climate_zone, cn.pattern_plant_pre_2000,
cn.pattern_drivers
# cn.pattern_ifl_primary,
# cn.pattern_annual_gain_AGC_natrl_forest_young,
# cn.pattern_stdev_annual_gain_AGC_natrl_forest_young,
# cn.pattern_annual_gain_AGC_BGC_natrl_forest_Europe,
# cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_Europe,
# cn.pattern_FIA_forest_group_processed,
# cn.pattern_age_cat_natrl_forest_US,
# cn.pattern_FIA_regions_processed
]
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# # Files to process: climate zone, IDN/MYS plantations before 2000, tree cover loss drivers, combine IFL and primary forest
# uu.s3_file_download(os.path.join(cn.climate_zone_raw_dir, cn.climate_zone_raw), cn.docker_base_dir, sensit_type)
# uu.s3_file_download(os.path.join(cn.plant_pre_2000_raw_dir, '{}.zip'.format(cn.pattern_plant_pre_2000_raw)), cn.docker_base_dir, sensit_type)
uu.s3_file_download(
os.path.join(cn.drivers_raw_dir, cn.pattern_drivers_raw),
cn.docker_base_dir, sensit_type)
# uu.s3_file_download(os.path.join(cn.annual_gain_AGC_BGC_natrl_forest_Europe_raw_dir, cn.name_annual_gain_AGC_BGC_natrl_forest_Europe_raw), cn.docker_base_dir, sensit_type)
# uu.s3_file_download(os.path.join(cn.stdev_annual_gain_AGC_BGC_natrl_forest_Europe_raw_dir, cn.name_stdev_annual_gain_AGC_BGC_natrl_forest_Europe_raw), cn.docker_base_dir, sensit_type)
# uu.s3_file_download(os.path.join(cn.FIA_regions_raw_dir, cn.name_FIA_regions_raw), cn.docker_base_dir, sensit_type)
# uu.s3_file_download(os.path.join(cn.age_cat_natrl_forest_US_raw_dir, cn.name_age_cat_natrl_forest_US_raw), cn.docker_base_dir, sensit_type)
# uu.s3_file_download(os.path.join(cn.FIA_forest_group_raw_dir, cn.name_FIA_forest_group_raw), cn.docker_base_dir, sensit_type)
# # For some reason, using uu.s3_file_download or otherwise using AWSCLI as a subprocess doesn't work for this raster.
# # Thus, using wget instead.
# cmd = ['wget', '{}'.format(cn.annual_gain_AGC_natrl_forest_young_raw_URL), '-P', '{}'.format(cn.docker_base_dir)]
# process = Popen(cmd, stdout=PIPE, stderr=STDOUT)
# with process.stdout:
# uu.log_subprocess_output(process.stdout)
# uu.s3_file_download(cn.stdev_annual_gain_AGC_natrl_forest_young_raw_URL, cn.docker_base_dir, sensit_type)
# cmd = ['aws', 's3', 'cp', cn.primary_raw_dir, cn.docker_base_dir, '--recursive']
# uu.log_subprocess_output_full(cmd)
#
# uu.s3_flexible_download(cn.ifl_dir, cn.pattern_ifl, cn.docker_base_dir, sensit_type, tile_id_list)
#
# uu.print_log("Unzipping pre-2000 plantations...")
# cmd = ['unzip', '-j', '{}.zip'.format(cn.pattern_plant_pre_2000_raw)]
# uu.log_subprocess_output_full(cmd)
# Creates tree cover loss driver tiles.
# The raw driver tile should have NoData for unassigned drivers as opposed to 0 for unassigned drivers.
# For the 2020 driver update, I reclassified the 0 values as NoData in ArcMap. I also unprojected the global drivers
# map to WGS84 because running the homolosine projection that Jimmy provided was giving incorrect processed results.
source_raster = cn.pattern_drivers_raw
out_pattern = cn.pattern_drivers
dt = 'Byte'
if cn.count == 96:
processes = 87 # 45 processors = 70 GB peak; 70 = 90 GB peak; 80 = 100 GB peak; 87 = 125 GB peak
else:
processes = int(cn.count / 2)
uu.print_log(
"Creating tree cover loss driver tiles with {} processors...".format(
processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.mp_warp_to_Hansen,
source_raster=source_raster,
out_pattern=out_pattern,
dt=dt,
no_upload=no_upload), tile_id_list)
pool.close()
pool.join()
# # Creates young natural forest removal rate tiles
# source_raster = cn.name_annual_gain_AGC_natrl_forest_young_raw
# out_pattern = cn.pattern_annual_gain_AGC_natrl_forest_young
# dt = 'float32'
# if cn.count == 96:
# processes = 80 # 32 processors = 210 GB peak; 60 = 370 GB peak; 80 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating young natural forest gain rate tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
# # Creates young natural forest removal rate standard deviation tiles
# source_raster = cn.name_stdev_annual_gain_AGC_natrl_forest_young_raw
# out_pattern = cn.pattern_stdev_annual_gain_AGC_natrl_forest_young
# dt = 'float32'
# if cn.count == 96:
# processes = 80 # 32 processors = 210 GB peak; 60 = 370 GB peak; 80 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating standard deviation for young natural forest removal rate tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
#
# # Creates pre-2000 oil palm plantation tiles
# if cn.count == 96:
# processes = 80 # 45 processors = 100 GB peak; 80 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating pre-2000 oil palm plantation tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(prep_other_inputs.rasterize_pre_2000_plantations, tile_id_list)
# pool.close()
# pool.join()
#
#
# # Creates climate zone tiles
# if cn.count == 96:
# processes = 80 # 45 processors = 230 GB peak (on second step); 80 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating climate zone tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(prep_other_inputs.create_climate_zone_tiles, tile_id_list)
# pool.close()
# pool.join()
#
# # Creates European natural forest removal rate tiles
# source_raster = cn.name_annual_gain_AGC_BGC_natrl_forest_Europe_raw
# out_pattern = cn.pattern_annual_gain_AGC_BGC_natrl_forest_Europe
# dt = 'float32'
# if cn.count == 96:
# processes = 60 # 32 processors = 60 GB peak; 60 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating European natural forest gain rate tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
# # Creates European natural forest standard deviation of removal rate tiles
# source_raster = cn.name_stdev_annual_gain_AGC_BGC_natrl_forest_Europe_raw
# out_pattern = cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_Europe
# dt = 'float32'
# if cn.count == 96:
# processes = 32 # 32 processors = 60 GB peak; 60 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating standard deviation for European natural forest gain rate tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
