def mp_plantation_preparation(gadm_index_shp, planted_index_shp):
os.chdir(cn.docker_base_dir)
# ## Not actually using this but leaving it here in case I want to add this functionality eventually. This
# # was to allow users to run plantations for a select (contiguous) area rather than for the whole planet.
# # List of bounding box coordinates
# bound_list = args.bounding_box
# # Checks if bounding box coordinates are in multiples of 10 (10 degree tiles). If they're not, the script stops.
# for bound in bound_list:
# if bound%10:
# uu.exception_log(bound, 'not a multiple of 10. Please make bounding box coordinates are multiples of 10.')
# Checks the validity of the two arguments. If either one is invalid, the script ends.
if (gadm_index_path not in cn.gadm_plant_1x1_index_dir or planted_index_path not in cn.gadm_plant_1x1_index_dir):
uu.exception_log('Invalid inputs. Please provide None or s3 shapefile locations for both arguments.')
# List of all possible 10x10 Hansen tiles except for those at very extreme latitudes (not just WHRC biomass tiles)
total_tile_list = uu.tile_list_s3(cn.pixel_area_dir)
uu.print_log("Number of possible 10x10 tiles to evaluate:", len(total_tile_list))
# Removes the latitude bands that don't have any planted forests in them according to Liz Goldman.
# i.e., Liz Goldman said by Slack on 1/2/19 that the nothernmost planted forest is 69.5146 and the southernmost is -46.938968.
# This creates a more focused list of 10x10 tiles to iterate through (removes ones that definitely don't have planted forest).
# NOTE: If the planted forest gdb is updated, the list of latitudes to exclude below may need to be changed to not exclude certain latitude bands.
planted_lat_tile_list = [tile for tile in total_tile_list if '90N' not in tile]
planted_lat_tile_list = [tile for tile in planted_lat_tile_list if '80N' not in tile]
planted_lat_tile_list = [tile for tile in planted_lat_tile_list if '50S' not in tile]
planted_lat_tile_list = [tile for tile in planted_lat_tile_list if '60S' not in tile]
planted_lat_tile_list = [tile for tile in planted_lat_tile_list if '70S' not in tile]
planted_lat_tile_list = [tile for tile in planted_lat_tile_list if '80S' not in tile]
# planted_lat_tile_list = ['10N_080W']
uu.print_log(planted_lat_tile_list)
uu.print_log("Number of 10x10 tiles to evaluate after extreme latitudes have been removed:", len(planted_lat_tile_list))
# If a planted forest extent 1x1 tile index shapefile isn't supplied
if 'None' in args.planted_tile_index:
### Entry point 1:
# If no shapefile of 1x1 tiles for countries with planted forests is supplied, 1x1 tiles of country extents will be created.
# This runs the process from the very beginning and will take a few days.
if 'None' in args.gadm_tile_index:
uu.print_log("No GADM 1x1 tile index shapefile provided. Creating 1x1 planted forest country tiles from scratch...")
# Downloads and unzips the GADM shapefile, which will be used to create 1x1 tiles of land areas
uu.s3_file_download(cn.gadm_path, cn.docker_base_dir)
cmd = ['unzip', cn.gadm_zip]
# 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)
# Creates a new GADM shapefile with just the countries that have planted forests in them.
# This limits creation of 1x1 rasters of land area on the countries that have planted forests rather than on all countries.
# NOTE: If the planted forest gdb is updated and has new countries added to it, the planted forest country list
# in constants_and_names.py must be updated, too.
uu.print_log("Creating shapefile of countries with planted forests...")
os.system('''ogr2ogr -sql "SELECT * FROM gadm_3_6_adm2_final WHERE iso IN ({0})" {1} gadm_3_6_adm2_final.shp'''.format(str(cn.plantation_countries)[1:-1], cn.gadm_iso))
# Creates 1x1 degree tiles of countries that have planted forests in them.
# I think this can handle using 50 processors because it's not trying to upload files to s3 and the tiles are small.
# This takes several days to run because it iterates through at least 250 10x10 tiles.
# For multiprocessor use.
processes = 50
uu.print_log('Rasterize GADM 1x1 max processors=', processes)
pool = Pool(processes)
pool.map(plantation_preparation.rasterize_gadm_1x1, planted_lat_tile_list)
pool.close()
pool.join()
# # Creates 1x1 degree tiles of countries that have planted forests in them.
# # For single processor use.
# for tile in planted_lat_tile_list:
#
# plantation_preparation.rasterize_gadm_1x1(tile)
# Creates a shapefile of the boundaries of the 1x1 GADM tiles in countries with planted forests
os.system('''gdaltindex {0}_{1}.shp GADM_*.tif'''.format(cn.pattern_gadm_1x1_index, uu.date_time_today))
cmd = ['aws', 's3', 'cp', cn.docker_base_dir, cn.gadm_plant_1x1_index_dir, '--exclude', '*', '--include', '{}*'.format(cn.pattern_gadm_1x1_index), '--recursive']
# 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)
# # Saves the 1x1 country extent tiles to s3
# # Only use if the entire process can't run in one go on the spot machine
# cmd = ['aws', 's3', 'cp', cn.docker_base_dir, 's3://gfw2-data/climate/carbon_model/temp_spotmachine_output/', '--exclude', '*', '--include', 'GADM_*.tif', '--recursive']
# # 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)
# Delete the aux.xml files
os.system('''rm GADM*.tif.*''')
# List of all 1x1 degree countey extent tiles created
gadm_list_1x1 = uu.tile_list_spot_machine(".", "GADM_")
uu.print_log("List of 1x1 degree tiles in countries that have planted forests, with defining coordinate in the northwest corner:", gadm_list_1x1)
uu.print_log(len(gadm_list_1x1))
### Entry point 2:
# If a shapefile of the boundaries of 1x1 degree tiles of countries with planted forests is supplied,
# a list of the 1x1 tiles is created from the shapefile.
# This avoids creating the 1x1 country extent tiles all over again because the relevant tile extent are supplied
# in the shapefile.
elif cn.gadm_plant_1x1_index_dir in args.gadm_tile_index:
uu.print_log("Country extent 1x1 tile index shapefile supplied. Using that to create 1x1 planted forest tiles...")
uu.print_log('{}/'.format(gadm_index_path))
# Copies the shapefile of 1x1 tiles of extent of countries with planted forests
cmd = ['aws', 's3', 'cp', '{}/'.format(gadm_index_path), cn.docker_base_dir, '--recursive', '--exclude', '*', '--include', '{}*'.format(gadm_index_shp)]
# 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)
# Gets the attribute table of the country extent 1x1 tile shapefile
gadm = glob.glob('{}*.dbf'.format(cn.pattern_gadm_1x1_index))[0]
# Converts the attribute table to a dataframe
dbf = Dbf5(gadm)
df = dbf.to_dataframe()
# Converts the column of the dataframe with the names of the tiles (which contain their coordinates) to a list
gadm_list_1x1 = df['location'].tolist()
gadm_list_1x1 = [str(y) for y in gadm_list_1x1]
uu.print_log("List of 1x1 degree tiles in countries that have planted forests, with defining coordinate in the northwest corner:", gadm_list_1x1)
uu.print_log("There are", len(gadm_list_1x1), "1x1 country extent tiles to iterate through.")
