def main(cimis_ws=os.getcwd(),
gridmet_ws=None,
ancillary_ws=os.getcwd(),
etr_flag=False,
eto_flag=False,
start_date=None,
end_date=None,
stats_flag=True,
overwrite_flag=False):
"""Fill missing CIMIS days with projected data from GRIDMET
Currently missing (CGM 2014-08-15)
2010-11-16 -> 2010-11-23
Args:
cimis_ws (str): root folder path of CIMIS data
gridmet_ws (str): root folder path of GRIDMET data
ancillary_ws (str): folder of ancillary rasters
etr_flag (bool): if True, compute alfalfa reference ET (ETr)
eto_flag (bool): if True, compute grass reference ET (ETo)
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nFilling CIMIS with GRIDMET')
cimis_re = re.compile(
'(?P<VAR>etr)_(?P<YYYY>\d{4})_daily_(?P<GRID>\w+).img$')
# gridmet_re = re.compile(
# '(?P<VAR>ppt)_(?P<YYY>\d{4})_daily_(?P<GRID>\w+).img$')
gridmet_fmt = 'etr_{}_daily_gridmet.img'
# Compute ETr and/or ETo
if not etr_flag and not eto_flag:
logging.info(' ETo/ETr flag(s) not set, defaulting to ETr')
etr_flag = True
logging.debug(' CIMIS: {}'.format(cimis_ws))
logging.debug(' GRIDMET: {}'.format(gridmet_ws))
# If a date is not set, process 2017
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2017, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2017, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Get GRIDMET spatial reference and cellsize from elevation raster
# gridmet_elev_raster = os.path.join(ancillary_ws, 'gridmet_elev.img')
# Get CIMIS spatial reference and cellsize from mask raster
cimis_mask_raster = os.path.join(ancillary_ws, 'cimis_mask.img')
# Resample type
# 0 = GRA_NearestNeighbour, Nearest neighbour (select on one input pixel)
# 1 = GRA_Bilinear,Bilinear (2x2 kernel)
# 2 = GRA_Cubic, Cubic Convolution Approximation (4x4 kernel)
# 3 = GRA_CubicSpline, Cubic B-Spline Approximation (4x4 kernel)
# 4 = GRA_Lanczos, Lanczos windowed sinc interpolation (6x6 kernel)
# 5 = GRA_Average, Average (computes the average of all non-NODATA contributing pixels)
# 6 = GRA_Mode, Mode (selects the value which appears most often of all the sampled points)
resample_type = gdal.GRA_Bilinear
# ETo/ETr workspaces
cimis_eto_ws = os.path.join(cimis_ws, 'eto')
cimis_etr_ws = os.path.join(cimis_ws, 'etr')
gridmet_eto_ws = os.path.join(gridmet_ws, 'eto')
gridmet_etr_ws = os.path.join(gridmet_ws, 'etr')
# This allows GDAL to throw Python Exceptions
# gdal.UseExceptions()
# mem_driver = gdal.GetDriverByName('MEM')
# Get CIMIS grid properties from mask
logging.info('\nCIMIS Properties')
cimis_mask_ds = gdal.Open(cimis_mask_raster)
cimis_osr = gdc.raster_ds_osr(cimis_mask_ds)
cimis_proj = gdc.osr_proj(cimis_osr)
cimis_cs = gdc.raster_ds_cellsize(cimis_mask_ds, x_only=True)
cimis_extent = gdc.raster_ds_extent(cimis_mask_ds)
cimis_geo = cimis_extent.geo(cimis_cs)
cimis_mask_ds = None
logging.debug(' Projection: {}'.format(cimis_proj))
logging.debug(' Cellsize: {}'.format(cimis_cs))
logging.debug(' Geo: {}'.format(cimis_geo))
logging.debug(' Extent: {}'.format(cimis_extent))
# Read the CIMIS mask array if present
cimis_mask, cimis_mask_nodata = gdc.raster_to_array(cimis_mask_raster)