#
# # Creates a vrt of the primary forests with nodata=0 from the continental primary forest rasters
# uu.print_log("Creating vrt of humid tropial primary forest...")
# primary_vrt = 'primary_2001.vrt'
# os.system('gdalbuildvrt -srcnodata 0 {} *2001_primary.tif'.format(primary_vrt))
# uu.print_log(" Humid tropical primary forest vrt created")
#
# # Creates primary forest tiles
# source_raster = primary_vrt
# out_pattern = 'primary_2001'
# dt = 'Byte'
# if cn.count == 96:
# processes = 45 # 45 processors = 650 GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating primary forest tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
#
# # Creates a combined IFL/primary forest raster
# # Uses very little memory since it's just file renaming
# if cn.count == 96:
# processes = 60 # 60 processors = 10 GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Assigning each tile to ifl2000 or primary forest with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(prep_other_inputs.create_combined_ifl_primary, tile_id_list)
# pool.close()
# pool.join()
#
#
# # Creates forest age category tiles for US forests
# source_raster = cn.name_age_cat_natrl_forest_US_raw
# out_pattern = cn.pattern_age_cat_natrl_forest_US
# dt = 'Byte'
# if cn.count == 96:
# processes = 70 # 32 processors = 35 GB peak; 70 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating US forest age category tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
# # Creates forest groups for US forests
# source_raster = cn.name_FIA_forest_group_raw
# out_pattern = cn.pattern_FIA_forest_group_processed
# dt = 'Byte'
# if cn.count == 96:
# processes = 80 # 32 processors = 25 GB peak; 80 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating US forest group tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
# # Creates FIA regions for US forests
# source_raster = cn.name_FIA_regions_raw
# out_pattern = cn.pattern_FIA_regions_processed
# dt = 'Byte'
# if cn.count == 96:
# processes = 70 # 32 processors = 35 GB peak; 70 = XXX GB peak
# else:
# processes = int(cn.count/2)
# uu.print_log("Creating US forest region tiles with {} processors...".format(processes))
# pool = multiprocessing.Pool(processes)
# pool.map(partial(uu.mp_warp_to_Hansen, source_raster=source_raster, out_pattern=out_pattern, dt=dt, no_upload=no_upload), tile_id_list)
# pool.close()
# pool.join()
#
#
for output_pattern in [
cn.pattern_drivers
# ,cn.pattern_annual_gain_AGC_natrl_forest_young, cn.pattern_stdev_annual_gain_AGC_natrl_forest_young
]:
# For some reason I can't figure out, the young forest rasters (rate and stdev) have NaN values in some places where 0 (NoData)
# should be. These NaN values show up as values when the check_and_delete_if_empty function runs, making the tiles not
# deleted even if they have no data. However, the light version (which uses gdalinfo rather than rasterio masks) doesn't
# have this problem. So I'm forcing the young forest rates to and stdev to have their emptiness checked by the gdalinfo version.
if output_pattern in [
cn.pattern_annual_gain_AGC_natrl_forest_young,
cn.pattern_stdev_annual_gain_AGC_natrl_forest_young
]:
processes = int(cn.count / 2)
uu.print_log(
"Checking for empty tiles of {0} pattern with {1} processors using light function..."
.format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.check_and_delete_if_empty_light,
output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
if cn.count == 96:
processes = 50 # 60 processors = >730 GB peak (for European natural forest forest removal rates); 50 = XXX GB peak
uu.print_log(
"Checking for empty tiles of {0} pattern with {1} processors..."
.format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.check_and_delete_if_empty,
output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
elif cn.count <= 2: # For local tests
processes = 1
uu.print_log(
"Checking for empty tiles of {0} pattern with {1} processors using light function..."
.format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.check_and_delete_if_empty_light,
output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
else:
processes = int(cn.count / 2)
uu.print_log(
"Checking for empty tiles of {0} pattern with {1} processors..."