# In case some other arguments are provided
else:
uu.exception_log('Invalid GADM tile index shapefile provided. Please provide a valid shapefile.')
# Creates 1x1 degree tiles of plantation growth wherever there are plantations.
# Because this is iterating through all 1x1 tiles in countries with planted forests, it first checks
# whether each 1x1 tile intersects planted forests before creating a 1x1 planted forest tile for that
# 1x1 country extent tile.
# 55 processors seems to use about 350 GB of memory, which seems fine. But there was some error about "PQconnectdb failed-- sorry, too many clients already".
# So, moved the number of processors down to 48.
# For multiprocessor use
processes = 48
uu.print_log('Create 1x1 plantation from 1x1 gadm max processors=', processes)
pool = Pool(processes)
pool.map(plantation_preparation.create_1x1_plantation_from_1x1_gadm, gadm_list_1x1)
pool.close()
pool.join()
# # Creates 1x1 degree tiles of plantation growth wherever there are plantations
# # For single processor use
# for tile in gadm_list_1x1:
#
# plantation_preparation.create_1x1_plantation(tile)
# Creates a shapefile in which each feature is the extent of a plantation extent tile.
# This index shapefile can be used the next time this process is run if starting with Entry Point 3.
os.system('''gdaltindex {0}_{1}.shp plant_gain_*.tif'''.format(cn.pattern_plant_1x1_index, uu.date_time_today))
cmd = ['aws', 's3', 'cp', cn.docker_base_dir, cn.gadm_plant_1x1_index_dir, '--exclude', '*', '--include', '{}*'.format(cn.pattern_plant_1x1_index), '--recursive']
# 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)
### Entry point 3
# If a shapefile of the extents of 1x1 planted forest tiles is provided.
# This is the part that actually creates the sequestration rate and forest type tiles.
if cn.pattern_plant_1x1_index in args.planted_tile_index:
uu.print_log("Planted forest 1x1 tile index shapefile supplied. Using that to create 1x1 planted forest growth rate and forest type tiles...")
# Copies the shapefile of 1x1 tiles of extent of planted forests
cmd = ['aws', 's3', 'cp', '{}/'.format(planted_index_path), cn.docker_base_dir, '--recursive', '--exclude', '*', '--include',
'{}*'.format(planted_index_shp), '--recursive']
# 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)
# Gets the attribute table of the planted forest extent 1x1 tile shapefile
gadm = glob.glob('{}*.dbf'.format(cn.pattern_plant_1x1_index))[0]
# Converts the attribute table to a dataframe
dbf = Dbf5(gadm)
df = dbf.to_dataframe()
# Converts the column of the dataframe with the names of the tiles (which contain their coordinates) to a list
planted_list_1x1 = df['location'].tolist()
planted_list_1x1 = [str(y) for y in planted_list_1x1]
uu.print_log("List of 1x1 degree tiles in countries that have planted forests, with defining coordinate in the northwest corner:", planted_list_1x1)
uu.print_log("There are", len(planted_list_1x1), "1x1 planted forest extent tiles to iterate through.")
# Creates 1x1 degree tiles of plantation growth and type wherever there are plantations.
# Because this is iterating through only 1x1 tiles that are known to have planted forests (from a previous run
# of this script), it does not need to check whether there are planted forests in this tile. It goes directly
# to intersecting the planted forest table with the 1x1 tile.
# For single processor use
#for tile in planted_list_1x1:
# plantation_preparation.create_1x1_plantation_growth_from_1x1_planted(tile)
# For multiprocessor use
# processes=40 uses about 360 GB of memory. Works on r4.16xlarge with space to spare
# processes=52 uses about 465 GB of memory (quite stably), so this is basically the max.
num_of_processes = 52
pool = Pool(num_of_processes)
pool.map(plantation_preparation.create_1x1_plantation_growth_from_1x1_planted, planted_list_1x1)
pool.close()
pool.join()
# This works with 50 processors on an r4.16xlarge marchine. Uses about 430 GB out of 480 GB.
num_of_processes = 52
pool = Pool(num_of_processes)
processes = 50
uu.print_log('Create 1x1 plantation type max processors=', processes)
pool = Pool(processes)
pool.map(plantation_preparation.create_1x1_plantation_type_from_1x1_planted, planted_list_1x1)
pool.close()
pool.join()
# This rasterizes the plantation removal factor standard deviations
# processes=50 peaks at about 450 GB
num_of_processes = 50
pool = Pool(num_of_processes)
pool.map(plantation_preparation.create_1x1_plantation_stdev_from_1x1_planted, planted_list_1x1)
pool.close()
pool.join()
def mp_tile_statistics(sensit_type, tile_id_list):
os.chdir(cn.docker_base_dir)
