def pre_process_tasks(run_for_test=False):
path10 = utils.get_rgi_region_file('10', '61')
path13 = utils.get_rgi_region_file('13', '61')
path14 = utils.get_rgi_region_file('14', '61')
path15 = utils.get_rgi_region_file('15', '61')
rgidf10 = gpd.read_file(path10)
rgidf10 = rgidf10[rgidf10.O2Region == '4']
rgidf13 = gpd.read_file(path13)
rgidf14 = gpd.read_file(path14)
rgidf15 = gpd.read_file(path15)
rgidf = pd.concat([rgidf10, rgidf13, rgidf14, rgidf15])
if (not run_in_cluster) or run_for_test:
rgidf = rgidf10.iloc[0:5, :]
cfg.initialize()
cfg.PARAMS['border'] = 160
cfg.PATHS['working_dir'] = utils.mkdir(working_dir)
cfg.PARAMS['continue_on_error'] = True
cfg.PARAMS['use_multiprocessing'] = True
gdirs = workflow.init_glacier_directories(rgidf, from_prepro_level=1,
reset=True, force=True)
task_list = [
tasks.define_glacier_region,
tasks.glacier_masks,
tasks.compute_centerlines,
tasks.initialize_flowlines,
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
tasks.catchment_area,
tasks.catchment_intersections,
tasks.catchment_width_geom,
tasks.catchment_width_correction,
tasks.process_cru_data,
tasks.local_t_star,
tasks.mu_star_calibration,
tasks.prepare_for_inversion,
tasks.mass_conservation_inversion,
tasks.filter_inversion_output,
tasks.init_present_time_glacier
]
for task in task_list:
workflow.execute_entity_task(task, gdirs)
return gdirs
def test_rgi(self):
# Make a fake RGI file
rgi_dir = os.path.join(self.dldir, 'rgi50')
utils.mkdir(rgi_dir)
make_fake_zipdir(os.path.join(rgi_dir, '01_rgi50_Region'),
fakefile='test.txt')
rgi_f = make_fake_zipdir(rgi_dir, fakefile='000_rgi50_manifest.txt')
def down_check(url, cache_name=None, reset=False):
expected = 'http://www.glims.org/RGI/rgi50_files/rgi50.zip'
self.assertEqual(url, expected)
return rgi_f
with FakeDownloadManager('_progress_urlretrieve', down_check):
rgi = utils.get_rgi_dir()
assert os.path.isdir(rgi)
assert os.path.exists(os.path.join(rgi, '000_rgi50_manifest.txt'))
assert os.path.exists(os.path.join(rgi, '01_rgi50_Region', 'test.txt'))
# Make a fake RGI file
rgi_dir = os.path.join(self.dldir, 'rgi60')
utils.mkdir(rgi_dir)
make_fake_zipdir(os.path.join(rgi_dir, '01_rgi60_Region'),
fakefile='01_rgi60_Region.shp')
rgi_f = make_fake_zipdir(rgi_dir, fakefile='000_rgi60_manifest.txt')
def down_check(url, cache_name=None, reset=False):
expected = 'http://www.glims.org/RGI/rgi60_files/00_rgi60.zip'
self.assertEqual(url, expected)
return rgi_f
with FakeDownloadManager('_progress_urlretrieve', down_check):
rgi = utils.get_rgi_dir(version='6')
assert os.path.isdir(rgi)
assert os.path.exists(os.path.join(rgi, '000_rgi60_manifest.txt'))
assert os.path.exists(
os.path.join(rgi, '01_rgi60_Region', '01_rgi60_Region.shp'))
with FakeDownloadManager('_progress_urlretrieve', down_check):
rgi_f = utils.get_rgi_region_file('01', version='6')
assert os.path.exists(rgi_f)
assert '01_rgi60_Region.shp' in rgi_f
def merge_wgms_lec(wgms, lec, repeat=False):
if repeat:
lec.loc[:, 'region'] = lec.rgi_id.apply(
lambda x: x.split('RGI60-')[-1].split('.')[0])
# sort values by RGI Id and set index
lec = lec.sort_values(by='rgi_id')
lec = lec.set_index('rgi_id').drop('Unnamed: 0', axis=1)
lec = lec[~lec.index.isin(wgms_df.index)]
lec.loc[:, 'rgi_area'] = np.nan
lec.loc[:, 'rgi_date'] = np.nan
for region in lec.region.unique():
ids = lec[lec.region == region].drop('region', axis=1)
# RGI file
path = utils.get_rgi_region_file(str(region).zfill(2),
version='61')
rgidf = gpd.read_file(path).set_index('RGIId')
rgidf.index.name = 'rgi_id'
df2 = pd.DataFrame()
df2.loc[:, 'rgi_area'] = rgidf[rgidf.index.isin(ids.index)].Area
date = rgidf[rgidf.index.isin(
ids.index)].BgnDate.apply(lambda x: int(str(x)[:4]))
df2.loc[:, 'rgi_date'] = date
print(df2.rgi_date)
lec.update(df2)
lec.loc[:, 'relative_diff'] = lec.area_diff / lec.rgi_area
lec = lec.rename(columns={"bias": "mb_bias"})
all = wgms.append(lec)
all = all[[
'region', 'rgi_date', 'rgi_area', 'temp_bias', 'iterations',
'mb_bias', 'area_diff', 'relative_diff', 'error'
]]
all.to_csv(
os.path.join(cfg.PATHS['working_dir'], 'all_experiment_df.csv'))
else:
all = pd.read_csv(
os.path.join(cfg.PATHS['working_dir'], 'all_experiment_df.csv'))
return all
def create_model_lec_df(home, repeat=False):
model_df = pd.DataFrame()
p = os.path.join(home, 'lec_model_df.pkl')
if repeat or not os.path.isfile(p):
for d in [d for d in os.listdir(home) if d.startswith('temp')]:
temp_bias = float(d.split('_')[-1])
dir = os.path.join(home, d)
if temp_bias <= 0:
for file in [
os.path.join(dir, d1) for d1 in os.listdir(dir)
if d1.endswith('.pkl')
]:
df = pd.read_pickle(file, compression='gzip')
df = df.assign(temp_bias=temp_bias)
model_df = model_df.append(df,
ignore_index=False,
sort=True)
model_df.index.name = 'rgi_id'
model_df.loc[:, 'rgi_date'] = model_df.ex_mod.apply(
lambda x: int(x.area_km2_ts().index[-1]))
model_df.loc[:, 'region'] = model_df.index.map(
lambda x: int(x.split('RGI60-')[-1].split('.')[0]))
for region in model_df.region.unique():
ids = model_df[model_df.region == region].index.get_level_values(0)
# RGI file
path = utils.get_rgi_region_file(str(region).zfill(2),
version='61')
rgidf = gpd.read_file(path).set_index('RGIId')
rgidf = rgidf[rgidf.index.isin(ids)]
model_df.loc[rgidf.index, 'rgi_area'] = rgidf.Area
model_df = model_df.reset_index().set_index(['rgi_id', 'temp_bias'
]).sort_index()
model_df.loc[:, 'ex_area'] = model_df.ex_mod.apply(
lambda x: x.area_km2_ts().values[-1])
model_df.to_pickle(p, compression='gzip')
return model_df
else:
return pd.read_pickle(p, compression='gzip')
def run_prepro_levels(rgi_version=None,
rgi_reg=None,
border=None,
output_folder='',
working_dir='',
dem_source='',
is_test=False,
demo=False,
test_rgidf=None,
test_intersects_file=None,
test_topofile=None,
test_crudir=None,
disable_mp=False,
timeout=0,
max_level=4,
logging_level='WORKFLOW'):
"""Does the actual job.
Parameters
----------
rgi_version : str
the RGI version to use (defaults to cfg.PARAMS)
rgi_reg : str
the RGI region to process
border : int
the number of pixels at the maps border
output_folder : str
path to the output folder (where to put the preprocessed tar files)
dem_source : str
which DEM source to use: default, SOURCE_NAME or ALL
working_dir : str
path to the OGGM working directory
is_test : bool
to test on a couple of glaciers only!
demo : bool
to run the prepro for the list of demo glaciers
test_rgidf : shapefile
for testing purposes only
test_intersects_file : shapefile
for testing purposes only
test_topofile : str
for testing purposes only
test_crudir : str
for testing purposes only
disable_mp : bool
disable multiprocessing
max_level : int
the maximum pre-processing level before stopping
logging_level : str
the logging level to use (DEBUG, INFO, WARNING, WORKFLOW)
"""
# TODO: temporarily silence Fiona deprecation warnings
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
# Input check
if max_level not in [1, 2, 3, 4]:
raise InvalidParamsError('max_level should be one of [1, 2, 3, 4]')
# Time
start = time.time()
def _time_log():
# Log util
m, s = divmod(time.time() - start, 60)
h, m = divmod(m, 60)
log.workflow('OGGM prepro_levels is done! Time needed: '
'{:02d}:{:02d}:{:02d}'.format(int(h), int(m), int(s)))
# Initialize OGGM and set up the run parameters
cfg.initialize(logging_level=logging_level)
# Local paths
utils.mkdir(working_dir)
cfg.PATHS['working_dir'] = working_dir
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = not disable_mp
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = border
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = True
# Timeout
cfg.PARAMS['task_timeout'] = timeout
# For statistics
climate_periods = [1920, 1960, 2000]
if rgi_version is None:
rgi_version = cfg.PARAMS['rgi_version']
rgi_dir_name = 'RGI{}'.format(rgi_version)
border_dir_name = 'b_{:03d}'.format(border)
base_dir = os.path.join(output_folder, rgi_dir_name, border_dir_name)
# Add a package version file
utils.mkdir(base_dir)
opath = os.path.join(base_dir, 'package_versions.txt')
with open(opath, 'w') as vfile:
vfile.write(utils.show_versions(logger=log))
if demo:
rgidf = utils.get_rgi_glacier_entities(cfg.DATA['demo_glaciers'].index)
elif test_rgidf is None:
# Get the RGI file
rgidf = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# We use intersects
rgif = utils.get_rgi_intersects_region_file(rgi_reg,
version=rgi_version)
cfg.set_intersects_db(rgif)
else:
rgidf = test_rgidf
cfg.set_intersects_db(test_intersects_file)
if is_test:
# Just for fun
rgidf = rgidf.sample(4)
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
log.workflow('Starting prepro run for RGI reg: {} '
'and border: {}'.format(rgi_reg, border))
log.workflow('Number of glaciers: {}'.format(len(rgidf)))
# Input
if test_topofile:
cfg.PATHS['dem_file'] = test_topofile
# L1 - initialize working directories
# Which DEM source?
if dem_source.upper() == 'ALL':
# This is the complex one, just do the job an leave
log.workflow('Running prepro on ALL sources')
for i, s in enumerate(utils.DEM_SOURCES):
rs = i == 0
rgidf['DEM_SOURCE'] = s
log.workflow('Running prepro on sources: {}'.format(s))
gdirs = workflow.init_glacier_regions(rgidf, reset=rs, force=rs)
workflow.execute_entity_task(_rename_dem_folder, gdirs, source=s)
# Compress all in output directory
l_base_dir = os.path.join(base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
_time_log()
return
if dem_source:
# Force a given source
rgidf['DEM_SOURCE'] = dem_source.upper()
# L1 - go
gdirs = workflow.init_glacier_regions(rgidf, reset=True, force=True)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L1', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L1 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
if max_level == 1:
_time_log()
return
# L2 - Tasks
# Pre-download other files just in case
if test_crudir is None:
_ = utils.get_cru_file(var='tmp')
_ = utils.get_cru_file(var='pre')
else:
cfg.PATHS['cru_dir'] = test_crudir
workflow.execute_entity_task(tasks.process_cru_data, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L2', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L2 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L2')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
if max_level == 2:
_time_log()
return
# L3 - Tasks
task_list = [
tasks.glacier_masks, tasks.compute_centerlines,
tasks.initialize_flowlines, tasks.compute_downstream_line,
tasks.compute_downstream_bedshape, tasks.catchment_area,
tasks.catchment_intersections, tasks.catchment_width_geom,
tasks.catchment_width_correction, tasks.local_t_star,
tasks.mu_star_calibration, tasks.prepare_for_inversion,
tasks.mass_conservation_inversion, tasks.filter_inversion_output,
tasks.init_present_time_glacier
]
for task in task_list:
workflow.execute_entity_task(task, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L3', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
opath = os.path.join(sum_dir, 'climate_statistics_{}.csv'.format(rgi_reg))
utils.compile_climate_statistics(gdirs,
add_climate_period=climate_periods,
path=opath)
# L3 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L3')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
if max_level == 3:
_time_log()
return
# L4 - No tasks: add some stats for consistency and make the dirs small
sum_dir = os.path.join(base_dir, 'L4', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# Copy mini data to new dir
base_dir = os.path.join(base_dir, 'L4')
mini_gdirs = workflow.execute_entity_task(tasks.copy_to_basedir,
gdirs,
base_dir=base_dir)
# L4 OK - compress all in output directory
workflow.execute_entity_task(utils.gdir_to_tar, mini_gdirs, delete=True)
utils.base_dir_to_tar(base_dir)
_time_log()
if ON_CLUSTER:
OUT_DIR = os.environ.get("OUTDIR")
cfg.PATHS['working_dir'] = OUT_DIR
REG = os.environ.get("I")
else:
WORKING_DIR = '/home/juliaeis/Dokumente/OGGM/work_dir/reconstruction/global'
OUT_DIR = WORKING_DIR
cfg.PATHS['working_dir'] = WORKING_DIR
utils.mkdir(WORKING_DIR, reset=False)
cfg.PATHS['plot_dir'] = os.path.join(cfg.PATHS['working_dir'], 'plots')
utils.mkdir(cfg.PATHS['plot_dir'], reset=False)
for dir in os.listdir(OUT_DIR):
if dir.startswith('reg1'):
cfg.PATHS['working_dir'] = os.path.join(OUT_DIR, dir)
REGION = dir.split('reg')[-1].split('-')[0].zfill(2)
if REGION == REG:
# RGI file
path = utils.get_rgi_region_file(REGION, version='61')
rgidf = gpd.read_file(path)
#rgidf = rgidf.sort_values('Area', ascending=False)
# exclude non-landterminating glaciers
rgidf = rgidf[rgidf.TermType == 0]
rgidf = rgidf[rgidf.Connect != 2]
gdirs = workflow.init_glacier_regions(rgidf.head(9))
df = read_results(gdirs)
print(df)
# We are using which baseline data?
cfg.PARAMS['baseline_climate'] = 'CUSTOM'
# change the custom climate data
cfg.PATHS[
'climate_file'] = '/exports/csce/datastore/geos/groups/geos_iceocean/kinnear/SWARM_files/oggm_SWARM_input_cru_ref_hgts/oggm_cru_hgt_input.nc'
# Set to True for operational runs - here we want all glaciers to run
cfg.PARAMS['continue_on_error'] = True
# Change the minimum timestep
cfg.PARAMS['cfl_min_dt'] = 10.0
# Local working directory (where OGGM will write its output) Need to create this beforehand and put the mass balance data in (ref_t_stars.csv).
WORKING_DIR = '/exports/csce/datastore/geos/groups/geos_iceocean/kinnear/oggm_runs/oggm_mswep_era_reference_run_90_geodetic'
cfg.PATHS['working_dir'] = WORKING_DIR
# RGI file setup, easiest but very inelegant way to do this atm is to make a list of all 13,14,15 RGI glaciers then filtering
#Start with 13,14 and 15
path = utils.get_rgi_region_file('13', version=rgi_version)
rgidf_13 = gpd.read_file(path)
path = utils.get_rgi_region_file('14', version=rgi_version)
rgidf_14 = gpd.read_file(path)
path = utils.get_rgi_region_file('15', version=rgi_version)
rgidf_15 = gpd.read_file(path)
#Now combine the files
# rgidf_temp = rgidf_13.concat(rgidf_14)
# rgidf = rgidf_temp.concat(rgidf_15)
rgidf = gpd.GeoDataFrame(pd.concat([rgidf_13, rgidf_14, rgidf_15]))
#print(rgidf)
# Get the shapefile
basin = gpd.read_file(
'/exports/csce/datastore/geos/groups/geos_iceocean/kinnear/SWARM-OGGM-Model/shape_files/swarm_grid.shp'
)
print('got glacier shp')
# Initialize OGGM and set up the default run parameters
cfg.initialize()
# How many grid points around the glacier?
cfg.PARAMS['border'] = 10
# Make it robust
cfg.PARAMS['use_intersects'] = False
cfg.PARAMS['continue_on_error'] = True
# Local working directory (where OGGM will write its output)
cfg.PATHS['working_dir'] = utils.get_temp_dir('some_wd')
# RGI file
path = utils.get_rgi_region_file('11')
rgidf = gpd.read_file(path)
# Select only 2 glaciers
rgidf = rgidf.iloc[:2]
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
# Go - create the pre-processed glacier directories
gdirs = workflow.init_glacier_directories(rgidf)
# Our task now
from dummy_task_module import dummy_task
workflow.execute_entity_task(dummy_task, gdirs)
def run_benchmark(rgi_version=None, rgi_reg=None, border=None,
output_folder='', working_dir='', is_test=False,
test_rgidf=None, test_intersects_file=None,
test_topofile=None, test_crudir=None):
"""Does the actual job.
Parameters
----------
rgi_version : str
the RGI version to use (defaults to cfg.PARAMS)
rgi_reg : str
the RGI region to process
border : int
the number of pixels at the maps border
output_folder : str
path to the output folder (where to put the preprocessed tar files)
working_dir : str
path to the OGGM working directory
is_test : bool
to test on a couple of glaciers only!
test_rgidf : shapefile
for testing purposes only
test_intersects_file : shapefile
for testing purposes only
test_topofile : str
for testing purposes only
test_crudir : str
for testing purposes only
"""
# TODO: temporarily silence Fiona deprecation warnings
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
# Module logger
log = logging.getLogger(__name__)
# Initialize OGGM and set up the run parameters
cfg.initialize(logging_level='WORKFLOW')
# Local paths
utils.mkdir(working_dir)
cfg.PATHS['working_dir'] = working_dir
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = True
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = border
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = True
# For statistics
odf = pd.DataFrame()
if rgi_version is None:
rgi_version = cfg.PARAMS['rgi_version']
base_dir = os.path.join(output_folder)
# Add a package version file
utils.mkdir(base_dir)
opath = os.path.join(base_dir, 'package_versions.txt')
with open(opath, 'w') as vfile:
vfile.write(utils.show_versions(logger=log))
# Read RGI
start = time.time()
if test_rgidf is None:
# Get the RGI file
rgidf = gpd.read_file(utils.get_rgi_region_file(rgi_reg,
version=rgi_version))
# We use intersects
rgif = utils.get_rgi_intersects_region_file(rgi_reg,
version=rgi_version)
cfg.set_intersects_db(rgif)
else:
rgidf = test_rgidf
cfg.set_intersects_db(test_intersects_file)
if is_test:
# Just for fun
rgidf = rgidf.sample(2)
_add_time_to_df(odf, 'Read RGI', time.time()-start)
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
log.workflow('Starting prepro run for RGI reg: {} '
'and border: {}'.format(rgi_reg, border))
log.workflow('Number of glaciers: {}'.format(len(rgidf)))
# Input
if test_topofile:
cfg.PATHS['dem_file'] = test_topofile
# Initialize working directories
start = time.time()
gdirs = workflow.init_glacier_regions(rgidf, reset=True, force=True)
_add_time_to_df(odf, 'init_glacier_regions', time.time()-start)
# Pre-download other files just in case
if test_crudir is None:
_ = utils.get_cru_file(var='tmp')
_ = utils.get_cru_file(var='pre')
else:
cfg.PATHS['cru_dir'] = test_crudir
# Tasks
task_list = [
tasks.process_cru_data,
tasks.glacier_masks,
tasks.compute_centerlines,
tasks.initialize_flowlines,
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
tasks.catchment_area,
tasks.catchment_intersections,
tasks.catchment_width_geom,
tasks.catchment_width_correction,
tasks.local_t_star,
tasks.mu_star_calibration,
tasks.prepare_for_inversion,
tasks.mass_conservation_inversion,
tasks.filter_inversion_output,
tasks.init_present_time_glacier,
]
for task in task_list:
start = time.time()
workflow.execute_entity_task(task, gdirs)
_add_time_to_df(odf, task.__name__, time.time()-start)
# Runs
start = time.time()
workflow.execute_entity_task(tasks.run_random_climate, gdirs,
nyears=250, bias=0, seed=0,
output_filesuffix='_tstar')
_add_time_to_df(odf, 'run_random_climate_tstar_250', time.time()-start)
start = time.time()
workflow.execute_entity_task(tasks.run_random_climate, gdirs,
nyears=250, y0=1995, seed=0,
output_filesuffix='_commit')
_add_time_to_df(odf, 'run_random_climate_commit_250', time.time()-start)
# Compile results
start = time.time()
utils.compile_glacier_statistics(gdirs)
_add_time_to_df(odf, 'compile_glacier_statistics', time.time()-start)
start = time.time()
utils.compile_climate_statistics(gdirs,
add_climate_period=[1920, 1960, 2000])
_add_time_to_df(odf, 'compile_climate_statistics', time.time()-start)
start = time.time()
utils.compile_run_output(gdirs, filesuffix='_tstar')
_add_time_to_df(odf, 'compile_run_output_tstar', time.time()-start)
start = time.time()
utils.compile_run_output(gdirs, filesuffix='_commit')
_add_time_to_df(odf, 'compile_run_output_commit', time.time()-start)
# Log
opath = os.path.join(base_dir, 'benchmarks_b{:03d}.csv'.format(border))
odf.index.name = 'Task'
odf.to_csv(opath)
log.workflow('OGGM benchmarks is done!')
def run_benchmark(rgi_version=None,
rgi_reg=None,
border=None,
output_folder='',
working_dir='',
is_test=False,
test_rgidf=None,
test_intersects_file=None,
test_topofile=None):
"""Does the actual job.