.format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.check_and_delete_if_empty,
output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
uu.print_log('\n')
# Uploads output tiles to s3
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
def mp_model_extent(sensit_type, tile_id_list, run_date = None):
os.chdir(cn.docker_base_dir)
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model. Which biomass tiles to use depends on sensitivity analysis
if sensit_type == 'biomass_swap':
tile_id_list = uu.tile_list_s3(cn.JPL_processed_dir, sensit_type)
elif sensit_type == 'legal_Amazon_loss':
tile_id_list = uu.tile_list_s3(cn.Brazil_forest_extent_2000_processed_dir, sensit_type)
else:
tile_id_list = uu.create_combined_tile_list(cn.WHRC_biomass_2000_unmasked_dir,
cn.mangrove_biomass_2000_dir,
cn.gain_dir, cn.tcd_dir
)
uu.print_log(tile_id_list)
uu.print_log("There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script.
download_dict = {
cn.mangrove_biomass_2000_dir: [cn.pattern_mangrove_biomass_2000],
cn.gain_dir: [cn.pattern_gain],
cn.plant_pre_2000_processed_dir: [cn.pattern_plant_pre_2000]
}
if sensit_type == 'legal_Amazon_loss':
download_dict[cn.Brazil_forest_extent_2000_processed_dir] = [cn.pattern_Brazil_forest_extent_2000_processed]
else:
download_dict[cn.tcd_dir] = [cn.pattern_tcd]
if sensit_type == 'biomass_swap':
download_dict[cn.JPL_processed_dir] = [cn.pattern_JPL_unmasked_processed]
else:
download_dict[cn.WHRC_biomass_2000_unmasked_dir] = [cn.pattern_WHRC_biomass_2000_unmasked]
# List of output directories and output file name patterns
output_dir_list = [cn.model_extent_dir]
output_pattern_list = [cn.pattern_model_extent]
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log("Changing output directory and file name pattern based on sensitivity analysis")
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type, output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Creates a single filename pattern to pass to the multiprocessor call
pattern = output_pattern_list[0]
# This configuration of the multiprocessing call is necessary for passing multiple arguments to the main function
# It is based on the example here: http://spencerimp.blogspot.com/2015/12/python-multiprocess-with-multiple.html
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 38
else:
processes = 42 # 30 processors = 480 GB peak (sporadic decreases followed by sustained increases);
# 36 = 550 GB peak; 40 = 590 GB peak; 42 = XXX GB peak
else:
processes = 3
uu.print_log('Removal model forest extent processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(partial(model_extent.model_extent, pattern=pattern, sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# model_extent.model_extent(tile_id, pattern, sensit_type)
output_pattern = output_pattern_list[0]
if cn.count <= 2: # For local tests
processes = 1
uu.print_log(
"Checking for empty tiles of {0} pattern with {1} processors using light function...".format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.check_and_delete_if_empty_light, output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
else:
processes = 50 # 50 processors = XXX GB peak
uu.print_log("Checking for empty tiles of {0} pattern with {1} processors...".format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(partial(uu.check_and_delete_if_empty, output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
# Uploads output tiles to s3
uu.upload_final_set(output_dir_list[0], output_pattern_list[0])
def mp_net_flux(sensit_type, tile_id_list, run_date=None):
os.chdir(cn.docker_base_dir)
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model
tile_id_list = uu.create_combined_tile_list(
cn.gross_emis_all_gases_all_drivers_biomass_soil_dir,
cn.cumul_gain_AGCO2_BGCO2_all_types_dir,
sensit_type=sensit_type)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script
download_dict = {
cn.cumul_gain_AGCO2_BGCO2_all_types_dir:
[cn.pattern_cumul_gain_AGCO2_BGCO2_all_types],
cn.gross_emis_all_gases_all_drivers_biomass_soil_dir:
[cn.pattern_gross_emis_all_gases_all_drivers_biomass_soil]
}
# List of output directories and output file name patterns
output_dir_list = [cn.net_flux_dir]
output_pattern_list = [cn.pattern_net_flux]
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type,
tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Creates a single filename pattern to pass to the multiprocessor call
pattern = output_pattern_list[0]
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 32 # 32 processors = XXX GB peak
else:
processes = 40 # 38 = 690 GB peak; 40 = 715 GB peak
else:
processes = 9
uu.print_log('Net flux max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(net_flux.net_calc, pattern=pattern, sensit_type=sensit_type),
tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# net_flux.net_calc(tile_id, output_pattern_list[0], sensit_type)
# Uploads output tiles to s3
uu.upload_final_set(output_dir_list[0], output_pattern_list[0])
def mp_annual_gain_rate_AGC_BGC_all_forest_types(sensit_type,
tile_id_list,
run_date=None):
os.chdir(cn.docker_base_dir)
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model
tile_id_list = uu.tile_list_s3(cn.model_extent_dir, sensit_type)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script.