# The column names for the tile summary statistics.
# If the statistics calculations are changed in tile_statistics.py, the list here needs to be changed, too.
headers = [
'tile_id', 'tile_type', 'tile_name', 'pixel_count', 'mean', 'median',
'percentile10', 'percentile25', 'percentile75', 'percentile90', 'min',
'max', 'sum'
]
header_no_brackets = ', '.join(headers)
tile_stats_txt = '{0}_v{1}_{2}_{3}.csv'.format(cn.tile_stats_pattern,
cn.version, sensit_type,
uu.date_time_today)
# Creates the output text file with the column names
with open(tile_stats_txt, 'w+') as f:
f.write(header_no_brackets + '\r\n')
f.close()
uu.print_log(tile_id_list)
# Pixel area tiles-- necessary for calculating sum of pixels for any set of tiles
uu.s3_flexible_download(cn.pixel_area_dir, cn.pattern_pixel_area,
cn.docker_base_dir, 'std', tile_id_list)
# For downloading all tiles in selected folders
download_dict = {
# cn.WHRC_biomass_2000_unmasked_dir: [cn.pattern_WHRC_biomass_2000_unmasked],
# cn.JPL_processed_dir: [cn.pattern_JPL_unmasked_processed],
# cn.mangrove_biomass_2000_dir: [cn.pattern_mangrove_biomass_2000],
# cn.cont_eco_dir: [cn.pattern_cont_eco_processed],
# cn.model_extent_dir: [cn.pattern_model_extent], # 15 = 370 GB peak
#
# # Mangrove removals
# cn.annual_gain_AGB_mangrove_dir: [cn.pattern_annual_gain_AGB_mangrove], # 15 = 640 GB peak
# cn.annual_gain_BGB_mangrove_dir: [cn.pattern_annual_gain_BGB_mangrove], # 15 = 640 GB peak
cn.stdev_annual_gain_AGB_mangrove_dir:
[cn.pattern_stdev_annual_gain_AGB_mangrove], # 15 = 640 GB peak
#
# # European forest removals
# cn.annual_gain_AGC_BGC_natrl_forest_Europe_dir: [cn.pattern_annual_gain_AGC_BGC_natrl_forest_Europe], # 15 = 630 GB peak
# cn.stdev_annual_gain_AGC_BGC_natrl_forest_Europe_dir: [cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_Europe], # 15 = 630 GB peak
#
# # Planted forest removals
# cn.annual_gain_AGC_BGC_planted_forest_unmasked_dir: [cn.pattern_annual_gain_AGC_BGC_planted_forest_unmasked], # 15 = 600 GB peak
# cn.planted_forest_type_unmasked_dir: [cn.pattern_planted_forest_type_unmasked], # 15 = 360 GB peak
# cn.stdev_annual_gain_AGC_BGC_planted_forest_unmasked_dir: [cn.pattern_stdev_annual_gain_AGC_BGC_planted_forest_unmasked], # 15 = 600 GB peak
#
# # US forest removals
# cn.FIA_regions_processed_dir: [cn.pattern_FIA_regions_processed], # 15 = 350 GB peak
# cn.FIA_forest_group_processed_dir: [cn.pattern_FIA_forest_group_processed], # 15 = 340 GB peak
# cn.age_cat_natrl_forest_US_dir: [cn.pattern_age_cat_natrl_forest_US], # 15 = 350 GB peak
# cn.annual_gain_AGC_BGC_natrl_forest_US_dir: [cn.pattern_annual_gain_AGC_BGC_natrl_forest_US], # 15 = 620 GB peak
# # cn.stdev_annual_gain_AGC_BGC_natrl_forest_US_dir: [cn.pattern_stdev_annual_gain_AGC_BGC_natrl_forest_US],
#
# # Young natural forest removals
# cn.annual_gain_AGC_natrl_forest_young_dir: [cn.pattern_annual_gain_AGC_natrl_forest_young], # 15 = 710 GB peak
# cn.stdev_annual_gain_AGC_natrl_forest_young_dir: [cn.pattern_stdev_annual_gain_AGC_natrl_forest_young], # 15 = 700 GB peak
#
# # IPCC defaults forest removals
# cn.age_cat_IPCC_dir: [cn.pattern_age_cat_IPCC], # 15 = 330 GB peak
# cn.annual_gain_AGB_IPCC_defaults_dir: [cn.pattern_annual_gain_AGB_IPCC_defaults], # 15 = 620 GB peak
# cn.annual_gain_BGB_IPCC_defaults_dir: [cn.pattern_annual_gain_BGB_IPCC_defaults], # 15 = 620 GB peak
# cn.stdev_annual_gain_AGB_IPCC_defaults_dir: [cn.pattern_stdev_annual_gain_AGB_IPCC_defaults], # 15 = 620 GB peak
#
# # Annual removals from all forest types
# cn.annual_gain_AGC_all_types_dir: [cn.pattern_annual_gain_AGC_all_types], # 15 = XXX GB peak
# cn.annual_gain_BGC_all_types_dir: [cn.pattern_annual_gain_BGC_all_types], # 15 > 550 GB peak
# cn.annual_gain_AGC_BGC_all_types_dir: [cn.pattern_annual_gain_AGC_BGC_all_types], # 15 = XXX GB peak
# cn.removal_forest_type_dir: [cn.pattern_removal_forest_type], # 15 = XXX GB peak
cn.stdev_annual_gain_AGC_all_types_dir:
[cn.pattern_stdev_annual_gain_AGC_all_types], # 15 = XXX GB peak
# # Gain year count
# cn.gain_year_count_dir: [cn.pattern_gain_year_count], # 15 = XXX GB peak
# # Gross removals from all forest types
# cn.cumul_gain_AGCO2_all_types_dir: [cn.pattern_cumul_gain_AGCO2_all_types], # 15 = 630 GB peak
# cn.cumul_gain_BGCO2_all_types_dir: [cn.pattern_cumul_gain_BGCO2_all_types], # 15 = XXX GB peak
# cn.cumul_gain_AGCO2_BGCO2_all_types_dir: [cn.pattern_cumul_gain_AGCO2_BGCO2_all_types], # 15 = XXX GB peak
# # Carbon pool inputs
# cn.elevation_processed_dir: [cn.pattern_elevation],
# cn.precip_processed_dir: [cn.pattern_precip],
# cn.bor_tem_trop_processed_dir: [cn.pattern_bor_tem_trop_processed],
# cn.drivers_processed_dir: [cn.pattern_drivers],
# cn.climate_zone_processed_dir: [cn.pattern_climate_zone],
# cn.soil_C_full_extent_2000_dir: [cn.pattern_soil_C_full_extent_2000], # 15 = 430 GB peak
cn.stdev_soil_C_full_extent_2000_dir:
[cn.pattern_stdev_soil_C_full_extent],
# Carbon pools in emissions year
# cn.AGC_emis_year_dir: [cn.pattern_AGC_emis_year], # 14 = 590 GB peak
# cn.BGC_emis_year_dir: [cn.pattern_BGC_emis_year], # 14 = > 520 GB peak
# cn.deadwood_emis_year_2000_dir: [cn.pattern_deadwood_emis_year_2000], # 14 > 560 GB peak (error memory when using 15, so switched to 14)
# cn.litter_emis_year_2000_dir: [cn.pattern_litter_emis_year_2000], # 14 = XXX GB peak
# cn.soil_C_emis_year_2000_dir: [cn.pattern_soil_C_emis_year_2000], # 14 = XXX GB peak
# cn.total_C_emis_year_dir: [cn.pattern_total_C_emis_year], # 14 = XXX GB peak
# # Carbon pools in 2000
# cn.AGC_2000_dir: [cn.pattern_AGC_2000],
# cn.BGC_2000_dir: [cn.pattern_BGC_2000],
# cn.deadwood_2000_dir: [cn.pattern_deadwood_2000],
# cn.litter_2000_dir: [cn.pattern_litter_2000],
# cn.total_C_2000_dir: [cn.pattern_total_C_2000],
# # Net flux
# cn.net_flux_dir: [cn.pattern_net_flux], # 14 = XXX GB peak
#
# # Gross emissions from biomass and soil
# cn.gross_emis_all_gases_all_drivers_biomass_soil_dir: [cn.pattern_gross_emis_all_gases_all_drivers_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_co2_only_all_drivers_biomass_soil_dir: [cn.pattern_gross_emis_co2_only_all_drivers_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_non_co2_all_drivers_biomass_soil_dir: [cn.pattern_gross_emis_non_co2_all_drivers_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_commod_biomass_soil_dir: [cn.pattern_gross_emis_commod_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_shifting_ag_biomass_soil_dir: [cn.pattern_gross_emis_shifting_ag_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_forestry_biomass_soil_dir: [cn.pattern_gross_emis_forestry_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_wildfire_biomass_soil_dir: [cn.pattern_gross_emis_wildfire_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_urban_biomass_soil_dir: [cn.pattern_gross_emis_urban_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_no_driver_biomass_soil_dir: [cn.pattern_gross_emis_no_driver_biomass_soil], # 14 = XXX GB peak
# cn.gross_emis_nodes_biomass_soil_dir: [cn.pattern_gross_emis_nodes_biomass_soil], # 14 = XXX GB peak
# Gross emissions from soil only
cn.gross_emis_all_gases_all_drivers_soil_only_dir:
[cn.pattern_gross_emis_all_gases_all_drivers_soil_only],
cn.gross_emis_co2_only_all_drivers_soil_only_dir:
[cn.pattern_gross_emis_co2_only_all_drivers_soil_only],
cn.gross_emis_non_co2_all_drivers_soil_only_dir:
[cn.pattern_gross_emis_non_co2_all_drivers_soil_only],
cn.gross_emis_commod_soil_only_dir:
[cn.pattern_gross_emis_commod_soil_only],
cn.gross_emis_shifting_ag_soil_only_dir:
[cn.pattern_gross_emis_shifting_ag_soil_only]
# cn.gross_emis_forestry_soil_only_dir: [cn.pattern_gross_emis_forestry_soil_only],
# cn.gross_emis_wildfire_soil_only_dir: [cn.pattern_gross_emis_wildfire_soil_only],
# cn.gross_emis_urban_soil_only_dir: [cn.pattern_gross_emis_urban_soil_only],
# cn.gross_emis_no_driver_soil_only_dir: [cn.pattern_gross_emis_no_driver_soil_only],
# cn.gross_emis_nodes_soil_only_dir: [cn.pattern_gross_emis_nodes_soil_only]
}
# Iterates through each set of tiles and gets statistics of it
for key, values in download_dict.items():
# Downloads input files or entire directories, depending on how many tiles are in the tile_id_list
dir = key
pattern = values[0]
uu.s3_flexible_download(dir, pattern, cn.docker_base_dir, sensit_type,
tile_id_list)
# List of all the tiles on the spot machine to be summarized (excludes pixel area tiles and tiles created by gdal_calc
# (in case this script was already run on this spot machine and created output from gdal_calc)
tile_list = uu.tile_list_spot_machine(".", ".tif")
# from https://stackoverflow.com/questions/12666897/removing-an-item-from-list-matching-a-substring
tile_list = [
i for i in tile_list
if not ('hanson_2013' in i or 'value_per_pixel' in i)
]
uu.print_log(tile_list)
uu.print_log(
"There are {} tiles to process".format(str(len(tile_list))) + "\n")
# For multiprocessor use.
processes = 14
uu.print_log('Tile statistics max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(tile_statistics.create_tile_statistics,
sensit_type=sensit_type,
tile_stats_txt=tile_stats_txt), tile_list)
# Added these in response to error12: Cannot allocate memory error.
# This fix was mentioned here: of https://stackoverflow.com/questions/26717120/python-cannot-allocate-memory-using-multiprocessing-pool
# Could also try this: https://stackoverflow.com/questions/42584525/python-multiprocessing-debugging-oserror-errno-12-cannot-allocate-memory
pool.close()
pool.join()
# # For single processor use
# for tile in tile_list:
# tile_statistics.create_tile_statistics(tile, sensit_type)
# Copies the text file to the tile statistics folder on s3
cmd = ['aws', 's3', 'cp', tile_stats_txt, cn.tile_stats_dir]
uu.log_subprocess_output_full(cmd)
# Spot machine can't store all the tiles, so this cleans it up
uu.print_log("Deleting tiles...")
for tile in tile_list:
os.remove(tile)
tile_short = tile[:-4]
outname = '{0}_value_per_pixel.tif'.format(tile_short)
os.remove(outname)
uu.print_log(" {} deleted".format(tile))
uu.print_log("Script complete. All tiles analyzed!")
def mp_aggregate_results_to_4_km(sensit_type,
thresh,
tile_id_list,
std_net_flux=None,
run_date=None,
no_upload=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.net_flux_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.annual_gain_AGC_all_types_dir:
[cn.pattern_annual_gain_AGC_all_types],
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],
cn.net_flux_dir: [cn.pattern_net_flux]
}
# Checks whether the canopy cover argument is valid
if thresh < 0 or thresh > 99:
uu.exception_log(
no_upload,
'Invalid tcd. Please provide an integer between 0 and 99.')
if uu.check_aws_creds():
# Pixel area tiles-- necessary for calculating sum of pixels for any set of tiles
uu.s3_flexible_download(cn.pixel_area_dir, cn.pattern_pixel_area,
cn.docker_base_dir, sensit_type, tile_id_list)
# Tree cover density, Hansen gain, and mangrove biomass tiles-- necessary for filtering sums to model extent
uu.s3_flexible_download(cn.tcd_dir, cn.pattern_tcd, cn.docker_base_dir,
sensit_type, tile_id_list)
uu.s3_flexible_download(cn.gain_dir, cn.pattern_gain,
cn.docker_base_dir, sensit_type, tile_id_list)
uu.s3_flexible_download(cn.mangrove_biomass_2000_dir,
cn.pattern_mangrove_biomass_2000,
cn.docker_base_dir, sensit_type, tile_id_list)
uu.print_log("Model outputs to process are:", download_dict)
# List of output directories. Modified later for sensitivity analysis.
# Output pattern is determined later.
output_dir_list = [cn.output_aggreg_dir]
# If the model run isn't the standard one, the output directory is 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)
# 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 the types of tiles to be processed
for dir, download_pattern in list(download_dict.items()):
download_pattern_name = download_pattern[0]
# 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():
uu.s3_flexible_download(dir, download_pattern_name,
cn.docker_base_dir, sensit_type,
tile_id_list)
# Gets an actual tile id to use as a dummy in creating the actual tile pattern
local_tile_list = uu.tile_list_spot_machine(cn.docker_base_dir,
download_pattern_name)
sample_tile_id = uu.get_tile_id(local_tile_list[0])
# Renames the tiles according to the sensitivity analysis before creating dummy tiles.
# The renaming function requires a whole tile name, so this passes a dummy time name that is then stripped a few
# lines later.
tile_id = sample_tile_id # a dummy tile id (but it has to be a real tile id). It is removed later.
output_pattern = uu.sensit_tile_rename(sensit_type, tile_id,
download_pattern_name)
pattern = output_pattern[9:-4]
# For sensitivity analysis runs, only aggregates the tiles if they were created as part of the sensitivity analysis
if (sensit_type != 'std') & (sensit_type not in pattern):
uu.print_log(
"{} not a sensitivity analysis output. Skipping aggregation..."