Parameters
----------
rgi_version : str
the RGI version to use (defaults to cfg.PARAMS)
rgi_reg : str
the RGI region to process
border : int
the number of pixels at the maps border
output_folder : str
path to the output folder (where to put the preprocessed tar files)
working_dir : str
path to the OGGM working directory
is_test : bool
to test on a couple of glaciers only!
test_rgidf : shapefile
for testing purposes only
test_intersects_file : shapefile
for testing purposes only
test_topofile : str
for testing purposes only
"""
# TODO: temporarily silence Fiona deprecation warnings
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
# Module logger
log = logging.getLogger(__name__)
# Initialize OGGM and set up the run parameters
cfg.initialize(logging_level='WORKFLOW')
# Local paths
utils.mkdir(working_dir)
cfg.PATHS['working_dir'] = working_dir
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = True
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = border
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = True
# For statistics
odf = pd.DataFrame()
if rgi_version is None:
rgi_version = cfg.PARAMS['rgi_version']
base_dir = os.path.join(output_folder)
# Add a package version file
utils.mkdir(base_dir)
opath = os.path.join(base_dir, 'package_versions.txt')
with open(opath, 'w') as vfile:
vfile.write(utils.show_versions(logger=log))
# Read RGI
start = time.time()
if test_rgidf is None:
# Get the RGI file
rgidf = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# We use intersects
rgif = utils.get_rgi_intersects_region_file(rgi_reg,
version=rgi_version)
cfg.set_intersects_db(rgif)
else:
rgidf = test_rgidf
cfg.set_intersects_db(test_intersects_file)
if is_test:
# Just for fun
rgidf = rgidf.sample(2)
_add_time_to_df(odf, 'Read RGI', time.time() - start)
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
log.workflow('Starting prepro run for RGI reg: {} '
'and border: {}'.format(rgi_reg, border))
log.workflow('Number of glaciers: {}'.format(len(rgidf)))
# Input
if test_topofile:
cfg.PATHS['dem_file'] = test_topofile
# Initialize working directories
start = time.time()
gdirs = workflow.init_glacier_directories(rgidf, reset=True, force=True)
_add_time_to_df(odf, 'init_glacier_directories', time.time() - start)
# Tasks
task_list = [
tasks.define_glacier_region,
tasks.process_cru_data,
tasks.glacier_masks,
tasks.compute_centerlines,
tasks.initialize_flowlines,
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
tasks.catchment_area,
tasks.catchment_intersections,
tasks.catchment_width_geom,
tasks.catchment_width_correction,
tasks.local_t_star,
tasks.mu_star_calibration,
tasks.prepare_for_inversion,
tasks.mass_conservation_inversion,
tasks.filter_inversion_output,
tasks.init_present_time_glacier,
]
for task in task_list:
start = time.time()
workflow.execute_entity_task(task, gdirs)
_add_time_to_df(odf, task.__name__, time.time() - start)
# Runs
start = time.time()
workflow.execute_entity_task(tasks.run_random_climate,
gdirs,
nyears=250,
bias=0,
seed=0,
output_filesuffix='_tstar')
_add_time_to_df(odf, 'run_random_climate_tstar_250', time.time() - start)
start = time.time()
workflow.execute_entity_task(tasks.run_random_climate,
gdirs,
nyears=250,
y0=1995,
seed=0,
output_filesuffix='_commit')
_add_time_to_df(odf, 'run_random_climate_commit_250', time.time() - start)
# Compile results
start = time.time()
utils.compile_glacier_statistics(gdirs)
_add_time_to_df(odf, 'compile_glacier_statistics', time.time() - start)
start = time.time()
utils.compile_climate_statistics(gdirs,
add_climate_period=[1920, 1960, 2000])
_add_time_to_df(odf, 'compile_climate_statistics', time.time() - start)
start = time.time()
utils.compile_run_output(gdirs, input_filesuffix='_tstar')
_add_time_to_df(odf, 'compile_run_output_tstar', time.time() - start)
start = time.time()
utils.compile_run_output(gdirs, input_filesuffix='_commit')
_add_time_to_df(odf, 'compile_run_output_commit', time.time() - start)
# Log
opath = os.path.join(base_dir, 'benchmarks_b{:03d}.csv'.format(border))
odf.index.name = 'Task'
odf.to_csv(opath)
log.workflow('OGGM benchmarks is done!')
utils.mkdir(WORKING_DIR)
cfg.PATHS['working_dir'] = WORKING_DIR
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = True
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = 160
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = True
cfg.PARAMS['auto_skip_task'] = False
# Get the RGI file
rgidf = gpd.read_file(utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
# Module logger
log = logging.getLogger(__name__)
log.info('Starting run for RGI reg: ' + rgi_reg)
log.info('Number of glaciers: {}'.format(len(rgidf)))
# Go - initialize working directories
gdirs = workflow.init_glacier_regions(rgidf, from_prepro_level=0)
# Tasks
workflow.execute_entity_task(tasks.glacier_masks, gdirs)
cfg.PARAMS['temp_melt'] = -1.75
cfg.PARAMS['temp_all_solid'] = 0.0
# add to BASENAMES
_doc = 'contains observed and searched glacier from synthetic experiment to find intial state'
cfg.BASENAMES['synthetic_experiment'] = ('synthetic_experiment.pkl', _doc)
# We use intersects
db = utils.get_rgi_intersects_region_file(version='61', region='11')
cfg.set_intersects_db(db)
cfg.PARAMS['run_mb_calibration'] = False
cfg.PARAMS['optimize_inversion_params'] = False
# RGI file
path = utils.get_rgi_region_file('11', version='61')
rgidf = gpd.read_file(path)
rgidf = rgidf[rgidf.RGIId == 'RGI60-11.00779']
# sort for efficient using
rgidf = rgidf.sort_values('Area', ascending=False)
if ON_CLUSTER:
rgidf = rgidf[job_nr:len(rgidf):80]
gdirs = workflow.init_glacier_regions(rgidf)
for gdir in gdirs:
if os.path.isfile(os.path.join(gdir.dir, 'model_run_experiment.nc')):
start = time.time()
def run_prepro_levels(rgi_version=None, rgi_reg=None, border=None,
output_folder='', working_dir='', is_test=False,
demo=False, test_rgidf=None, test_intersects_file=None,
test_topofile=None, test_crudir=None):
"""Does the actual job.
Parameters
----------
rgi_version : str
the RGI version to use (defaults to cfg.PARAMS)
rgi_reg : str
the RGI region to process
border : int
the number of pixels at the maps border
output_folder : str
path to the output folder (where to put the preprocessed tar files)
working_dir : str
path to the OGGM working directory
is_test : bool
to test on a couple of glaciers only!