download_dict = {
cn.model_extent_dir: [cn.pattern_model_extent],
cn.annual_gain_AGB_mangrove_dir: [cn.pattern_annual_gain_AGB_mangrove],
cn.annual_gain_BGB_mangrove_dir: [cn.pattern_annual_gain_BGB_mangrove],
cn.annual_gain_AGC_BGC_natrl_forest_Europe_dir:
[cn.pattern_annual_gain_AGC_BGC_natrl_forest_Europe],
cn.annual_gain_AGC_BGC_planted_forest_unmasked_dir:
[cn.pattern_annual_gain_AGC_BGC_planted_forest_unmasked],
cn.annual_gain_AGC_BGC_natrl_forest_US_dir:
[cn.pattern_annual_gain_AGC_BGC_natrl_forest_US],
cn.annual_gain_AGC_natrl_forest_young_dir:
[cn.pattern_annual_gain_AGC_natrl_forest_young],
cn.age_cat_IPCC_dir: [cn.pattern_age_cat_IPCC],
cn.annual_gain_AGB_IPCC_defaults_dir:
[cn.pattern_annual_gain_AGB_IPCC_defaults],
cn.stdev_annual_gain_AGB_mangrove_dir:
[cn.pattern_stdev_annual_gain_AGB_mangrove],
cn.stdev_annual_gain_AGC_BGC_natrl_forest_Europe_dir:
[cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_Europe],
cn.stdev_annual_gain_AGC_BGC_planted_forest_unmasked_dir:
[cn.pattern_stdev_annual_gain_AGC_BGC_planted_forest_unmasked],
cn.stdev_annual_gain_AGC_BGC_natrl_forest_US_dir:
[cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_US],
cn.stdev_annual_gain_AGC_natrl_forest_young_dir:
[cn.pattern_stdev_annual_gain_AGC_natrl_forest_young],
cn.stdev_annual_gain_AGB_IPCC_defaults_dir:
[cn.pattern_stdev_annual_gain_AGB_IPCC_defaults]
}
# List of output directories and output file name patterns
output_dir_list = [
cn.removal_forest_type_dir, cn.annual_gain_AGC_all_types_dir,
cn.annual_gain_BGC_all_types_dir, cn.annual_gain_AGC_BGC_all_types_dir,
cn.stdev_annual_gain_AGC_all_types_dir
]
output_pattern_list = [
cn.pattern_removal_forest_type, cn.pattern_annual_gain_AGC_all_types,
cn.pattern_annual_gain_BGC_all_types,
cn.pattern_annual_gain_AGC_BGC_all_types,
cn.pattern_stdev_annual_gain_AGC_all_types
]
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type,
tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# This configuration of the multiprocessing call is necessary for passing multiple arguments to the main function
# It is based on the example here: http://spencerimp.blogspot.com/2015/12/python-multiprocess-with-multiple.html
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 13
else:
processes = 17 # 30 processors > 740 GB peak; 18 = >740 GB peak; 16 = 660 GB peak; 17 = XXX GB peak
else:
processes = 2
uu.print_log('Removal factor processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(annual_gain_rate_AGC_BGC_all_forest_types.
annual_gain_rate_AGC_BGC_all_forest_types,
output_pattern_list=output_pattern_list,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# annual_gain_rate_AGC_BGC_all_forest_types.annual_gain_rate_AGC_BGC_all_forest_types(tile_id, sensit_type)
# Uploads output tiles to s3
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
def mp_create_carbon_pools(sensit_type, tile_id_list, carbon_pool_extent, run_date = None):
os.chdir(cn.docker_base_dir)
if (sensit_type != 'std') & (carbon_pool_extent != 'loss'):
uu.exception_log("Sensitivity analysis run must use 'loss' extent")
# Checks the validity of the carbon_pool_extent argument
if (carbon_pool_extent not in ['loss', '2000', 'loss,2000', '2000,loss']):
uu.exception_log("Invalid carbon_pool_extent input. Please choose loss, 2000, loss,2000 or 2000,loss.")
# If a full model run is specified, the correct set of tiles for the particular script is listed.
# For runs generating carbon pools in emissions year, only tiles with model extent and loss are relevant.
if (tile_id_list == 'all') & (carbon_pool_extent == 'loss'):
# Lists the tiles that have both model extent and loss pixels
model_extent_tile_id_list = uu.tile_list_s3(cn.model_extent_dir, sensit_type=sensit_type)
loss_tile_id_list = uu.tile_list_s3(cn.loss_dir, sensit_type=sensit_type)
uu.print_log("Carbon pool at emissions year is combination of model_extent and loss tiles:")
tile_id_list = list(set(model_extent_tile_id_list).intersection(loss_tile_id_list))
# For runs generating carbon pools in 2000, all model extent tiles are relevant.
if (tile_id_list == 'all') & (carbon_pool_extent != 'loss'):
tile_id_list = uu.tile_list_s3(cn.model_extent_dir, sensit_type=sensit_type)
uu.print_log(tile_id_list)
uu.print_log("There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
output_dir_list = []
output_pattern_list = []
# Output files and patterns and files to download if carbon emitted_pools for 2000 are being generated
if '2000' in carbon_pool_extent:
# List of output directories and output file name patterns
output_dir_list = output_dir_list + [cn.AGC_2000_dir, cn.BGC_2000_dir, cn.deadwood_2000_dir,
cn.litter_2000_dir, cn.soil_C_full_extent_2000_dir, cn.total_C_2000_dir]
output_pattern_list = output_pattern_list + [cn.pattern_AGC_2000, cn.pattern_BGC_2000, cn.pattern_deadwood_2000,
cn.pattern_litter_2000, cn.pattern_soil_C_full_extent_2000, cn.pattern_total_C_2000]
# Files to download for this script
download_dict = {
cn.removal_forest_type_dir: [cn.pattern_removal_forest_type],
cn.mangrove_biomass_2000_dir: [cn.pattern_mangrove_biomass_2000],
cn.cont_eco_dir: [cn.pattern_cont_eco_processed],
cn.bor_tem_trop_processed_dir: [cn.pattern_bor_tem_trop_processed],
cn.precip_processed_dir: [cn.pattern_precip],
cn.elevation_processed_dir: [cn.pattern_elevation],
cn.soil_C_full_extent_2000_dir: [cn.pattern_soil_C_full_extent_2000],
cn.gain_dir: [cn.pattern_gain],
}
# Adds the correct AGB tiles to the download dictionary depending on the model run
if sensit_type == 'biomass_swap':
download_dict[cn.JPL_processed_dir] = [cn.pattern_JPL_unmasked_processed]
else:
download_dict[cn.WHRC_biomass_2000_unmasked_dir] = [cn.pattern_WHRC_biomass_2000_unmasked]
# Adds the correct loss tile to the download dictionary depending on the model run
if sensit_type == 'legal_Amazon_loss':
download_dict[cn.Brazil_annual_loss_processed_dir] = [cn.pattern_Brazil_annual_loss_processed]
elif sensit_type == 'Mekong_loss':
download_dict[cn.Mekong_loss_processed_dir] = [cn.pattern_Mekong_loss_processed]
else:
download_dict[cn.loss_dir] = [cn.pattern_loss]
# Output files and patterns and files to download if carbon emitted_pools for loss year are being generated
if 'loss' in carbon_pool_extent:
# List of output directories and output file name patterns
output_dir_list = output_dir_list + [cn.AGC_emis_year_dir, cn.BGC_emis_year_dir, cn.deadwood_emis_year_2000_dir,
cn.litter_emis_year_2000_dir, cn.soil_C_emis_year_2000_dir, cn.total_C_emis_year_dir]
output_pattern_list = output_pattern_list + [cn.pattern_AGC_emis_year, cn.pattern_BGC_emis_year, cn.pattern_deadwood_emis_year_2000,
cn.pattern_litter_emis_year_2000, cn.pattern_soil_C_emis_year_2000, cn.pattern_total_C_emis_year]