.format(pattern))
uu.print_log("")
continue
# Lists the tiles of the particular type that is being iterates through.
# Excludes all intermediate files
tile_list = uu.tile_list_spot_machine(".", "{}.tif".format(pattern))
# from https://stackoverflow.com/questions/12666897/removing-an-item-from-list-matching-a-substring
tile_list = [i for i in tile_list if not ('hanson_2013' in i)]
tile_list = [i for i in tile_list if not ('rewindow' in i)]
tile_list = [i for i in tile_list if not ('0_4deg' in i)]
tile_list = [i for i in tile_list if not ('.ovr' in i)]
# tile_list = ['00N_070W_cumul_gain_AGCO2_BGCO2_t_ha_all_forest_types_2001_15_biomass_swap.tif'] # test tiles
uu.print_log("There are {0} tiles to process for pattern {1}".format(
str(len(tile_list)), download_pattern) + "\n")
uu.print_log("Processing:", dir, "; ", pattern)
# Converts the 10x10 degree Hansen tiles that are in windows of 40000x1 pixels to windows of 400x400 pixels,
# which is the resolution of the output tiles. This will allow the 30x30 m pixels in each window to be summed.
# For multiprocessor use. count/2 used about 400 GB of memory on an r4.16xlarge machine, so that was okay.
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 12 # 12 processors = XXX GB peak
else:
processes = 16 # 12 processors = 140 GB peak; 16 = XXX GB peak; 20 = >750 GB (maxed out)
else:
processes = 8
uu.print_log('Rewindow max processors=', processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(aggregate_results_to_4_km.rewindow, no_upload=no_upload),
tile_list)
# Added these in response to error12: Cannot allocate memory error.
# This fix was mentioned here: of https://stackoverflow.com/questions/26717120/python-cannot-allocate-memory-using-multiprocessing-pool
# Could also try this: https://stackoverflow.com/questions/42584525/python-multiprocessing-debugging-oserror-errno-12-cannot-allocate-memory
pool.close()
pool.join()
# # For single processor use
# for tile in tile_list:
#
# aggregate_results_to_4_km.rewindow(til, no_upload)
# Converts the existing (per ha) values to per pixel values (e.g., emissions/ha to emissions/pixel)
# and sums those values in each 400x400 pixel window.
# The sum for each 400x400 pixel window is stored in a 2D array, which is then converted back into a raster at
# 0.1x0.1 degree resolution (approximately 10m in the tropics).
# Each pixel in that raster is the sum of the 30m pixels converted to value/pixel (instead of value/ha).
# The 0.1x0.1 degree tile is output.
# For multiprocessor use. This used about 450 GB of memory with count/2, it's okay on an r4.16xlarge
if cn.count == 96:
if sensit_type == 'biomass_swap':
processes = 10 # 10 processors = XXX GB peak
else:
processes = 12 # 16 processors = 180 GB peak; 16 = XXX GB peak; 20 = >750 GB (maxed out)
else:
processes = 8
uu.print_log('Conversion to per pixel and aggregate max processors=',
processes)
pool = multiprocessing.Pool(processes)
pool.map(
partial(aggregate_results_to_4_km.aggregate,
thresh=thresh,
sensit_type=sensit_type,
no_upload=no_upload), tile_list)
pool.close()
pool.join()
# # For single processor use
# for tile in tile_list:
#
# aggregate_results_to_4_km.aggregate(tile, thresh, sensit_type, no_upload)
# Makes a vrt of all the output 10x10 tiles (10 km resolution)
out_vrt = "{}_0_4deg.vrt".format(pattern)
os.system('gdalbuildvrt -tr 0.04 0.04 {0} *{1}_0_4deg*.tif'.format(
out_vrt, pattern))
# Creates the output name for the 10km map
out_pattern = uu.name_aggregated_output(download_pattern_name, thresh,
sensit_type)
uu.print_log(out_pattern)
# Produces a single raster of all the 10x10 tiles (0.4 degree resolution)
cmd = [
'gdalwarp', '-t_srs', "EPSG:4326", '-overwrite', '-dstnodata', '0',
'-co', 'COMPRESS=LZW', '-tr', '0.04', '0.04', out_vrt,
'{}.tif'.format(out_pattern)
]
uu.log_subprocess_output_full(cmd)
# Adds metadata tags to output rasters
uu.add_universal_metadata_tags('{0}.tif'.format(out_pattern),
sensit_type)
# Units are different for annual removal factor, so metadata has to reflect that
if 'annual_removal_factor' in out_pattern:
cmd = [
'gdal_edit.py', '-mo',
'units=Mg aboveground carbon/yr/pixel, where pixels are 0.04x0.04 degrees',
'-mo',
'source=per hectare version of the same model output, aggregated from 0.00025x0.00025 degree pixels',
'-mo', 'extent=Global', '-mo',
'scale=negative values are removals', '-mo',
'treecover_density_threshold={0} (only model pixels with canopy cover > {0} are included in aggregation'
.format(thresh), '{0}.tif'.format(out_pattern)
]
uu.log_subprocess_output_full(cmd)
else:
cmd = [
'gdal_edit.py', '-mo',
'units=Mg CO2e/yr/pixel, where pixels are 0.04x0.04 degrees',
'-mo',
'source=per hectare version of the same model output, aggregated from 0.00025x0.00025 degree pixels',
'-mo', 'extent=Global', '-mo',
'treecover_density_threshold={0} (only model pixels with canopy cover > {0} are included in aggregation'
.format(thresh), '{0}.tif'.format(out_pattern)
]
uu.log_subprocess_output_full(cmd)
# If no_upload flag is not activated, output is uploaded
if not no_upload:
uu.print_log("Tiles processed. Uploading to s3 now...")