demo : bool
to run the prepro for the list of demo glaciers
test_rgidf : shapefile
for testing purposes only
test_intersects_file : shapefile
for testing purposes only
test_topofile : str
for testing purposes only
test_crudir : str
for testing purposes only
"""
# TODO: temporarily silence Fiona deprecation warnings
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
# Module logger
log = logging.getLogger(__name__)
# Time
start = time.time()
# Initialize OGGM and set up the run parameters
cfg.initialize(logging_level='WORKFLOW')
# Local paths
utils.mkdir(working_dir)
cfg.PATHS['working_dir'] = working_dir
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = True
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = border
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = True
# For statistics
climate_periods = [1920, 1960, 2000]
if rgi_version is None:
rgi_version = cfg.PARAMS['rgi_version']
rgi_dir_name = 'RGI{}'.format(rgi_version)
border_dir_name = 'b_{:03d}'.format(border)
base_dir = os.path.join(output_folder, rgi_dir_name, border_dir_name)
# Add a package version file
utils.mkdir(base_dir)
opath = os.path.join(base_dir, 'package_versions.txt')
with open(opath, 'w') as vfile:
vfile.write(utils.show_versions(logger=log))
if demo:
rgidf = utils.get_rgi_glacier_entities(cfg.DEMO_GLACIERS.index)
elif test_rgidf is None:
# Get the RGI file
rgidf = gpd.read_file(utils.get_rgi_region_file(rgi_reg,
version=rgi_version))
# We use intersects
rgif = utils.get_rgi_intersects_region_file(rgi_reg,
version=rgi_version)
cfg.set_intersects_db(rgif)
else:
rgidf = test_rgidf
cfg.set_intersects_db(test_intersects_file)
if is_test:
# Just for fun
rgidf = rgidf.sample(4)
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
log.workflow('Starting prepro run for RGI reg: {} '
'and border: {}'.format(rgi_reg, border))
log.workflow('Number of glaciers: {}'.format(len(rgidf)))
# Input
if test_topofile:
cfg.PATHS['dem_file'] = test_topofile
# L1 - initialize working directories
gdirs = workflow.init_glacier_regions(rgidf, reset=True, force=True)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L1', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L1 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar, gdirs, delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
# L2 - Tasks
# Pre-download other files just in case
if test_crudir is None:
_ = utils.get_cru_file(var='tmp')
_ = utils.get_cru_file(var='pre')
else:
cfg.PATHS['cru_dir'] = test_crudir
workflow.execute_entity_task(tasks.process_cru_data, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L2', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L2 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L2')
workflow.execute_entity_task(utils.gdir_to_tar, gdirs, delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
# L3 - Tasks
task_list = [
tasks.glacier_masks,
tasks.compute_centerlines,
tasks.initialize_flowlines,
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
tasks.catchment_area,
tasks.catchment_intersections,
tasks.catchment_width_geom,
tasks.catchment_width_correction,
tasks.local_t_star,
tasks.mu_star_calibration,
tasks.prepare_for_inversion,
tasks.mass_conservation_inversion,
tasks.filter_inversion_output,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L3', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
opath = os.path.join(sum_dir, 'climate_statistics_{}.csv'.format(rgi_reg))
utils.compile_climate_statistics(gdirs, add_climate_period=climate_periods,
path=opath)
# L3 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L3')
workflow.execute_entity_task(utils.gdir_to_tar, gdirs, delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
# L4 - Tasks
workflow.execute_entity_task(tasks.init_present_time_glacier, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L4', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# Copy mini data to new dir
base_dir = os.path.join(base_dir, 'L4')
mini_gdirs = workflow.execute_entity_task(tasks.copy_to_basedir, gdirs,
base_dir=base_dir)
# L4 OK - compress all in output directory
workflow.execute_entity_task(utils.gdir_to_tar, mini_gdirs, delete=True)
utils.base_dir_to_tar(base_dir)
# Log
m, s = divmod(time.time() - start, 60)
h, m = divmod(m, 60)
log.workflow('OGGM prepro_levels is done! Time needed: '
'{:02d}:{:02d}:{:02d}'.format(int(h), int(m), int(s)))
rgi_version = '61'
rgi_region = '11' # Region Central Europe
# Here we override some of the default parameters
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large:
# here, 80 is more than enough
cfg.PARAMS['border'] = 80
# Local working directory (where OGGM will write its output)
WORKING_DIR = utils.gettempdir('OGGM_Rofental')
utils.mkdir(WORKING_DIR, reset=True)
cfg.PATHS['working_dir'] = WORKING_DIR
# RGI file
path = utils.get_rgi_region_file(rgi_region, version=rgi_version)
rgidf = gpd.read_file(path)
# Get the Rofental Basin file
path = utils.get_demo_file('rofental_hydrosheds.shp')
basin = gpd.read_file(path)
# Take all glaciers in the Rofental Basin
in_bas = [basin.geometry.contains(shpg.Point(x, y))[0] for
(x, y) in zip(rgidf.CenLon, rgidf.CenLat)]
rgidf = rgidf.loc[in_bas]
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
log.workflow('Starting OGGM run')
def run_prepro_levels(rgi_version=None,
rgi_reg=None,
border=None,
output_folder='',
working_dir='',
dem_source='',
is_test=False,
test_ids=None,
demo=False,
test_rgidf=None,
test_intersects_file=None,
test_topofile=None,
disable_mp=False,
params_file=None,
elev_bands=False,
match_geodetic_mb=False,
centerlines_only=False,
add_consensus=False,
max_level=5,
logging_level='WORKFLOW',
disable_dl_verify=False):
"""Does the actual job.
Parameters
----------
rgi_version : str
the RGI version to use (defaults to cfg.PARAMS)
rgi_reg : str
the RGI region to process
border : int
the number of pixels at the maps border
output_folder : str
path to the output folder (where to put the preprocessed tar files)
dem_source : str
which DEM source to use: default, SOURCE_NAME or ALL
working_dir : str
path to the OGGM working directory
params_file : str
path to the OGGM parameter file (to override defaults)
is_test : bool
to test on a couple of glaciers only!
test_ids : list
if is_test: list of ids to process
demo : bool
to run the prepro for the list of demo glaciers
test_rgidf : shapefile
for testing purposes only
test_intersects_file : shapefile
for testing purposes only
test_topofile : str
for testing purposes only
test_crudir : str
for testing purposes only
disable_mp : bool
disable multiprocessing
elev_bands : bool
compute all flowlines based on the Huss&Hock 2015 method instead
of the OGGM default, which is a mix of elev_bands and centerlines.
centerlines_only : bool
compute all flowlines based on the OGGM centerline(s) method instead
of the OGGM default, which is a mix of elev_bands and centerlines.
match_geodetic_mb : bool
match the regional mass-balance estimates at the regional level
(currently Hugonnet et al., 2020).
add_consensus : bool
adds (reprojects) the consensus estimates thickness to the glacier
directories. With elev_bands=True, the data will also be binned.
max_level : int
the maximum pre-processing level before stopping
logging_level : str
the logging level to use (DEBUG, INFO, WARNING, WORKFLOW)
disable_dl_verify : bool
disable the hash verification of OGGM downloads
"""
# TODO: temporarily silence Fiona and other deprecation warnings
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
# Input check
if max_level not in [1, 2, 3, 4, 5]:
raise InvalidParamsError('max_level should be one of [1, 2, 3, 4, 5]')
# Time
start = time.time()
def _time_log():
# Log util
m, s = divmod(time.time() - start, 60)
h, m = divmod(m, 60)
log.workflow('OGGM prepro_levels is done! Time needed: '
'{:02d}:{:02d}:{:02d}'.format(int(h), int(m), int(s)))
# Config Override Params
params = {}
# Local paths
utils.mkdir(working_dir)
params['working_dir'] = working_dir
# Initialize OGGM and set up the run parameters
cfg.initialize(file=params_file,
params=params,
logging_level=logging_level,
future=True)
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = not disable_mp
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = border
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = True
# Check for the integrity of the files OGGM downloads at run time
# For large files (e.g. using a 1 tif DEM like ALASKA) calculating the hash
# takes a long time, so deactivating this can make sense
cfg.PARAMS['dl_verify'] = not disable_dl_verify
# Log the parameters
msg = '# OGGM Run parameters:'
for k, v in cfg.PARAMS.items():
if type(v) in [pd.DataFrame, dict]:
continue
msg += '\n {}: {}'.format(k, v)
log.workflow(msg)
if rgi_version is None:
rgi_version = cfg.PARAMS['rgi_version']
output_base_dir = os.path.join(output_folder, 'RGI{}'.format(rgi_version),
'b_{:03d}'.format(border))
# Add a package version file
utils.mkdir(output_base_dir)
opath = os.path.join(output_base_dir, 'package_versions.txt')
with open(opath, 'w') as vfile:
vfile.write(utils.show_versions(logger=log))
if demo:
rgidf = utils.get_rgi_glacier_entities(cfg.DATA['demo_glaciers'].index)
elif test_rgidf is None:
# Get the RGI file
rgidf = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# We use intersects
rgif = utils.get_rgi_intersects_region_file(rgi_reg,
version=rgi_version)
cfg.set_intersects_db(rgif)
# Some RGI input quality checks - this is based on visual checks
# of large glaciers in the RGI
ids_to_ice_cap = [
'RGI60-05.10315', # huge Greenland ice cap
'RGI60-03.01466', # strange thing next to Devon
'RGI60-09.00918', # Academy of sciences Ice cap
'RGI60-09.00969',
'RGI60-09.00958',
'RGI60-09.00957',
]
rgidf.loc[rgidf.RGIId.isin(ids_to_ice_cap), 'Form'] = '1'
# In AA almost all large ice bodies are actually ice caps
if rgi_reg == '19':
rgidf.loc[rgidf.Area > 100, 'Form'] = '1'
# For greenland we omit connectivity level 2
if rgi_reg == '05':
rgidf = rgidf.loc[rgidf['Connect'] != 2]
else:
rgidf = test_rgidf
cfg.set_intersects_db(test_intersects_file)
if is_test:
if test_ids is not None:
rgidf = rgidf.loc[rgidf.RGIId.isin(test_ids)]
else:
rgidf = rgidf.sample(4)
log.workflow('Starting prepro run for RGI reg: {} '
'and border: {}'.format(rgi_reg, border))
log.workflow('Number of glaciers: {}'.format(len(rgidf)))
# L0 - go
gdirs = workflow.init_glacier_directories(rgidf, reset=True, force=True)
# Glacier stats
sum_dir = os.path.join(output_base_dir, 'L0', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L0 OK - compress all in output directory
log.workflow('L0 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L0')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 0:
_time_log()
return
# L1 - Add dem files
if test_topofile:
cfg.PATHS['dem_file'] = test_topofile
# Which DEM source?
if dem_source.upper() == 'ALL':
# This is the complex one, just do the job and leave
log.workflow('Running prepro on ALL sources')
for i, s in enumerate(utils.DEM_SOURCES):
rs = i == 0
log.workflow('Running prepro on sources: {}'.format(s))
gdirs = workflow.init_glacier_directories(rgidf,
reset=rs,
force=rs)
workflow.execute_entity_task(tasks.define_glacier_region,
gdirs,
source=s)
workflow.execute_entity_task(_rename_dem_folder, gdirs, source=s)
# make a GeoTiff mask of the glacier, choose any source
workflow.execute_entity_task(gis.rasterio_glacier_mask,
gdirs,
source='ALL')
# Compress all in output directory
level_base_dir = os.path.join(output_base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
_time_log()
return
# Force a given source
source = dem_source.upper() if dem_source else None
# L1 - go
workflow.execute_entity_task(tasks.define_glacier_region,
gdirs,
source=source)
# Glacier stats
sum_dir = os.path.join(output_base_dir, 'L1', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L1 OK - compress all in output directory
log.workflow('L1 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 1:
_time_log()
return
# L2 - Tasks
# Check which glaciers will be processed as what
if elev_bands:
gdirs_band = gdirs
gdirs_cent = []
elif centerlines_only:
gdirs_band = []
gdirs_cent = gdirs
else:
# Default is to mix
# Curated list of large (> 50 km2) glaciers that don't run
# (CFL error) mostly because the centerlines are crap
# This is a really temporary fix until we have some better
# solution here
ids_to_bands = [
'RGI60-01.13696', 'RGI60-03.01710', 'RGI60-01.13635',
'RGI60-01.14443', 'RGI60-03.01678', 'RGI60-03.03274',
'RGI60-01.17566', 'RGI60-03.02849', 'RGI60-01.16201',
'RGI60-01.14683', 'RGI60-07.01506', 'RGI60-07.01559',
'RGI60-03.02687', 'RGI60-17.00172', 'RGI60-01.23649',
'RGI60-09.00077', 'RGI60-03.00994', 'RGI60-01.26738',
'RGI60-03.00283', 'RGI60-01.16121', 'RGI60-01.27108',
'RGI60-09.00132', 'RGI60-13.43483', 'RGI60-09.00069',
'RGI60-14.04404', 'RGI60-17.01218', 'RGI60-17.15877',
'RGI60-13.30888', 'RGI60-17.13796', 'RGI60-17.15825',
'RGI60-01.09783'
]
if rgi_reg == '19':
gdirs_band = gdirs
gdirs_cent = []
else:
gdirs_band = []
gdirs_cent = []
for gdir in gdirs:
if gdir.is_icecap or gdir.rgi_id in ids_to_bands:
gdirs_band.append(gdir)
else:
gdirs_cent.append(gdir)
log.workflow('Start flowline processing with: '
'N centerline type: {}, '
'N elev bands type: {}.'