# Files to download for this script. This has the same items as the download_dict for 2000 pools plus
# other tiles.
download_dict = {
cn.removal_forest_type_dir: [cn.pattern_removal_forest_type],
cn.mangrove_biomass_2000_dir: [cn.pattern_mangrove_biomass_2000],
cn.cont_eco_dir: [cn.pattern_cont_eco_processed],
cn.bor_tem_trop_processed_dir: [cn.pattern_bor_tem_trop_processed],
cn.precip_processed_dir: [cn.pattern_precip],
cn.elevation_processed_dir: [cn.pattern_elevation],
cn.soil_C_full_extent_2000_dir: [cn.pattern_soil_C_full_extent_2000],
cn.gain_dir: [cn.pattern_gain],
cn.annual_gain_AGC_all_types_dir: [cn.pattern_annual_gain_AGC_all_types],
cn.cumul_gain_AGCO2_all_types_dir: [cn.pattern_cumul_gain_AGCO2_all_types]
}
# Adds the correct AGB tiles to the download dictionary depending on the model run
if sensit_type == 'biomass_swap':
download_dict[cn.JPL_processed_dir] = [cn.pattern_JPL_unmasked_processed]
else:
download_dict[cn.WHRC_biomass_2000_unmasked_dir] = [cn.pattern_WHRC_biomass_2000_unmasked]
# Adds the correct loss tile to the download dictionary depending on the model run
if sensit_type == 'legal_Amazon_loss':
download_dict[cn.Brazil_annual_loss_processed_dir] = [cn.pattern_Brazil_annual_loss_processed]
elif sensit_type == 'Mekong_loss':
download_dict[cn.Mekong_loss_processed_dir] = [cn.pattern_Mekong_loss_processed]
else:
download_dict[cn.loss_dir] = [cn.pattern_loss]
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log("Changing output directory and file name pattern based on sensitivity analysis")
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type, output_pattern_list)
else:
uu.print_log("Output directory list for standard model:", output_dir_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Table with IPCC Wetland Supplement Table 4.4 default mangrove gain rates
cmd = ['aws', 's3', 'cp', os.path.join(cn.gain_spreadsheet_dir, cn.gain_spreadsheet), cn.docker_base_dir]
uu.log_subprocess_output_full(cmd)
pd.options.mode.chained_assignment = None
# Imports the table with the ecozone-continent codes and the carbon gain rates
gain_table = pd.read_excel("{}".format(cn.gain_spreadsheet),
sheet_name="mangrove gain, for model")
# Removes rows with duplicate codes (N. and S. America for the same ecozone)
gain_table_simplified = gain_table.drop_duplicates(subset='gainEcoCon', keep='first')
mang_BGB_AGB_ratio = create_carbon_pools.mangrove_pool_ratio_dict(gain_table_simplified,
cn.below_to_above_trop_dry_mang,
cn.below_to_above_trop_wet_mang,
cn.below_to_above_subtrop_mang)
mang_deadwood_AGB_ratio = create_carbon_pools.mangrove_pool_ratio_dict(gain_table_simplified,
cn.deadwood_to_above_trop_dry_mang,
cn.deadwood_to_above_trop_wet_mang,
cn.deadwood_to_above_subtrop_mang)
mang_litter_AGB_ratio = create_carbon_pools.mangrove_pool_ratio_dict(gain_table_simplified,
cn.litter_to_above_trop_dry_mang,
cn.litter_to_above_trop_wet_mang,
cn.litter_to_above_subtrop_mang)
uu.print_log("Creating tiles of aboveground carbon in {}".format(carbon_pool_extent))
if cn.count == 96:
# More processors can be used for loss carbon pools than for 2000 carbon pools
if carbon_pool_extent == 'loss':
if sensit_type == 'biomass_swap':
processes = 16 # 16 processors = XXX GB peak
else:
processes = 20 # 25 processors > 750 GB peak; 16 = 560 GB peak;
# 18 = 570 GB peak; 19 = 620 GB peak; 20 = 670 GB peak; 21 > 750 GB peak
else: # For 2000, or loss & 2000
processes = 15 # 12 processors = 490 GB peak (stops around 455, then increases slowly); 15 = XXX GB peak
else:
processes = 2
uu.print_log('AGC loss year max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(partial(create_carbon_pools.create_AGC,
sensit_type=sensit_type, carbon_pool_extent=carbon_pool_extent), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_AGC(tile_id, sensit_type, carbon_pool_extent)
if carbon_pool_extent in ['loss', '2000']:
uu.upload_final_set(output_dir_list[0], output_pattern_list[0])
else:
uu.upload_final_set(output_dir_list[0], output_pattern_list[0])
uu.upload_final_set(output_dir_list[6], output_pattern_list[6])
uu.check_storage()
uu.print_log(":::::Freeing up memory for belowground carbon creation; deleting unneeded tiles")
tiles_to_delete = glob.glob('*{}*tif'.format(cn.pattern_annual_gain_AGC_all_types))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_cumul_gain_AGCO2_all_types)))
uu.print_log(" Deleting", len(tiles_to_delete), "tiles...")