uu.upload_final_set(output_dir_list[0], out_pattern)
# Cleans up the folder before starting on the next raster type
vrtList = glob.glob('*vrt')
for vrt in vrtList:
os.remove(vrt)
for tile_name in tile_list:
tile_id = uu.get_tile_id(tile_name)
# os.remove('{0}_{1}.tif'.format(tile_id, pattern))
os.remove('{0}_{1}_rewindow.tif'.format(tile_id, pattern))
os.remove('{0}_{1}_0_4deg.tif'.format(tile_id, pattern))
# Compares the net flux from the standard model and the sensitivity analysis in two ways.
# This does not work for compariing the raw outputs of the biomass_swap and US_removals sensitivity models because their
# extents are different from the standard model's extent (tropics and US tiles vs. global).
# Thus, in order to do this comparison, you need to clip the standard model net flux and US_removals net flux to
# the outline of the US and clip the standard model net flux to the extent of JPL AGB2000.
# Then, manually upload the clipped US_removals and biomass_swap net flux rasters to the spot machine and the
# code below should work.
if sensit_type not in [
'std', 'biomass_swap', 'US_removals', 'legal_Amazon_loss'
]:
if std_net_flux:
uu.print_log(
"Standard aggregated flux results provided. Creating comparison maps."
)
# Copies the standard model aggregation outputs to s3. Only net flux is used, though.
uu.s3_file_download(std_net_flux, cn.docker_base_dir, sensit_type)
# Identifies the standard model net flux map
std_aggreg_flux = os.path.split(std_net_flux)[1]
try:
# Identifies the sensitivity model net flux map
sensit_aggreg_flux = glob.glob(
'net_flux_Mt_CO2e_*{}*'.format(sensit_type))[0]
uu.print_log("Standard model net flux:", std_aggreg_flux)
uu.print_log("Sensitivity model net flux:", sensit_aggreg_flux)
except:
uu.print_log(
'Cannot do comparison. One of the input flux tiles is not valid. Verify that both net flux rasters are on the spot machine.'
)
uu.print_log(
"Creating map of percent difference between standard and {} net flux"
.format(sensit_type))
aggregate_results_to_4_km.percent_diff(std_aggreg_flux,
sensit_aggreg_flux,
sensit_type, no_upload)
uu.print_log(
"Creating map of which pixels change sign and which stay the same between standard and {}"
.format(sensit_type))
aggregate_results_to_4_km.sign_change(std_aggreg_flux,
sensit_aggreg_flux,
sensit_type, no_upload)
# If no_upload flag is not activated, output is uploaded
if not no_upload:
uu.upload_final_set(output_dir_list[0],
cn.pattern_aggreg_sensit_perc_diff)
uu.upload_final_set(output_dir_list[0],
cn.pattern_aggreg_sensit_sign_change)
else:
uu.print_log(
"No standard aggregated flux results provided. Not creating comparison maps."
)
def main():
# Create the output log
uu.initiate_log()
os.chdir(cn.docker_base_dir)
# Files to download for this script.
download_dict = {
cn.gain_dir: [cn.pattern_gain],
cn.annual_gain_AGB_IPCC_defaults_dir:
[cn.pattern_annual_gain_AGB_IPCC_defaults]
}
# 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.annual_gain_AGB_IPCC_defaults_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
# List of output directories and output file name patterns
output_dir_list = [
cn.US_annual_gain_AGB_natrl_forest_dir,
cn.US_annual_gain_BGB_natrl_forest_dir
]
output_pattern_list = [
cn.pattern_US_annual_gain_AGB_natrl_forest,
cn.pattern_US_annual_gain_BGB_natrl_forest
]
# By definition, this script is for US-specific removals
sensit_type = 'US_removals'
# Counts how many processed FIA region tiles there are on s3 already. 16 tiles cover the continental US.
FIA_regions_tile_count = uu.count_tiles_s3(cn.FIA_regions_processed_dir)
# Only creates FIA region tiles if they don't already exist on s3.
if FIA_regions_tile_count == 16:
uu.print_log("FIA region tiles already created. Copying to s3 now...")
uu.s3_flexible_download(cn.FIA_regions_processed_dir,
cn.pattern_FIA_regions_processed,
cn.docker_base_dir, 'std', 'all')
else:
uu.print_log(
"FIA region tiles do not exist. Creating tiles, then copying to s3 for future use..."
)
uu.s3_file_download(
os.path.join(cn.FIA_regions_raw_dir, cn.name_FIA_regions_raw),
cn.docker_base_dir, 'std')
cmd = ['unzip', '-o', '-j', cn.name_FIA_regions_raw]
# 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)
# Converts the region shapefile to Hansen tiles
pool = multiprocessing.Pool(int(cn.count / 2))
pool.map(US_removal_rates.prep_FIA_regions, tile_id_list)
# List of FIA region tiles on the spot machine. Only this list is used for the rest of the script.
US_tile_list = uu.tile_list_spot_machine(
cn.docker_base_dir, '{}.tif'.format(cn.pattern_FIA_regions_processed))
US_tile_id_list = [i[0:8] for i in US_tile_list]
# US_tile_id_list = ['50N_130W'] # For testing
uu.print_log(US_tile_id_list)
uu.print_log(
"There are {} tiles to process".format(str(len(US_tile_id_list))) +
"\n")
# Counts how many processed forest age category tiles there are on s3 already. 16 tiles cover the continental US.
US_age_tile_count = uu.count_tiles_s3(cn.US_forest_age_cat_processed_dir)
# Only creates FIA forest age category tiles if they don't already exist on s3.
if US_age_tile_count == 16:
uu.print_log(
"Forest age category tiles already created. Copying to spot machine now..."
)
uu.s3_flexible_download(cn.US_forest_age_cat_processed_dir,
cn.pattern_US_forest_age_cat_processed, '',
'std', US_tile_id_list)
else:
uu.print_log(
"Southern forest age category tiles do not exist. Creating tiles, then copying to s3 for future use..."
)
uu.s3_file_download(
os.path.join(cn.US_forest_age_cat_raw_dir,
cn.name_US_forest_age_cat_raw), cn.docker_base_dir,
'std')
# Converts the national forest age category raster to Hansen tiles
source_raster = cn.name_US_forest_age_cat_raw
out_pattern = cn.pattern_US_forest_age_cat_processed
dt = 'Int16'
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), US_tile_id_list)
uu.upload_final_set(cn.US_forest_age_cat_processed_dir,
cn.pattern_US_forest_age_cat_processed)
# Counts how many processed FIA forest group tiles there are on s3 already. 16 tiles cover the continental US.
FIA_forest_group_tile_count = uu.count_tiles_s3(
cn.FIA_forest_group_processed_dir)
# Only creates FIA forest group tiles if they don't already exist on s3.
if FIA_forest_group_tile_count == 16:
uu.print_log(
"FIA forest group tiles already created. Copying to spot machine now..."