''.format(len(gdirs_cent), len(gdirs_band)))
# HH2015 method
workflow.execute_entity_task(tasks.simple_glacier_masks, gdirs_band)
# Centerlines OGGM
workflow.execute_entity_task(tasks.glacier_masks, gdirs_cent)
if add_consensus:
from oggm.shop.bedtopo import add_consensus_thickness
workflow.execute_entity_task(add_consensus_thickness, gdirs_band)
workflow.execute_entity_task(add_consensus_thickness, gdirs_cent)
# Elev bands with var data
vn = 'consensus_ice_thickness'
workflow.execute_entity_task(tasks.elevation_band_flowline,
gdirs_band,
bin_variables=vn)
workflow.execute_entity_task(tasks.fixed_dx_elevation_band_flowline,
gdirs_band,
bin_variables=vn)
else:
# HH2015 method without it
task_list = [
tasks.elevation_band_flowline,
tasks.fixed_dx_elevation_band_flowline,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs_band)
# HH2015 method
task_list = [
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs_band)
# Centerlines OGGM
task_list = [
tasks.compute_centerlines,
tasks.initialize_flowlines,
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
tasks.catchment_area,
tasks.catchment_intersections,
tasks.catchment_width_geom,
tasks.catchment_width_correction,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs_cent)
# Glacier stats
sum_dir = os.path.join(output_base_dir, 'L2', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L2 OK - compress all in output directory
log.workflow('L2 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L2')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 2:
_time_log()
return
# L3 - Tasks
task_list = [
tasks.process_climate_data,
tasks.historical_climate_qc,
tasks.local_t_star,
tasks.mu_star_calibration,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs)
# Inversion: we match the consensus
workflow.calibrate_inversion_from_consensus(gdirs,
apply_fs_on_mismatch=True,
error_on_mismatch=False)
# Do we want to match geodetic estimates?
# This affects only the bias so we can actually do this *after*
# the inversion, but we really want to take calving into account here
if match_geodetic_mb:
workflow.match_regional_geodetic_mb(gdirs, rgi_reg)
# We get ready for modelling
workflow.execute_entity_task(tasks.init_present_time_glacier, gdirs)
# Glacier stats
sum_dir = os.path.join(output_base_dir, 'L3', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
opath = os.path.join(sum_dir, 'climate_statistics_{}.csv'.format(rgi_reg))
utils.compile_climate_statistics(gdirs, path=opath)
opath = os.path.join(sum_dir,
'fixed_geometry_mass_balance_{}.csv'.format(rgi_reg))
utils.compile_fixed_geometry_mass_balance(gdirs, path=opath)
# L3 OK - compress all in output directory
log.workflow('L3 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L3')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 3:
_time_log()
return
# L4 - No tasks: add some stats for consistency and make the dirs small
sum_dir_L3 = sum_dir
sum_dir = os.path.join(output_base_dir, 'L4', 'summary')
utils.mkdir(sum_dir)
# Copy L3 files for consistency
for bn in [
'glacier_statistics', 'climate_statistics',
'fixed_geometry_mass_balance'
]:
ipath = os.path.join(sum_dir_L3, bn + '_{}.csv'.format(rgi_reg))
opath = os.path.join(sum_dir, bn + '_{}.csv'.format(rgi_reg))
shutil.copyfile(ipath, opath)
# Copy mini data to new dir
mini_base_dir = os.path.join(working_dir, 'mini_perglacier')
mini_gdirs = workflow.execute_entity_task(tasks.copy_to_basedir,
gdirs,
base_dir=mini_base_dir)
# L4 OK - compress all in output directory
log.workflow('L4 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L4')
workflow.execute_entity_task(utils.gdir_to_tar,
mini_gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 4:
_time_log()
return
# L5 - spinup run in mini gdirs
gdirs = mini_gdirs
# Get end date. The first gdir might have blown up, try some others
i = 0
while True:
if i >= len(gdirs):
raise RuntimeError('Found no valid glaciers!')
try:
y0 = gdirs[i].get_climate_info()['baseline_hydro_yr_0']
# One adds 1 because the run ends at the end of the year
ye = gdirs[i].get_climate_info()['baseline_hydro_yr_1'] + 1
break
except BaseException:
i += 1
# OK - run
workflow.execute_entity_task(tasks.run_from_climate_data,
gdirs,
min_ys=y0,
ye=ye,
output_filesuffix='_historical')
# Now compile the output
sum_dir = os.path.join(output_base_dir, 'L5', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir,
'historical_run_output_{}.nc'.format(rgi_reg))
utils.compile_run_output(gdirs, path=opath, input_filesuffix='_historical')
# Glacier statistics we recompute here for error analysis
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# Other stats for consistency
for bn in ['climate_statistics', 'fixed_geometry_mass_balance']:
ipath = os.path.join(sum_dir_L3, bn + '_{}.csv'.format(rgi_reg))
opath = os.path.join(sum_dir, bn + '_{}.csv'.format(rgi_reg))
shutil.copyfile(ipath, opath)
# Add the extended files
pf = os.path.join(sum_dir, 'historical_run_output_{}.nc'.format(rgi_reg))
mf = os.path.join(sum_dir,
'fixed_geometry_mass_balance_{}.csv'.format(rgi_reg))
# This is crucial - extending calving only with L3 data!!!
sf = os.path.join(sum_dir_L3, 'glacier_statistics_{}.csv'.format(rgi_reg))
opath = os.path.join(
sum_dir, 'historical_run_output_extended_{}.nc'.format(rgi_reg))
utils.extend_past_climate_run(past_run_file=pf,
fixed_geometry_mb_file=mf,
glacier_statistics_file=sf,
path=opath)
# L5 OK - compress all in output directory
log.workflow('L5 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L5')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
_time_log()
#!/usr/bin/env python
# coding: utf-8
# Extract glacier directories
import os
import geopandas as gpd
from oggm import cfg, utils, workflow
# define paths
prepro_dir = '/home/users/moberrauch/run_output/vas_prepro'
working_dir = '/home/users/moberrauch/wdirs/historical'
# OGGM initialization
cfg.initialize()
cfg.PATHS['working_dir'] = working_dir
# specify RGI version and regions
rgi_version = '62'
rgi_regions = [11, 13, 14, 15]
# get RGI IDs
for rgi_region in rgi_regions:
fpath = utils.get_rgi_region_file(rgi_region, rgi_version)
if rgi_region == rgi_regions[0]:
rgi_ids = gpd.read_file(fpath)
else:
rgi_ids = rgi_ids.append(gpd.read_file(fpath))
# extract working directories from *.tar files
workflow.init_glacier_directories(rgi_ids, from_tar=prepro_dir)
def run_cmip():
"""
"""
# Initialize OGGM and set up the default run parameters
vascaling.initialize(logging_level='DEBUG')
rgi_version = '62'
cfg.PARAMS['border'] = 80
# CLUSTER paths
wdir = os.environ.get('WORKDIR', '')
utils.mkdir(wdir)
cfg.PATHS['working_dir'] = wdir
outdir = os.environ.get('OUTDIR', '')
utils.mkdir(outdir)
# define the baseline climate CRU or HISTALP
cfg.PARAMS['baseline_climate'] = 'CRU'
# set the mb hyper parameters accordingly
cfg.PARAMS['prcp_scaling_factor'] = 3
cfg.PARAMS['temp_melt'] = 0
cfg.PARAMS['temp_all_solid'] = 4
cfg.PARAMS['prcp_default_gradient'] = 4e-4
cfg.PARAMS['run_mb_calibration'] = False
# set minimum ice thickness to include in glacier length computation
# this reduces weird spikes in length records
cfg.PARAMS['min_ice_thick_for_length'] = 0.1
# the bias is defined to be zero during the calibration process,
# which is why we don't use it here to reproduce the results
cfg.PARAMS['use_bias_for_run'] = True
# read RGI entry for the glaciers as DataFrame
# containing the outline area as shapefile
# RGI glaciers
rgi_reg = os.environ.get('RGI_REG', '')
if rgi_reg not in ['{:02d}'.format(r) for r in range(1, 20)]:
raise RuntimeError('Need an RGI Region')
rgi_ids = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# For greenland we omit connectivity level 2
if rgi_reg == '05':
rgi_ids = rgi_ids.loc[rgi_ids['Connect'] != 2]
# get and set path to intersect shapefile
intersects_db = utils.get_rgi_intersects_region_file(region=rgi_reg)
cfg.set_intersects_db(intersects_db)
# operational run, all glaciers should run
cfg.PARAMS['continue_on_error'] = True
# Module logger
log = logging.getLogger(__name__)
log.workflow('Starting run for RGI reg {}'.format(rgi_reg))
# Go - get the pre-processed glacier directories
base_url = 'https://cluster.klima.uni-bremen.de/' \
'~moberrauch/prepro_vas_paper/'
gdirs = workflow.init_glacier_directories(rgi_ids, from_prepro_level=3,
prepro_base_url=base_url,
prepro_rgi_version=rgi_version)
# read gcm list
gcms = pd.read_csv('/home/www/oggm/cmip6/all_gcm_list.csv', index_col=0)
# iterate over all specified GCMs
for gcm in sys.argv[1:]:
# iterate over all SSPs (Shared Socioeconomic Pathways)
df1 = gcms.loc[gcms.gcm == gcm]
for ssp in df1.ssp.unique():
df2 = df1.loc[df1.ssp == ssp]
assert len(df2) == 2
# get temperature projections
ft = df2.loc[df2['var'] == 'tas'].iloc[0]
# get precipitation projections
fp = df2.loc[df2['var'] == 'pr'].iloc[0].path
rid = ft.fname.replace('_r1i1p1f1_tas.nc', '')
ft = ft.path
log.workflow('Starting run for {}'.format(rid))
workflow.execute_entity_task(gcm_climate.process_cmip_data, gdirs,
# recognize the climate file for later
filesuffix='_' + rid,
# temperature projections
fpath_temp=ft,
# precip projections
fpath_precip=fp,
year_range=('1981', '2020'))
workflow.execute_entity_task(vascaling.run_from_climate_data,
gdirs,
# use gcm_data, not climate_historical
climate_filename='gcm_data',
# use a different scenario
climate_input_filesuffix='_' + rid,
# this is important! Start from 2019
init_model_filesuffix='_historical',
# recognize the run for later
output_filesuffix=rid,
return_value=False)
gcm_dir = os.path.join(outdir, 'RGI' + rgi_reg, gcm)
utils.mkdir(gcm_dir)
utils.compile_run_output(gdirs, input_filesuffix=rid,
path=os.path.join(gcm_dir, rid + '.nc'))
log.workflow('OGGM Done')
def run_cmip():
# Initialize OGGM and set up the default run parameters
vascaling.initialize(logging_level='WORKFLOW')
rgi_version = '62'
cfg.PARAMS['border'] = 80
# CLUSTER paths
wdir = os.environ.get('WORKDIR', '')
cfg.PATHS['working_dir'] = wdir
outdir = os.environ.get('OUTDIR', '')
# define the baseline climate CRU or HISTALP
cfg.PARAMS['baseline_climate'] = 'CRU'