cimis_mask = cimis_mask != cimis_mask_nodata
# # Get extent/geo from elevation raster
# logging.info('\nGRIDMET Properties')
# gridmet_ds = gdal.Open(gridmet_elev_raster)
# gridmet_osr = gdc.raster_ds_osr(gridmet_ds)
# gridmet_proj = gdc.osr_proj(gridmet_osr)
# gridmet_cs = gdc.raster_ds_cellsize(gridmet_ds, x_only=True)
# gridmet_full_extent = gdc.raster_ds_extent(gridmet_ds)
# gridmet_full_geo = gridmet_full_extent.geo(gridmet_cs)
# gridmet_x, gridmet_y = gridmet_full_extent.origin()
# gridmet_ds = None
# logging.debug(' Projection: {}'.format(gridmet_proj))
# logging.debug(' Cellsize: {}'.format(gridmet_cs))
# logging.debug(' Geo: {}'.format(gridmet_full_geo))
# logging.debug(' Extent: {}'.format(gridmet_full_extent))
# # Project CIMIS extent to the GRIDMET spatial reference
# logging.info('\nGet CIMIS extent in GRIDMET spat. ref.')
# gridmet_sub_extent = gdc.project_extent(
# cimis_extent, cimis_osr, gridmet_osr, cimis_cs)
# gridmet_sub_extent.buffer_extent(4 * gridmet_cs)
# gridmet_sub_extent.adjust_to_snap(
# 'EXPAND', gridmet_x, gridmet_y, gridmet_cs)
# gridmet_sub_geo = gridmet_sub_extent.geo(gridmet_cs)
# logging.debug(' Geo: {}'.format(gridmet_sub_geo))
# logging.debug(' Extent: {}'.format(gridmet_sub_extent))
# Process Missing ETo
if eto_flag:
logging.info('\nETo')
for cimis_name in sorted(os.listdir(cimis_eto_ws)):
logging.debug("\n{}".format(cimis_name))
cimis_match = cimis_re.match(cimis_name)
if not cimis_match:
logging.debug(' Regular expression didn\'t match, skipping')
continue
year = int(cimis_match.group('YYYY'))
logging.info(" {}".format(str(year)))
if start_dt is not None and year < start_dt.year:
logging.debug(' Before start date, skipping')
continue
elif end_dt is not None and year > end_dt.year:
logging.debug(' After end date, skipping')
continue
cimis_path = os.path.join(cimis_eto_ws, cimis_name)
gridmet_path = os.path.join(gridmet_eto_ws,
gridmet_fmt.format(str(year)))
if not os.path.isfile(gridmet_path):
logging.debug(' GRIDMET raster does not exist, skipping')
continue
if not os.path.isfile(cimis_path):
logging.error(' CIMIS raster does not exist, skipping')
continue
# Check all valid dates in the year
year_dates = date_range(dt.datetime(year, 1, 1),
dt.datetime(year + 1, 1, 1))
for date_dt in year_dates:
if start_dt is not None and date_dt < start_dt:
continue
elif end_dt is not None and date_dt > end_dt:
continue
doy = int(date_dt.strftime('%j'))
# Look for arrays that don't have data
eto_array = gdc.raster_to_array(cimis_path,
band=doy,
return_nodata=False)
if np.any(np.isfinite(eto_array)):
logging.debug(' {} - no missing data, skipping'.format(
date_dt.strftime('%Y-%m-%d')))
continue
else:
logging.info(' {}'.format(date_dt.strftime('%Y-%m-%d')))