)
uu.s3_flexible_download(cn.FIA_forest_group_processed_dir,
cn.pattern_FIA_forest_group_processed, '',
'std', US_tile_id_list)
else:
uu.print_log(
"FIA forest group tiles do not exist. Creating tiles, then copying to s3 for future use..."
)
uu.s3_file_download(
os.path.join(cn.FIA_forest_group_raw_dir,
cn.name_FIA_forest_group_raw), cn.docker_base_dir,
'std')
# Converts the national forest group raster to Hansen forest group tiles
source_raster = cn.name_FIA_forest_group_raw
out_pattern = cn.pattern_FIA_forest_group_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), US_tile_id_list)
uu.upload_final_set(cn.FIA_forest_group_processed_dir,
cn.pattern_FIA_forest_group_processed)
# 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,
US_tile_id_list)
# 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
]
# 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)
# Imports the table with the region-group-age AGB removal rates
gain_table = pd.read_excel("{}".format(cn.table_US_removal_rate),
sheet_name="US_rates_for_model")
# 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)
# count/2 on a m4.16xlarge maxes out at about 230 GB of memory (processing 16 tiles at once), so it's okay on an m4.16xlarge
pool = multiprocessing.Pool(int(cn.count / 2))
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,
output_pattern_list=output_pattern_list,
sensit_type=sensit_type), US_tile_id_list)
pool.close()
pool.join()
# # For single processor use
# for tile_id in US_tile_id_list:
#
# US_removal_rates.US_removal_rate_calc(tile_id, gain_table_group_region_age_dict, gain_table_group_region_dict,
# output_pattern_list, 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 main():
parser = argparse.ArgumentParser(
description='Create planted forest carbon gain rate tiles')
parser.add_argument(
'--gadm-tile-index',
'-gi',
required=True,
help=
'Shapefile of 1x1 degree tiles of countries that contain planted forests (i.e. countries with planted forests rasterized to 1x1 deg). If no shapefile, write None.'
)
parser.add_argument(
'--planted-tile-index',
'-pi',
required=True,
help=
'Shapefile of 1x1 degree tiles of that contain planted forests (i.e. planted forest extent rasterized to 1x1 deg). If no shapefile, write None.'
)
args = parser.parse_args()
# Creates the directory and shapefile names for the two possible arguments (index shapefiles)
gadm_index = os.path.split(args.gadm_tile_index)
gadm_index_path = gadm_index[0]
gadm_index_shp = gadm_index[1]
gadm_index_shp = gadm_index_shp[:-4]
planted_index = os.path.split(args.planted_tile_index)
planted_index_path = planted_index[0]
planted_index_shp = planted_index[1]
planted_index_shp = planted_index_shp[:-4]
# Checks the validity of the two arguments. If either one is invalid, the script ends.
if (gadm_index_path not in cn.gadm_plant_1x1_index_dir
or planted_index_path not in cn.gadm_plant_1x1_index_dir):
raise Exception(
'Invalid inputs. Please provide None or s3 shapefile locations for both arguments.'
)
# List of all possible 10x10 Hansen tiles except for those at very extreme latitudes (not just WHRC biomass tiles)
total_tile_list = uu.tile_list(cn.pixel_area_dir)
print "Number of possible 10x10 tiles to evaluate:", len(total_tile_list)
# Removes the latitude bands that don't have any planted forests in them according to Liz Goldman.
# i.e., Liz Goldman said by Slack on 1/2/19 that the nothernmost planted forest is 69.5146 and the southernmost is -46.938968.
# This creates a more focused list of 10x10 tiles to iterate through (removes ones that definitely don't have planted forest).
# NOTE: If the planted forest gdb is updated, the list of latitudes to exclude below may need to be changed to not exclude certain latitude bands.
planted_lat_tile_list = [
tile for tile in total_tile_list if '90N' not in tile
]
planted_lat_tile_list = [
tile for tile in planted_lat_tile_list if '80N' not in tile
]
planted_lat_tile_list = [
tile for tile in planted_lat_tile_list if '50S' not in tile
]
planted_lat_tile_list = [
tile for tile in planted_lat_tile_list if '60S' not in tile
]
planted_lat_tile_list = [
tile for tile in planted_lat_tile_list if '70S' not in tile
]
planted_lat_tile_list = [
tile for tile in planted_lat_tile_list if '80S' not in tile
]
# planted_lat_tile_list = ['10N_080W']
print planted_lat_tile_list
print "Number of 10x10 tiles to evaluate after extreme latitudes have been removed:", len(
planted_lat_tile_list)
# If a planted forest extent 1x1 tile index shapefile isn't supplied
if 'None' in args.planted_tile_index:
### Entry point 1:
# If no shapefile of 1x1 tiles for countries with planted forests is supplied, 1x1 tiles of country extents will be created.
# This runs the process from the very beginning and will take a few days.
if 'None' in args.gadm_tile_index:
print "No GADM 1x1 tile index shapefile provided. Creating 1x1 planted forest country tiles from scratch..."
# Downloads and unzips the GADM shapefile, which will be used to create 1x1 tiles of land areas
uu.s3_file_download(cn.gadm_path, '.')
cmd = ['unzip', cn.gadm_zip]
subprocess.check_call(cmd)
# Creates a new GADM shapefile with just the countries that have planted forests in them.
# This limits creation of 1x1 rasters of land area on the countries that have planted forests rather than on all countries.
# NOTE: If the planted forest gdb is updated and has new countries added to it, the planted forest country list
# in constants_and_names.py must be updated, too.
print "Creating shapefile of countries with planted forests..."
os.system(
'''ogr2ogr -sql "SELECT * FROM gadm_3_6_adm2_final WHERE iso IN ({0})" {1} gadm_3_6_adm2_final.shp'''
.format(str(cn.plantation_countries)[1:-1], cn.gadm_iso))
# Creates 1x1 degree tiles of countries that have planted forests in them.
# I assume this can handle using 50 processors because it's not trying to upload files to s3 and the tiles are small.
# This takes several days to run because it iterates through at least 250 10x10 tiles.
# For multiprocessor use.
num_of_processes = 50
pool = Pool(num_of_processes)
pool.map(plantation_preparation.rasterize_gadm_1x1,
planted_lat_tile_list)
pool.close()
pool.join()