for tile_to_delete in tiles_to_delete:
os.remove(tile_to_delete)
uu.print_log(":::::Deleted unneeded tiles")
uu.check_storage()
uu.print_log("Creating tiles of belowground carbon in {}".format(carbon_pool_extent))
# Creates a single filename pattern to pass to the multiprocessor call
if cn.count == 96:
# More processors can be used for loss carbon pools than for 2000 carbon pools
if carbon_pool_extent == 'loss':
if sensit_type == 'biomass_swap':
processes = 30 # 30 processors = XXX GB peak
else:
processes = 38 # 20 processors = 370 GB peak; 32 = 590 GB peak; 36 = 670 GB peak; 38 = 700 GB peak
else: # For 2000, or loss & 2000
processes = 30 # 20 processors = 370 GB peak; 25 = 460 GB peak; 30 = XXX GB peak
else:
processes = 2
uu.print_log('BGC max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(partial(create_carbon_pools.create_BGC, mang_BGB_AGB_ratio=mang_BGB_AGB_ratio,
carbon_pool_extent=carbon_pool_extent,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_BGC(tile_id, mang_BGB_AGB_ratio, carbon_pool_extent, sensit_type)
if carbon_pool_extent in ['loss', '2000']:
uu.upload_final_set(output_dir_list[1], output_pattern_list[1])
else:
uu.upload_final_set(output_dir_list[1], output_pattern_list[1])
uu.upload_final_set(output_dir_list[7], output_pattern_list[7])
uu.check_storage()
# 825 GB isn't enough space to create deadwood and litter 2000 while having AGC and BGC 2000 on.
# Thus must delete AGC, BGC, and soil C 2000 for creation of deadwood and litter, then copy them back to spot machine
# for total C 2000 calculation.
if '2000' in carbon_pool_extent:
uu.print_log(":::::Freeing up memory for deadwood and litter carbon 2000 creation; deleting unneeded tiles")
tiles_to_delete = []
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_BGC_2000)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_removal_forest_type)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_loss)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_gain)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_soil_C_full_extent_2000)))
uu.print_log(" Deleting", len(tiles_to_delete), "tiles...")
for tile_to_delete in tiles_to_delete:
os.remove(tile_to_delete)
uu.print_log(":::::Deleted unneeded tiles")
uu.check_storage()
uu.print_log("Creating tiles of deadwood and litter carbon in {}".format(carbon_pool_extent))
if cn.count == 96:
# More processors can be used for loss carbon pools than for 2000 carbon pools
if carbon_pool_extent == 'loss':
if sensit_type == 'biomass_swap':
processes = 10 # 10 processors = XXX GB peak
else:
processes = 14 # 32 processors = >750 GB peak; 24 > 750 GB peak; 14 = 650 GB peak; 15 = 700 GB peak
else: # For 2000, or loss & 2000
### Note: deleted precip, elevation, and WHRC AGB tiles at equatorial latitudes as deadwood and litter were produced.
### There wouldn't have been enough room for all deadwood and litter otherwise.
### For example, when deadwood and litter generation started getting up to around 50N, I deleted
### 00N precip, elevation, and WHRC AGB. I deleted all of those from 30N to 20S.
processes = 16 # 7 processors = 320 GB peak; 14 = 620 GB peak; 16 = XXX GB peak
else:
processes = 2
uu.print_log('Deadwood and litter max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(create_carbon_pools.create_deadwood_litter, mang_deadwood_AGB_ratio=mang_deadwood_AGB_ratio,
mang_litter_AGB_ratio=mang_litter_AGB_ratio,
carbon_pool_extent=carbon_pool_extent,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_deadwood_litter(tile_id, mang_deadwood_AGB_ratio, mang_litter_AGB_ratio, carbon_pool_extent, sensit_type)
if carbon_pool_extent in ['loss', '2000']:
uu.upload_final_set(output_dir_list[2], output_pattern_list[2]) # deadwood
uu.upload_final_set(output_dir_list[3], output_pattern_list[3]) # litter
else:
uu.upload_final_set(output_dir_list[2], output_pattern_list[2]) # deadwood
uu.upload_final_set(output_dir_list[3], output_pattern_list[3]) # litter
uu.upload_final_set(output_dir_list[8], output_pattern_list[8]) # deadwood
uu.upload_final_set(output_dir_list[9], output_pattern_list[9]) # litter
uu.check_storage()
uu.print_log(":::::Freeing up memory for soil and total carbon creation; deleting unneeded tiles")
tiles_to_delete = []
tiles_to_delete .extend(glob.glob('*{}*tif'.format(cn.pattern_elevation)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_precip)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_WHRC_biomass_2000_unmasked)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_JPL_unmasked_processed)))
tiles_to_delete.extend(glob.glob('*{}*tif'.format(cn.pattern_cont_eco_processed)))
uu.print_log(" Deleting", len(tiles_to_delete), "tiles...")