# # This is much faster but doesn't apply the CIMIS mask
# # Create an in memory dataset of the full ETo array
# eto_full_rows, eto_full_cols = eto_full_array[:,:,doy_i].shape
# eto_full_type, eto_full_nodata = numpy_to_gdal_type(np.float32)
# eto_full_ds = mem_driver.Create(
# '', eto_full_cols, eto_full_rows, 1, eto_full_type)
# eto_full_ds.SetProjection(gridmet_proj)
# eto_full_ds.SetGeoTransform(gridmet_full_geo)
# eto_full_band = eto_full_ds.GetRasterBand(1)
# # eto_full_band.Fill(eto_full_nodata)
# eto_full_band.SetNoDataValue(eto_full_nodata)
# eto_full_band.WriteArray(eto_full_array[:,:,doy_i], 0, 0)
#
# # Extract the subset
# eto_sub_array, eto_sub_nodata = gdc.raster_ds_to_array(
# eto_full_ds, 1, gridmet_sub_extent)
# eto_sub_rows, eto_sub_cols = eto_sub_array.shape
# eto_full_ds = None
#
# # Create projected raster
# eto_sub_ds = mem_driver.Create(
# '', eto_sub_cols, eto_sub_rows, 1, eto_full_type)
# eto_sub_ds.SetProjection(gridmet_proj)
# eto_sub_ds.SetGeoTransform(gridmet_sub_geo)
# eto_sub_band = eto_sub_ds.GetRasterBand(1)
# eto_sub_band.Fill(eto_sub_nodata)
# eto_sub_band.SetNoDataValue(eto_sub_nodata)
# eto_sub_band.WriteArray(eto_sub_array, 0, 0)
# eto_sub_ds.FlushCache()
#
# # Project input DEM to CIMIS spat. ref.
# gdc.project_raster_ds(
# eto_sub_ds, gridmet_path, resample_type,
# env.snap_proj, env.cellsize, cimis_extent)
# eto_sub_ds = None
# Extract the subset
gridmet_ds = gdal.Open(gridmet_path)
gridmet_extent = gdc.raster_ds_extent(gridmet_ds)
gridmet_cs = gdc.raster_ds_cellsize(gridmet_ds, x_only=True)
gridmet_osr = gdc.raster_ds_osr(gridmet_ds)
eto_full_array = gdc.raster_ds_to_array(gridmet_ds,
band=doy,
return_nodata=False)
gridmet_ds = None
# Get the projected subset of the full ETo array
# This is slower than projecting the subset above
eto_sub_array = gdc.project_array(eto_full_array,
resample_type, gridmet_osr,
gridmet_cs, gridmet_extent,
cimis_osr, cimis_cs,
cimis_extent)
# Save the projected array
gdc.array_to_comp_raster(eto_sub_array,
cimis_path,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# eto_sub_array, output_path, output_geo=cimis_geo,
# output_proj=cimis_proj, stats_flag=False)
# gdc.array_to_raster(
# eto_sub_array, output_path,
# output_geo=cimis_geo, output_proj=cimis_proj,
# mask_array=cimis_mask, stats_flag=False)
del eto_sub_array, eto_full_array
if stats_flag:
gdc.raster_statistics(cimis_path)
# Process Missing ETr
if etr_flag:
logging.info('\nETr')
for cimis_name in sorted(os.listdir(cimis_etr_ws)):
cimis_match = cimis_re.match(cimis_name)
if not cimis_match:
continue
year = int(cimis_match.group('YYYY'))
if start_dt is not None and year < start_dt.year:
continue
elif end_dt is not None and year > end_dt.year:
continue
logging.info("{}".format(str(year)))
cimis_path = os.path.join(cimis_etr_ws, cimis_name)
gridmet_path = os.path.join(gridmet_etr_ws,
gridmet_fmt.format(str(year)))
if not os.path.isfile(gridmet_path):
continue
if not os.path.isfile(cimis_path):
logging.error(' CIMIS raster does not exist')
continue
# Check all valid dates in the year
year_dates = date_range(dt.datetime(year, 1, 1),
dt.datetime(year + 1, 1, 1))
for date_dt in year_dates:
if start_dt is not None and date_dt < start_dt:
continue
elif end_dt is not None and date_dt > end_dt:
continue
doy = int(date_dt.strftime('%j'))