# set the mb hyper parameters accordingly
cfg.PARAMS['prcp_scaling_factor'] = 3
cfg.PARAMS['temp_melt'] = 0
cfg.PARAMS['temp_all_solid'] = 4
cfg.PARAMS['run_mb_calibration'] = False
# set minimum ice thickness to include in glacier length computation
# this reduces weird spikes in length records
cfg.PARAMS['min_ice_thick_for_length'] = 0.1
# the bias is defined to be zero during the calibration process,
# which is why we don't use it here to reproduce the results
cfg.PARAMS['use_bias_for_run'] = True
# read RGI entry for the glaciers as DataFrame
# containing the outline area as shapefile
# RGI glaciers
rgi_reg = os.environ.get('OGGM_RGI_REG', '')
if rgi_reg not in ['{:02d}'.format(r) for r in range(1, 20)]:
raise RuntimeError('Need an RGI Region')
rgi_ids = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# get and set path to intersect shapefile
intersects_db = utils.get_rgi_intersects_region_file(region=rgi_reg)
cfg.set_intersects_db(intersects_db)
# operational run, all glaciers should run
cfg.PARAMS['continue_on_error'] = True
# Module logger
log = logging.getLogger(__name__)
log.workflow('Starting run for RGI reg {}'.format(rgi_reg))
# Go - get the pre-processed glacier directories
# base_url = 'https://cluster.klima.uni-bremen.de/~oggm/gdirs/oggm_v1.4/' \
# 'L3-L5_files/RGIV62_fleb_qc3_CRU_pcp2.5'
prepro_dir = '/home/users/moberrauch/run_output/vas_prepro/'
gdirs = workflow.init_glacier_directories(rgi_ids, from_tar=prepro_dir)
# # run vascaling climate tasks
# workflow.execute_entity_task(vascaling.local_t_star, gdirs)
# # adjust mass balance residual with geodetic observations
# vascaling.match_regional_geodetic_mb(gdirs=gdirs, rgi_reg=rgi_reg)
# # prepare historic "spinup"
# workflow.execute_entity_task(vascaling.run_from_climate_data, gdirs,
# ys=2003, ye=2020,
# output_filesuffix='_historical')
# read gcm list
gcms = pd.read_csv('/home/www/oggm/cmip6/all_gcm_list.csv', index_col=0)
# iterate over all specified gcms
for gcm in sys.argv[1:]:
# iterate over all SSPs (Shared Socioeconomic Pathways)
df1 = gcms.loc[gcms.gcm == gcm]
for ssp in df1.ssp.unique():
df2 = df1.loc[df1.ssp == ssp]
assert len(df2) == 2
# get temperature projections
ft = df2.loc[df2['var'] == 'tas'].iloc[0]
# get precipitation projections
fp = df2.loc[df2['var'] == 'pr'].iloc[0].path
rid = ft.fname.replace('_r1i1p1f1_tas.nc', '')
ft = ft.path
log.workflow('Starting run for {}'.format(rid))
workflow.execute_entity_task(
gcm_climate.process_cmip_data,
gdirs,
filesuffix='_' + rid,
# recognize the climate file for later
fpath_temp=ft,
# temperature projections
fpath_precip=fp, # precip projections
year_range=('1981', '2020'))
workflow.execute_entity_task(vascaling.run_from_climate_data,
gdirs,
climate_filename='gcm_data',
climate_input_filesuffix='_' + rid,
init_model_filesuffix='_historical',
output_filesuffix=rid,
return_value=False)
gcm_dir = os.path.join(outdir, 'RGI' + rgi_reg, gcm)
utils.mkdir(gcm_dir)
utils.compile_run_output(gdirs,
input_filesuffix=rid,
path=os.path.join(gcm_dir, rid + '.nc'))
log.workflow('OGGM Done')
def run_prepro_levels(rgi_version=None,
rgi_reg=None,
border=None,
output_folder='',
working_dir='',
is_test=False,
demo=False,
test_rgidf=None,
test_intersects_file=None,
test_topofile=None,
test_crudir=None):
"""Does the actual job.
Parameters
----------
rgi_version : str
the RGI version to use (defaults to cfg.PARAMS)
rgi_reg : str
the RGI region to process
border : int
the number of pixels at the maps border
output_folder : str
path to the output folder (where to put the preprocessed tar files)
working_dir : str
path to the OGGM working directory
is_test : bool
to test on a couple of glaciers only!
demo : bool
to run the prepro for the list of demo glaciers
test_rgidf : shapefile
for testing purposes only
test_intersects_file : shapefile
for testing purposes only
test_topofile : str
for testing purposes only
test_crudir : str
for testing purposes only
"""
# TODO: temporarily silence Fiona deprecation warnings
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
# Module logger
log = logging.getLogger(__name__)
# Time
start = time.time()
# Initialize OGGM and set up the run parameters
cfg.initialize(logging_level='WORKFLOW')
# Local paths
utils.mkdir(working_dir)
cfg.PATHS['working_dir'] = working_dir
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = True
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = border
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = True
# For statistics
climate_periods = [1920, 1960, 2000]
if rgi_version is None:
rgi_version = cfg.PARAMS['rgi_version']
rgi_dir_name = 'RGI{}'.format(rgi_version)
border_dir_name = 'b_{:03d}'.format(border)
base_dir = os.path.join(output_folder, rgi_dir_name, border_dir_name)
# Add a package version file
utils.mkdir(base_dir)
opath = os.path.join(base_dir, 'package_versions.txt')
with open(opath, 'w') as vfile:
vfile.write(utils.show_versions(logger=log))
if demo:
rgidf = utils.get_rgi_glacier_entities(cfg.DATA['demo_glaciers'].index)
elif test_rgidf is None:
# Get the RGI file
rgidf = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# We use intersects
rgif = utils.get_rgi_intersects_region_file(rgi_reg,
version=rgi_version)
cfg.set_intersects_db(rgif)
else:
rgidf = test_rgidf
cfg.set_intersects_db(test_intersects_file)
if is_test:
# Just for fun
rgidf = rgidf.sample(4)
# Sort for more efficient parallel computing
rgidf = rgidf.sort_values('Area', ascending=False)
log.workflow('Starting prepro run for RGI reg: {} '
'and border: {}'.format(rgi_reg, border))
log.workflow('Number of glaciers: {}'.format(len(rgidf)))
# Input
if test_topofile:
cfg.PATHS['dem_file'] = test_topofile
# L1 - initialize working directories
gdirs = workflow.init_glacier_regions(rgidf, reset=True, force=True)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L1', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L1 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
# L2 - Tasks
# Pre-download other files just in case
if test_crudir is None:
_ = utils.get_cru_file(var='tmp')
_ = utils.get_cru_file(var='pre')
else:
cfg.PATHS['cru_dir'] = test_crudir
workflow.execute_entity_task(tasks.process_cru_data, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L2', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L2 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L2')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
# L3 - Tasks
task_list = [
tasks.glacier_masks,
tasks.compute_centerlines,
tasks.initialize_flowlines,
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
tasks.catchment_area,
tasks.catchment_intersections,
tasks.catchment_width_geom,
tasks.catchment_width_correction,
tasks.local_t_star,
tasks.mu_star_calibration,
tasks.prepare_for_inversion,
tasks.mass_conservation_inversion,
tasks.filter_inversion_output,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L3', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
opath = os.path.join(sum_dir, 'climate_statistics_{}.csv'.format(rgi_reg))
utils.compile_climate_statistics(gdirs,
add_climate_period=climate_periods,
path=opath)
# L3 OK - compress all in output directory
l_base_dir = os.path.join(base_dir, 'L3')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=l_base_dir)
utils.base_dir_to_tar(l_base_dir)
# L4 - Tasks
workflow.execute_entity_task(tasks.init_present_time_glacier, gdirs)
# Glacier stats
sum_dir = os.path.join(base_dir, 'L4', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# Copy mini data to new dir
base_dir = os.path.join(base_dir, 'L4')
mini_gdirs = workflow.execute_entity_task(tasks.copy_to_basedir,
gdirs,
base_dir=base_dir)
# L4 OK - compress all in output directory
workflow.execute_entity_task(utils.gdir_to_tar, mini_gdirs, delete=True)
utils.base_dir_to_tar(base_dir)
# Log
m, s = divmod(time.time() - start, 60)
h, m = divmod(m, 60)
log.workflow('OGGM prepro_levels is done! Time needed: '
'{:02d}:{:02d}:{:02d}'.format(int(h), int(m), int(s)))
cfg.PARAMS['continue_on_error'] = True
# Init
workflow.init_mp_pool(True)
rgi_reg = os.environ.get('OGGM_RGI_REG', '')
if rgi_reg not in ['{:02d}'.format(r) for r in range(1, 20)]:
raise RuntimeError('Need an RGI Region')
# Module logger
log = logging.getLogger(__name__)
log.workflow('Starting run for RGI reg {}'.format(rgi_reg))
# RGI glaciers
rgi_ids = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# For greenland we omit connectivity level 2
if rgi_reg == '05':
rgi_ids = rgi_ids.loc[rgi_ids['Connect'] != 2]
# Go - get the pre-processed glacier directories
base_url = 'https://cluster.klima.uni-bremen.de/~fmaussion/gdirs/final_prepro_cmip6/era5_eb'
gdirs = workflow.init_glacier_directories(rgi_ids,
from_prepro_level=5,
prepro_base_url=base_url,
prepro_rgi_version=rgi_version)
gcms = pd.read_csv('/home/www/oggm/cmip6/all_gcm_list.csv', index_col=0)
n_gcms = len(sys.argv) - 1
def run_prepro_levels(rgi_version=None,
rgi_reg=None,
border=None,
output_folder='',
working_dir='',
dem_source='',
is_test=False,
test_ids=None,
demo=False,
test_rgidf=None,
test_intersects_file=None,
test_topofile=None,
disable_mp=False,
params_file=None,
elev_bands=False,
match_regional_geodetic_mb=False,
match_geodetic_mb_per_glacier=False,
evolution_model='fl_sia',
centerlines_only=False,
override_params=None,
add_consensus=False,
start_level=None,
start_base_url=None,
max_level=5,
ref_tstars_base_url='',
logging_level='WORKFLOW',
disable_dl_verify=False,
dynamic_spinup=False,
continue_on_error=True):
"""Generate the preprocessed OGGM glacier directories for this OGGM version
Parameters
----------
rgi_version : str
the RGI version to use (defaults to cfg.PARAMS)
rgi_reg : str
the RGI region to process
border : int
the number of pixels at the maps border
output_folder : str
path to the output folder (where to put the preprocessed tar files)
dem_source : str
which DEM source to use: default, SOURCE_NAME or ALL
working_dir : str
path to the OGGM working directory
ref_tstars_base_url : str
url where to find the pre-calibrated reference tstar list.