for tile_to_delete in tiles_to_delete:
os.remove(tile_to_delete)
uu.print_log(":::::Deleted unneeded tiles")
uu.check_storage()
if 'loss' in carbon_pool_extent:
uu.print_log("Creating tiles of soil carbon in loss extent")
# If pools in 2000 weren't generated, soil carbon in emissions extent is 4.
# If pools in 2000 were generated, soil carbon in emissions extent is 10.
if '2000' not in carbon_pool_extent:
pattern = output_pattern_list[4]
else:
pattern = output_pattern_list[10]
if cn.count == 96:
# More processors can be used for loss carbon pools than for 2000 carbon pools
if carbon_pool_extent == 'loss':
if sensit_type == 'biomass_swap':
processes = 36 # 36 processors = XXX GB peak
else:
processes = 42 # 24 processors = 360 GB peak; 32 = 490 GB peak; 38 = 580 GB peak; 42 = XXX GB peak
else: # For 2000, or loss & 2000
processes = 12 # 12 processors = XXX GB peak
else:
processes = 2
uu.print_log('Soil carbon loss year max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(partial(create_carbon_pools.create_soil_emis_extent, pattern=pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_soil_emis_extent(tile_id, pattern, sensit_type)
# If pools in 2000 weren't generated, soil carbon in emissions extent is 4.
# If pools in 2000 were generated, soil carbon in emissions extent is 10.
if '2000' not in carbon_pool_extent:
uu.upload_final_set(output_dir_list[4], output_pattern_list[4])
else:
uu.upload_final_set(output_dir_list[10], output_pattern_list[10])
uu.check_storage()
if '2000' in carbon_pool_extent:
uu.print_log("Skipping soil for 2000 carbon pool calculation. Soil carbon in 2000 already created.")
uu.check_storage()
# 825 GB isn't enough space to create deadwood and litter 2000 while having AGC and BGC 2000 on.
# Thus must delete BGC and soil C 2000 for creation of deadwood and litter, then copy them back to spot machine
# for total C 2000 calculation.
if '2000' in carbon_pool_extent:
# Files to download for total C 2000. Previously deleted to save space
download_dict = {
cn.BGC_2000_dir: [cn.pattern_BGC_2000],
cn.soil_C_full_extent_2000_dir: [cn.pattern_soil_C_full_extent_2000]
}
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type, tile_id_list)
uu.print_log("Creating tiles of total carbon")
if cn.count == 96:
# More processors can be used for loss carbon pools than for 2000 carbon pools
if carbon_pool_extent == 'loss':
if sensit_type == 'biomass_swap':
processes = 14 # 14 processors = XXX GB peak
else:
processes = 18 # 20 processors > 750 GB peak (by just a bit, I think); 15 = 550 GB peak; 18 = XXX GB peak
else: # For 2000, or loss & 2000
processes = 12 # 12 processors = XXX GB peak
else:
processes = 2
uu.print_log('Total carbon loss year max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(partial(create_carbon_pools.create_total_C, carbon_pool_extent=carbon_pool_extent,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# create_carbon_pools.create_total_C(tile_id, carbon_pool_extent, sensit_type)
if carbon_pool_extent in ['loss', '2000']:
uu.upload_final_set(output_dir_list[5], output_pattern_list[5])
else:
uu.upload_final_set(output_dir_list[5], output_pattern_list[5])
uu.upload_final_set(output_dir_list[11], output_pattern_list[11])
uu.check_storage()
def mp_gross_removals_all_forest_types(sensit_type,
tile_id_list,
run_date=None,
no_upload=True):
os.chdir(cn.docker_base_dir)
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model
# tile_id_list = uu.tile_list_s3(cn.model_extent_dir, sensit_type)
gain_year_count_tile_id_list = uu.tile_list_s3(cn.gain_year_count_dir,
sensit_type=sensit_type)
annual_removals_tile_id_list = uu.tile_list_s3(
cn.annual_gain_AGC_all_types_dir, sensit_type=sensit_type)
tile_id_list = list(
set(gain_year_count_tile_id_list).intersection(
annual_removals_tile_id_list))
uu.print_log(
"Gross removals tile_id_list is combination of gain_year_count and annual_removals tiles:"
)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) + "\n")
# Files to download for this script.
download_dict = {
cn.annual_gain_AGC_all_types_dir:
[cn.pattern_annual_gain_AGC_all_types],
cn.annual_gain_BGC_all_types_dir:
[cn.pattern_annual_gain_BGC_all_types],
cn.gain_year_count_dir: [cn.pattern_gain_year_count]
}
# List of output directories and output file name patterns
output_dir_list = [
cn.cumul_gain_AGCO2_all_types_dir, cn.cumul_gain_BGCO2_all_types_dir,
cn.cumul_gain_AGCO2_BGCO2_all_types_dir
]
output_pattern_list = [
cn.pattern_cumul_gain_AGCO2_all_types,
cn.pattern_cumul_gain_BGCO2_all_types,
cn.pattern_cumul_gain_AGCO2_BGCO2_all_types
]
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list, if AWS credentials are found
if uu.check_aws_creds():
for key, values in download_dict.items():
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Calculates gross removals
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 18
else:
processes = 22 # 50 processors > 740 GB peak; 25 = >740 GB peak; 15 = 490 GB peak; 20 = 590 GB peak; 22 = 710 GB peak
else:
processes = 2
uu.print_log('Gross removals max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(
gross_removals_all_forest_types.gross_removals_all_forest_types,
output_pattern_list=output_pattern_list,
sensit_type=sensit_type,
no_upload=no_upload), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# gross_removals_all_forest_types.gross_removals_all_forest_types(tile_id, output_pattern_list, sensit_type, no_upload)
# Checks the gross removals outputs for tiles with no data
for output_pattern in output_pattern_list:
if cn.count <= 2: # For local tests
processes = 1
uu.print_log(
"Checking for empty tiles of {0} pattern with {1} processors using light function..."