# # Creates 1x1 degree tiles of countries that have planted forests in them.
# # For single processor use.
# for tile in planted_lat_tile_list:
#
# plantation_preparation.rasterize_gadm_1x1(tile)
# Creates a shapefile of the boundaries of the 1x1 GADM tiles in countries with planted forests
os.system('''gdaltindex {0}_{1}.shp GADM_*.tif'''.format(
cn.pattern_gadm_1x1_index, uu.date))
cmd = [
'aws', 's3', 'cp', '.', cn.gadm_plant_1x1_index_dir,
'--exclude', '*', '--include',
'{}*'.format(cn.pattern_gadm_1x1_index), '--recursive'
]
subprocess.check_call(cmd)
# # Saves the 1x1 country extent tiles to s3
# # Only use if the entire process can't run in one go on the spot machine
# cmd = ['aws', 's3', 'cp', '.', 's3://gfw2-data/climate/carbon_model/temp_spotmachine_output/', '--exclude', '*', '--include', 'GADM_*.tif', '--recursive']
# subprocess.check_call(cmd)
# Delete the aux.xml files
os.system('''rm GADM*.tif.*''')
# List of all 1x1 degree countey extent tiles created
gadm_list_1x1 = uu.tile_list_spot_machine(".", "GADM_")
print "List of 1x1 degree tiles in countries that have planted forests, with defining coordinate in the northwest corner:", gadm_list_1x1
print len(gadm_list_1x1)
### Entry point 2:
# If a shapefile of the boundaries of 1x1 degree tiles of countries with planted forests is supplied,
# a list of the 1x1 tiles is created from the shapefile.
# This avoids creating the 1x1 country extent tiles all over again because the relevant tile extent are supplied
# in the shapefile.
elif cn.gadm_plant_1x1_index_dir in args.gadm_tile_index:
print "Country extent 1x1 tile index shapefile supplied. Using that to create 1x1 planted forest tiles..."
# Copies the shapefile of 1x1 tiles of extent of countries with planted forests
cmd = [
'aws', 's3', 'cp', '{}/'.format(gadm_index_path), '.',
'--recursive', '--exclude', '*', '--include',
'{}*'.format(gadm_index_shp), '--recursive'
]
subprocess.check_call(cmd)
# Gets the attribute table of the country extent 1x1 tile shapefile
gadm = glob.glob('{}*.dbf'.format(cn.pattern_gadm_1x1_index))[0]
# Converts the attribute table to a dataframe
dbf = Dbf5(gadm)
df = dbf.to_dataframe()
# Converts the column of the dataframe with the names of the tiles (which contain their coordinates) to a list
gadm_list_1x1 = df['location'].tolist()
gadm_list_1x1 = [str(y) for y in gadm_list_1x1]
print "List of 1x1 degree tiles in countries that have planted forests, with defining coordinate in the northwest corner:", gadm_list_1x1
print "There are", len(
gadm_list_1x1), "1x1 country extent tiles to iterate through."
# In case some other arguments are provided
else:
raise Exception(
'Invalid GADM tile index shapefile provided. Please provide a valid shapefile.'
)
# Creates 1x1 degree tiles of plantation growth wherever there are plantations.
# Because this is iterating through all 1x1 tiles in countries with planted forests, it first checks
# whether each 1x1 tile intersects planted forests before creating a 1x1 planted forest tile for that
# 1x1 country extent tile.
# For multiprocessor use
num_of_processes = 30
pool = Pool(num_of_processes)
pool.map(plantation_preparation.create_1x1_plantation_from_1x1_gadm,
gadm_list_1x1)
pool.close()
pool.join()
# # Creates 1x1 degree tiles of plantation growth wherever there are plantations
# # For single processor use
# for tile in gadm_list_1x1:
#
# plantation_preparation.create_1x1_plantation(tile)
# Creates a shapefile in which each feature is the extent of a plantation extent tile.
# This index shapefile can be used the next time this process is run if starting with Entry Point 3.
os.system('''gdaltindex {0}_{1}.shp plant_*.tif'''.format(
cn.pattern_plant_1x1_index, uu.date))
cmd = [
'aws', 's3', 'cp', '.', cn.gadm_plant_1x1_index_dir, '--exclude',
'*', '--include', '{}*'.format(cn.pattern_plant_1x1_index),
'--recursive'
]
subprocess.check_call(cmd)
### Entry point 3
# If a shapefile of the extents of 1x1 planted forest tiles is provided
if cn.pattern_plant_1x1_index in args.planted_tile_index:
print "Planted forest 1x1 tile index shapefile supplied. Using that to create 1x1 planted forest growth tiles..."
# Copies the shapefile of 1x1 tiles of extent of planted forests
cmd = [
'aws', 's3', 'cp', '{}/'.format(planted_index_path), '.',
'--recursive', '--exclude', '*', '--include',
'{}*'.format(planted_index_shp), '--recursive'
]
subprocess.check_call(cmd)
# Gets the attribute table of the planted forest extent 1x1 tile shapefile
gadm = glob.glob('{}*.dbf'.format(cn.pattern_plant_1x1_index))[0]
# Converts the attribute table to a dataframe
dbf = Dbf5(gadm)
df = dbf.to_dataframe()
# Converts the column of the dataframe with the names of the tiles (which contain their coordinates) to a list
planted_list_1x1 = df['location'].tolist()
planted_list_1x1 = [str(y) for y in planted_list_1x1]
print "List of 1x1 degree tiles in countries that have planted forests, with defining coordinate in the northwest corner:", planted_list_1x1
print "There are", len(
planted_list_1x1
), "1x1 planted forest extent tiles to iterate through."
# Creates 1x1 degree tiles of plantation growth wherever there are plantations.
# Because this is iterating through only 1x1 tiles that are known to have planted forests (from a previous run
# of this script), it does not need to check whether there are planted forests in this tile. It goes directly
# to intersecting the planted forest table with the 1x1 tile.
# For multiprocessor use
# This works with 30 processors on an r4.16xlarge.
num_of_processes = 50
pool = Pool(num_of_processes)
pool.map(plantation_preparation.create_1x1_plantation_from_1x1_planted,
planted_list_1x1)
pool.close()
pool.join()
### All entry points meet here: creation of 10x10 degree planted forest tiles from 1x1 degree planted forest tiles
# Name of the vrt of 1x1 planted forest tiles
plant_1x1_vrt = 'plant_1x1.vrt'
# Creates a mosaic of all the 1x1 plantation growth rate tiles
print "Creating vrt of 1x1 plantation growth rate tiles"
os.system('gdalbuildvrt {} plant_*.tif'.format(plant_1x1_vrt))
# Creates 10x10 degree tiles of plantation growth by iterating over the pixel area tiles that are in latitudes with planted forests
# For multiprocessor use
num_of_processes = 20
pool = Pool(num_of_processes)
pool.map(
partial(plantation_preparation.create_10x10_plantation,
plant_1x1_vrt=plant_1x1_vrt), planted_lat_tile_list)
pool.close()
pool.join()