Required as of v1.4.
params_file : str
path to the OGGM parameter file (to override defaults)
is_test : bool
to test on a couple of glaciers only!
test_ids : list
if is_test: list of ids to process
demo : bool
to run the prepro for the list of demo glaciers
test_rgidf : shapefile
for testing purposes only
test_intersects_file : shapefile
for testing purposes only
test_topofile : str
for testing purposes only
test_crudir : str
for testing purposes only
disable_mp : bool
disable multiprocessing
elev_bands : bool
compute all flowlines based on the Huss&Hock 2015 method instead
of the OGGM default, which is a mix of elev_bands and centerlines.
centerlines_only : bool
compute all flowlines based on the OGGM centerline(s) method instead
of the OGGM default, which is a mix of elev_bands and centerlines.
match_regional_geodetic_mb : str
match the regional mass-balance estimates at the regional level
('hugonnet': Hugonnet et al., 2020 or 'zemp': Zemp et al., 2019).
match_geodetic_mb_per_glacier : str
match the mass-balance estimates at the glacier level
(currently only 'hugonnet': Hugonnet et al., 2020).
evolution_model : str
which geometry evolution model to use: `fl_sia` (default),
or `massredis` (mass redistribution curve).
add_consensus : bool
adds (reprojects) the consensus estimates thickness to the glacier
directories. With elev_bands=True, the data will also be binned.
start_level : int
the pre-processed level to start from (default is to start from
scratch). If set, you'll need to indicate start_base_url as well.
start_base_url : str
the pre-processed base-url to fetch the data from.
max_level : int
the maximum pre-processing level before stopping
logging_level : str
the logging level to use (DEBUG, INFO, WARNING, WORKFLOW)
override_params : dict
a dict of parameters to override.
disable_dl_verify : bool
disable the hash verification of OGGM downloads
dynamic_spinup: str
include a dynamic spinup matching 'area' OR 'volume' at the RGI-date
"""
# Input check
if max_level not in [1, 2, 3, 4, 5]:
raise InvalidParamsError('max_level should be one of [1, 2, 3, 4, 5]')
if start_level is not None:
if start_level not in [0, 1, 2]:
raise InvalidParamsError('start_level should be one of [0, 1, 2]')
if start_level > 0 and start_base_url is None:
raise InvalidParamsError('With start_level, please also indicate '
'start_base_url')
else:
start_level = 0
if match_regional_geodetic_mb and match_geodetic_mb_per_glacier:
raise InvalidParamsError(
'match_regional_geodetic_mb incompatible with '
'match_geodetic_mb_per_glacier!')
if match_geodetic_mb_per_glacier and match_geodetic_mb_per_glacier != 'hugonnet':
raise InvalidParamsError('Currently only `hugonnet` is available for '
'match_geodetic_mb_per_glacier.')
if evolution_model not in ['fl_sia', 'massredis']:
raise InvalidParamsError('evolution_model should be one of '
"['fl_sia', 'massredis'].")
if dynamic_spinup and dynamic_spinup not in ['area', 'volume']:
raise InvalidParamsError(f"Dynamic spinup option '{dynamic_spinup}' "
"not supported")
if dynamic_spinup and evolution_model == 'massredis':
raise InvalidParamsError("Dynamic spinup is not working/tested"
"with massredis!")
# Time
start = time.time()
def _time_log():
# Log util
m, s = divmod(time.time() - start, 60)
h, m = divmod(m, 60)
log.workflow('OGGM prepro_levels is done! Time needed: '
'{:02d}:{:02d}:{:02d}'.format(int(h), int(m), int(s)))
# Local paths
if override_params is None:
override_params = {}
utils.mkdir(working_dir)
override_params['working_dir'] = working_dir
# Initialize OGGM and set up the run parameters
cfg.initialize(file=params_file,
params=override_params,
logging_level=logging_level,
future=True)
if match_geodetic_mb_per_glacier and (cfg.PARAMS['hydro_month_nh'] != 1 or
cfg.PARAMS['hydro_month_sh'] != 1):
raise InvalidParamsError('We recommend to set hydro_month_nh and sh '
'to 1 for the geodetic MB calibration per '
'glacier.')
# Use multiprocessing?
cfg.PARAMS['use_multiprocessing'] = not disable_mp
# How many grid points around the glacier?
# Make it large if you expect your glaciers to grow large
cfg.PARAMS['border'] = border
# Set to True for operational runs
cfg.PARAMS['continue_on_error'] = continue_on_error
# Check for the integrity of the files OGGM downloads at run time
# For large files (e.g. using a 1 tif DEM like ALASKA) calculating the hash
# takes a long time, so deactivating this can make sense
cfg.PARAMS['dl_verify'] = not disable_dl_verify
# Other things that make sense
cfg.PARAMS['store_model_geometry'] = True
# Log the parameters
msg = '# OGGM Run parameters:'
for k, v in cfg.PARAMS.items():
if type(v) in [pd.DataFrame, dict]:
continue
msg += '\n {}: {}'.format(k, v)
log.workflow(msg)
if rgi_version is None:
rgi_version = cfg.PARAMS['rgi_version']
output_base_dir = os.path.join(output_folder, 'RGI{}'.format(rgi_version),
'b_{:03d}'.format(border))
# Add a package version file
utils.mkdir(output_base_dir)
opath = os.path.join(output_base_dir, 'package_versions.txt')
with open(opath, 'w') as vfile:
vfile.write(utils.show_versions(logger=log))
if demo:
rgidf = utils.get_rgi_glacier_entities(cfg.DATA['demo_glaciers'].index)
elif test_rgidf is None:
# Get the RGI file
rgidf = gpd.read_file(
utils.get_rgi_region_file(rgi_reg, version=rgi_version))
# We use intersects
rgif = utils.get_rgi_intersects_region_file(rgi_reg,
version=rgi_version)
cfg.set_intersects_db(rgif)
# Some RGI input quality checks - this is based on visual checks
# of large glaciers in the RGI
ids_to_ice_cap = [
'RGI60-05.10315', # huge Greenland ice cap
'RGI60-03.01466', # strange thing next to Devon
'RGI60-09.00918', # Academy of sciences Ice cap
'RGI60-09.00969',
'RGI60-09.00958',
'RGI60-09.00957',
]
rgidf.loc[rgidf.RGIId.isin(ids_to_ice_cap), 'Form'] = '1'
# In AA almost all large ice bodies are actually ice caps
if rgi_reg == '19':
rgidf.loc[rgidf.Area > 100, 'Form'] = '1'
# For greenland we omit connectivity level 2
if rgi_reg == '05':
rgidf = rgidf.loc[rgidf['Connect'] != 2]
else:
rgidf = test_rgidf
cfg.set_intersects_db(test_intersects_file)
if is_test:
if test_ids is not None:
rgidf = rgidf.loc[rgidf.RGIId.isin(test_ids)]
else:
rgidf = rgidf.sample(4)
if max_level > 2:
# Also use ref tstars
utils.apply_test_ref_tstars()
if max_level > 2 and ref_tstars_base_url:
workflow.download_ref_tstars(base_url=ref_tstars_base_url)
log.workflow('Starting prepro run for RGI reg: {} '
'and border: {}'.format(rgi_reg, border))
log.workflow('Number of glaciers: {}'.format(len(rgidf)))
# L0 - go
if start_level == 0:
gdirs = workflow.init_glacier_directories(rgidf,
reset=True,
force=True)
# Glacier stats
sum_dir = os.path.join(output_base_dir, 'L0', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir,
'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L0 OK - compress all in output directory
log.workflow('L0 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L0')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 0:
_time_log()
return
else:
gdirs = workflow.init_glacier_directories(
rgidf,
reset=True,
force=True,
from_prepro_level=start_level,
prepro_border=border,
prepro_rgi_version=rgi_version,
prepro_base_url=start_base_url)
# L1 - Add dem files
if start_level == 0:
if test_topofile:
cfg.PATHS['dem_file'] = test_topofile
# Which DEM source?
if dem_source.upper() == 'ALL':
# This is the complex one, just do the job and leave
log.workflow('Running prepro on ALL sources')
for i, s in enumerate(utils.DEM_SOURCES):
rs = i == 0
log.workflow('Running prepro on sources: {}'.format(s))
gdirs = workflow.init_glacier_directories(rgidf,
reset=rs,
force=rs)
workflow.execute_entity_task(tasks.define_glacier_region,
gdirs,
source=s)
workflow.execute_entity_task(_rename_dem_folder,
gdirs,
source=s)
# make a GeoTiff mask of the glacier, choose any source
workflow.execute_entity_task(gis.rasterio_glacier_mask,
gdirs,
source='ALL')
# Compress all in output directory
level_base_dir = os.path.join(output_base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
_time_log()
return
# Force a given source
source = dem_source.upper() if dem_source else None
# L1 - go
workflow.execute_entity_task(tasks.define_glacier_region,
gdirs,
source=source)
# Glacier stats
sum_dir = os.path.join(output_base_dir, 'L1', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir,
'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# L1 OK - compress all in output directory
log.workflow('L1 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L1')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 1:
_time_log()
return
# L2 - Tasks
if start_level <= 1:
# Check which glaciers will be processed as what
if elev_bands:
gdirs_band = gdirs
gdirs_cent = []
elif centerlines_only:
gdirs_band = []
gdirs_cent = gdirs
else:
# Default is to centerlines_only, but it used to be a mix
# (e.g. bands for ice caps, etc)
# I still keep this logic here in case we want to mix again
gdirs_band = []
gdirs_cent = gdirs
log.workflow('Start flowline processing with: '
'N centerline type: {}, '
'N elev bands type: {}.'