.format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.check_and_delete_if_empty_light,
output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
else:
processes = 55 # 55 processors = 670 GB peak
uu.print_log(
"Checking for empty tiles of {0} pattern with {1} processors..."
.format(output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.check_and_delete_if_empty,
output_pattern=output_pattern), tile_id_list)
pool.close()
pool.join()
# If no_upload flag is not activated, output is uploaded
if not no_upload:
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
def mp_output_per_pixel(sensit_type, tile_id_list, run_date=None):
os.chdir(cn.docker_base_dir)
# Pixel area tiles-- necessary for calculating values per pixel
uu.s3_flexible_download(cn.pixel_area_dir, cn.pattern_pixel_area,
cn.docker_base_dir, 'std', tile_id_list)
# Files to download for this script. Unusually, this script needs the output pattern in the dictionary as well!
download_dict = {
cn.cumul_gain_AGCO2_BGCO2_all_types_dir: [
cn.pattern_cumul_gain_AGCO2_BGCO2_all_types,
cn.pattern_cumul_gain_AGCO2_BGCO2_all_types_per_pixel
],
cn.gross_emis_all_gases_all_drivers_biomass_soil_dir: [
cn.pattern_gross_emis_all_gases_all_drivers_biomass_soil,
cn.pattern_gross_emis_all_gases_all_drivers_biomass_soil_per_pixel
],
cn.net_flux_dir: [cn.pattern_net_flux, cn.pattern_net_flux_per_pixel]
}
# List of output directories and output file name patterns
output_dir_list = [
cn.cumul_gain_AGCO2_BGCO2_all_types_per_pixel_dir,
cn.gross_emis_all_gases_all_drivers_biomass_soil_per_pixel_dir,
cn.net_flux_per_pixel_dir
]
output_pattern_list = [
cn.pattern_cumul_gain_AGCO2_BGCO2_all_types_per_pixel,
cn.pattern_gross_emis_all_gases_all_drivers_biomass_soil_per_pixel,
cn.pattern_net_flux_per_pixel
]
# If the model run isn't the standard one, the output directory and file names are changed
if sensit_type != 'std':
uu.print_log(
"Changing output directory and file name pattern based on sensitivity analysis"
)
output_dir_list = uu.alter_dirs(sensit_type, output_dir_list)
output_pattern_list = uu.alter_patterns(sensit_type,
output_pattern_list)
# A date can optionally be provided by the full model script or a run of this script.
# This replaces the date in constants_and_names.
if run_date is not None:
output_dir_list = uu.replace_output_dir_date(output_dir_list, run_date)
# Iterates through input tile sets
for key, values in download_dict.items():
# Sets the directory and pattern for the input being processed
input_dir = key
input_pattern = values[0]
# If a full model run is specified, the correct set of tiles for the particular script is listed
if tile_id_list == 'all':
# List of tiles to run in the model
tile_id_list = uu.tile_list_s3(input_dir, sensit_type)
uu.print_log(tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_id_list))) +
"\n")
uu.print_log("Downloading tiles from", input_dir)
uu.s3_flexible_download(input_dir, input_pattern, cn.docker_base_dir,
sensit_type, tile_id_list)
# The pattern of the output files
output_pattern = values[1]
# 20 processors = 430 GB peak for cumul gain; 30 = 640 GB peak for cumul gain;
# 32 = 680 GB peak for cumul gain; 33 = 710 GB peak for cumul gain, gross emis, net flux
if cn.count == 96:
processes = 20
else:
processes = 2
uu.print_log("Creating {0} with {1} processors...".format(
output_pattern, processes))
pool = multiprocessing.Pool(processes)
pool.map(
partial(output_per_pixel.output_per_pixel,
input_pattern=input_pattern,
output_pattern=output_pattern,
sensit_type=sensit_type), tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in tile_id_list:
# output_per_pixel.output_per_pixel(tile_id, input_pattern, output_pattern, sensit_type)
metadata_list = [
'units=Mg CO2e/pixel over model duration (2001-20{})'.format(
cn.loss_years), 'extent=Model extent',
'pixel_areas=Pixel areas depend on the latitude at which the pixel is found',
'scale=If this is for net flux, negative values are net sinks and positive values are net sources'
]
if cn.count == 96:
processes = 45 # 45 processors = XXX GB peak
else:
processes = 9
uu.print_log('Adding metadata tags max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(uu.add_metadata_tags,
output_pattern=output_pattern,
sensit_type=sensit_type,
metadata_list=metadata_list), tile_id_list)
pool.close()
pool.join()
# for tile_id in tile_id_list:
# uu.add_metadata_tags(tile_id, output_pattern, sensit_type, metadata_list)
# Uploads output tiles to s3
for i in range(0, len(output_dir_list)):
uu.upload_final_set(output_dir_list[i], output_pattern_list[i])