''.format(len(gdirs_cent), len(gdirs_band)))
# HH2015 method
workflow.execute_entity_task(tasks.simple_glacier_masks, gdirs_band)
# Centerlines OGGM
workflow.execute_entity_task(tasks.glacier_masks, gdirs_cent)
if add_consensus:
from oggm.shop.bedtopo import add_consensus_thickness
workflow.execute_entity_task(add_consensus_thickness, gdirs_band)
workflow.execute_entity_task(add_consensus_thickness, gdirs_cent)
# Elev bands with var data
vn = 'consensus_ice_thickness'
workflow.execute_entity_task(tasks.elevation_band_flowline,
gdirs_band,
bin_variables=vn)
workflow.execute_entity_task(
tasks.fixed_dx_elevation_band_flowline,
gdirs_band,
bin_variables=vn)
else:
# HH2015 method without it
task_list = [
tasks.elevation_band_flowline,
tasks.fixed_dx_elevation_band_flowline,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs_band)
# Centerlines OGGM
task_list = [
tasks.compute_centerlines,
tasks.initialize_flowlines,
tasks.catchment_area,
tasks.catchment_intersections,
tasks.catchment_width_geom,
tasks.catchment_width_correction,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs_cent)
# Same for all glaciers
if border >= 20:
task_list = [
tasks.compute_downstream_line,
tasks.compute_downstream_bedshape,
]
for task in task_list:
workflow.execute_entity_task(task, gdirs)
else:
log.workflow('L2: for map border values < 20, wont compute '
'downstream lines.')
# Glacier stats
sum_dir = os.path.join(output_base_dir, 'L2', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir,
'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# And for level 2: shapes
if len(gdirs_cent) > 0:
opath = os.path.join(sum_dir, 'centerlines_{}.shp'.format(rgi_reg))
utils.write_centerlines_to_shape(gdirs_cent,
to_tar=True,
path=opath)
# L2 OK - compress all in output directory
log.workflow('L2 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L2')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 2:
_time_log()
return
# L3 - Tasks
sum_dir = os.path.join(output_base_dir, 'L3', 'summary')
utils.mkdir(sum_dir)
# Climate
workflow.execute_entity_task(tasks.process_climate_data, gdirs)
if cfg.PARAMS['climate_qc_months'] > 0:
workflow.execute_entity_task(tasks.historical_climate_qc, gdirs)
if match_geodetic_mb_per_glacier:
utils.get_geodetic_mb_dataframe() # Small optim to avoid concurrency
workflow.execute_entity_task(
tasks.mu_star_calibration_from_geodetic_mb, gdirs)
workflow.execute_entity_task(tasks.apparent_mb_from_any_mb, gdirs)
else:
workflow.execute_entity_task(tasks.local_t_star, gdirs)
workflow.execute_entity_task(tasks.mu_star_calibration, gdirs)
# Inversion: we match the consensus
filter = border >= 20
workflow.calibrate_inversion_from_consensus(gdirs,
apply_fs_on_mismatch=True,
error_on_mismatch=False,
filter_inversion_output=filter)
# Do we want to match geodetic estimates?
# This affects only the bias so we can actually do this *after*
# the inversion, but we really want to take calving into account here
if match_regional_geodetic_mb:
opath = os.path.join(
sum_dir, 'fixed_geometry_mass_balance_'
'before_match_{}.csv'.format(rgi_reg))
utils.compile_fixed_geometry_mass_balance(gdirs, path=opath)
workflow.match_regional_geodetic_mb(gdirs,
rgi_reg=rgi_reg,
dataset=match_regional_geodetic_mb)
# We get ready for modelling
if border >= 20:
workflow.execute_entity_task(tasks.init_present_time_glacier, gdirs)
else:
log.workflow(
'L3: for map border values < 20, wont initialize glaciers '
'for the run.')
# Glacier stats
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
opath = os.path.join(sum_dir, 'climate_statistics_{}.csv'.format(rgi_reg))
utils.compile_climate_statistics(gdirs, path=opath)
opath = os.path.join(sum_dir,
'fixed_geometry_mass_balance_{}.csv'.format(rgi_reg))
utils.compile_fixed_geometry_mass_balance(gdirs, path=opath)
# L3 OK - compress all in output directory
log.workflow('L3 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L3')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 3:
_time_log()
return
if border < 20:
log.workflow('L3: for map border values < 20, wont compute L4 and L5.')
_time_log()
return
# L4 - No tasks: add some stats for consistency and make the dirs small
sum_dir_L3 = sum_dir
sum_dir = os.path.join(output_base_dir, 'L4', 'summary')
utils.mkdir(sum_dir)
# Copy L3 files for consistency
for bn in [
'glacier_statistics', 'climate_statistics',
'fixed_geometry_mass_balance'
]:
ipath = os.path.join(sum_dir_L3, bn + '_{}.csv'.format(rgi_reg))
opath = os.path.join(sum_dir, bn + '_{}.csv'.format(rgi_reg))
shutil.copyfile(ipath, opath)
# Copy mini data to new dir
mini_base_dir = os.path.join(working_dir, 'mini_perglacier',
'RGI{}'.format(rgi_version),
'b_{:03d}'.format(border))
mini_gdirs = workflow.execute_entity_task(tasks.copy_to_basedir,
gdirs,
base_dir=mini_base_dir)
# L4 OK - compress all in output directory
log.workflow('L4 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L4')
workflow.execute_entity_task(utils.gdir_to_tar,
mini_gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
if max_level == 4:
_time_log()
return
# L5 - spinup run in mini gdirs
gdirs = mini_gdirs
# Get end date. The first gdir might have blown up, try some others
i = 0
while True:
if i >= len(gdirs):
raise RuntimeError('Found no valid glaciers!')
try:
y0 = gdirs[i].get_climate_info()['baseline_hydro_yr_0']
# One adds 1 because the run ends at the end of the year
ye = gdirs[i].get_climate_info()['baseline_hydro_yr_1'] + 1
break
except BaseException:
i += 1
# Which model?
if evolution_model == 'massredis':
from oggm.core.flowline import MassRedistributionCurveModel
evolution_model = MassRedistributionCurveModel
else:
from oggm.core.flowline import FluxBasedModel
evolution_model = FluxBasedModel
# OK - run
if dynamic_spinup:
workflow.execute_entity_task(
tasks.run_dynamic_spinup,
gdirs,
evolution_model=evolution_model,
minimise_for=dynamic_spinup,
precision_percent=1,
output_filesuffix='_dynamic_spinup',
)
workflow.execute_entity_task(tasks.run_from_climate_data,
gdirs,
min_ys=y0,
ye=ye,
evolution_model=evolution_model,
init_model_filesuffix='_dynamic_spinup',
output_filesuffix='_hist_spin')
workflow.execute_entity_task(tasks.merge_consecutive_run_outputs,
gdirs,
input_filesuffix_1='_dynamic_spinup',
input_filesuffix_2='_hist_spin',
output_filesuffix='_historical_spinup',
delete_input=True)
workflow.execute_entity_task(tasks.run_from_climate_data,
gdirs,
min_ys=y0,
ye=ye,
evolution_model=evolution_model,
output_filesuffix='_historical')
# Now compile the output
sum_dir = os.path.join(output_base_dir, 'L5', 'summary')
utils.mkdir(sum_dir)
opath = os.path.join(sum_dir, f'historical_run_output_{rgi_reg}.nc')
utils.compile_run_output(gdirs, path=opath, input_filesuffix='_historical')
if dynamic_spinup:
opath = os.path.join(sum_dir,
f'historical_spinup_run_output_{rgi_reg}.nc')
utils.compile_run_output(gdirs,
path=opath,
input_filesuffix='_historical_spinup')
# Glacier statistics we recompute here for error analysis
opath = os.path.join(sum_dir, 'glacier_statistics_{}.csv'.format(rgi_reg))
utils.compile_glacier_statistics(gdirs, path=opath)
# Other stats for consistency
for bn in ['climate_statistics', 'fixed_geometry_mass_balance']:
ipath = os.path.join(sum_dir_L3, bn + '_{}.csv'.format(rgi_reg))
opath = os.path.join(sum_dir, bn + '_{}.csv'.format(rgi_reg))
shutil.copyfile(ipath, opath)
# Add the extended files
pf = os.path.join(sum_dir, 'historical_run_output_{}.nc'.format(rgi_reg))
mf = os.path.join(sum_dir,
'fixed_geometry_mass_balance_{}.csv'.format(rgi_reg))
# This is crucial - extending calving only possible with L3 data!!!
sf = os.path.join(sum_dir_L3, 'glacier_statistics_{}.csv'.format(rgi_reg))
opath = os.path.join(
sum_dir, 'historical_run_output_extended_{}.nc'.format(rgi_reg))
utils.extend_past_climate_run(past_run_file=pf,
fixed_geometry_mb_file=mf,
glacier_statistics_file=sf,
path=opath)
# L5 OK - compress all in output directory
log.workflow('L5 done. Writing to tar...')
level_base_dir = os.path.join(output_base_dir, 'L5')
workflow.execute_entity_task(utils.gdir_to_tar,
gdirs,
delete=False,
base_dir=level_base_dir)
utils.base_dir_to_tar(level_base_dir)
_time_log()