# Look for arrays that don't have data
etr_array = gdc.raster_to_array(cimis_path,
band=doy,
return_nodata=False)
if np.any(np.isfinite(etr_array)):
logging.debug(' {} - skipping'.format(
date_dt.strftime('%Y-%m-%d')))
continue
else:
logging.info(' {}'.format(date_dt.strftime('%Y-%m-%d')))
# Extract the subset
gridmet_ds = gdal.Open(gridmet_path)
gridmet_extent = gdc.raster_ds_extent(gridmet_ds)
gridmet_cs = gdc.raster_ds_cellsize(gridmet_ds, x_only=True)
gridmet_osr = gdc.raster_ds_osr(gridmet_ds)
etr_full_array = gdc.raster_ds_to_array(gridmet_ds,
band=doy,
return_nodata=False)
gridmet_ds = None
# Get the projected subset of the full ETr array
# This is slower than projecting the subset
etr_sub_array = gdc.project_array(etr_full_array,
resample_type, gridmet_osr,
gridmet_cs, gridmet_extent,
cimis_osr, cimis_cs,
cimis_extent)
# # Save the projected array
gdc.array_to_comp_raster(etr_sub_array,
cimis_path,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# etr_sub_array, output_path,
# output_geo=cimis_geo, output_proj=cimis_proj,
# mask_array=cimis_mask, stats_flag=False)
del etr_sub_array, etr_full_array
if stats_flag:
gdc.raster_statistics(cimis_path)
logging.debug('\nScript Complete')
def main(grb_ws=os.getcwd(), ancillary_ws=os.getcwd(), output_ws=os.getcwd(),
variables=['pr'], landsat_ws=None,
start_date=None, end_date=None, times_str='',
extent_path=None, output_extent=None,
stats_flag=True, overwrite_flag=False):
"""Extract NLDAS target variable(s)
Args:
grb_ws (str): folder of NLDAS GRB files
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
variable (list): NLDAS variables to download
('ppt', 'srad', 'sph', 'tair', tmmn', 'tmmx', 'vs')
landsat_ws (str): folder of Landsat scenes or tar.gz files
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
times (str): comma separated values and/or ranges of UTC hours
(i.e. "1, 2, 5-8")
Parsed with python_common.parse_int_set()
extent_path (str): file path defining the output extent
output_extent (list): decimal degrees values defining output extent
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nExtract NLDAS target variable(s)')
# input_fmt = 'NLDAS_FORA0125_H.A{:04d}{:02d}{:02d}.{}.002.grb'
input_re = re.compile(
'NLDAS_FORA0125_H.A(?P<YEAR>\d{4})(?P<MONTH>\d{2})' +
'(?P<DAY>\d{2}).(?P<TIME>\d{4}).002.grb$')
output_fmt = '{}_{:04d}{:02d}{:02d}_hourly_nldas.img'
# output_fmt = '{}_{:04d}{:02d}{:02d}_{:04d}_nldas.img'
# If a date is not set, process 2017
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2017, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2017, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Only process a specific hours
if not times_str:
time_list = range(0, 24, 1)
else:
time_list = list(parse_int_set(times_str))
time_list = ['{:02d}00'.format(t) for t in time_list]
# Assume NLDAS is NAD83
# input_epsg = 'EPSG:4269'
# NLDAS rasters to extract
data_full_list = ['pr', 'srad', 'sph', 'tair', 'tmmn', 'tmmx', 'vs']
if not variables:
logging.error('\nERROR: variables parameter is empty\n')
sys.exit()
elif type(variables) is not list:
# DEADBEEF - I could try converting comma separated strings to lists?
logging.warning('\nERROR: variables parameter must be a list\n')
sys.exit()
elif not set(variables).issubset(set(data_full_list)):
logging.error('\nERROR: variables parameter is invalid\n {}'.format(
variables))
sys.exit()
# Ancillary raster paths
mask_path = os.path.join(ancillary_ws, 'nldas_mask.img')
# Build a date list from landsat_ws scene folders or tar.gz files
date_list = []
if landsat_ws is not None and os.path.isdir(landsat_ws):
logging.info('\nReading dates from Landsat IDs')
logging.info(' {}'.format(landsat_ws))
landsat_re = re.compile(
'^(?:LT04|LT05|LE07|LC08)_(?:\d{3})(?:\d{3})_' +
'(?P<year>\d{4})(?P<month>\d{2})(?P<day>\d{2})')
for root, dirs, files in os.walk(landsat_ws, topdown=True):
# If root matches, don't explore subfolders
try:
landsat_match = landsat_re.match(os.path.basename(root))
date_list.append(dt.datetime.strptime(
'_'.join(landsat_match.groups()), '%Y_%m_%d').date().isoformat())
dirs[:] = []
except:
pass
for file in files:
try:
landsat_match = landsat_re.match(file)
date_list.append(dt.datetime.strptime(
'_'.join(landsat_match.groups()), '%Y_%m_%d').date().isoformat())
except:
pass
date_list = sorted(list(set(date_list)))
# elif landsat_ws is not None and os.path.isfile(landsat_ws):
# with open(landsat_ws) as landsat_f:
# This allows GDAL to throw Python Exceptions
# gdal.UseExceptions()
# mem_driver = gdal.GetDriverByName('MEM')
# Get the NLDAS spatial reference from the mask raster
nldas_ds = gdal.Open(mask_path)
nldas_osr = gdc.raster_ds_osr(nldas_ds)
nldas_proj = gdc.osr_proj(nldas_osr)
nldas_cs = gdc.raster_ds_cellsize(nldas_ds, x_only=True)
nldas_extent = gdc.raster_ds_extent(nldas_ds)
nldas_geo = nldas_extent.geo(nldas_cs)
nldas_x, nldas_y = nldas_extent.origin()
nldas_ds = None
logging.debug(' Projection: {}'.format(nldas_proj))
logging.debug(' Cellsize: {}'.format(nldas_cs))
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(nldas_extent))
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
nldas_extent = gdc.Extent(output_extent)
nldas_extent.adjust_to_snap('EXPAND', nldas_x, nldas_y, nldas_cs)
nldas_geo = nldas_extent.geo(nldas_cs)
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(output_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
if extent_path.lower().endswith('.shp'):
nldas_extent = gdc.feature_path_extent(extent_path)
extent_osr = gdc.feature_path_osr(extent_path)
extent_cs = None
else:
nldas_extent = gdc.raster_path_extent(extent_path)
extent_osr = gdc.raster_path_osr(extent_path)
extent_cs = gdc.raster_path_cellsize(extent_path, x_only=True)
nldas_extent = gdc.project_extent(
nldas_extent, extent_osr, nldas_osr, extent_cs)
nldas_extent.adjust_to_snap('EXPAND', nldas_x, nldas_y, nldas_cs)
nldas_geo = nldas_extent.geo(nldas_cs)
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(nldas_extent))
logging.debug('')
# Read the NLDAS mask array if present
if mask_path and os.path.isfile(mask_path):
mask_array, mask_nodata = gdc.raster_to_array(
mask_path, mask_extent=nldas_extent, fill_value=0,
return_nodata=True)
mask_array = mask_array != mask_nodata
else:
mask_array = None
# NLDAS band name dictionary
nldas_band_dict = dict()
nldas_band_dict['pr'] = 'Total precipitation [kg/m^2]'
nldas_band_dict['srad'] = 'Downward shortwave radiation flux [W/m^2]'
nldas_band_dict['sph'] = 'Specific humidity [kg/kg]'
nldas_band_dict['tair'] = 'Temperature [C]'
nldas_band_dict['tmmn'] = 'Temperature [C]'
nldas_band_dict['tmmx'] = 'Temperature [C]'
nldas_band_dict['vs'] = [
'u-component of wind [m/s]', 'v-component of wind [m/s]']
# NLDAS band name dictionary
# nldas_band_dict = dict()
# nldas_band_dict['pr'] = 'precipitation_amount'
# nldas_band_dict['srad'] = 'surface_downwelling_shortwave_flux_in_air'
# nldas_band_dict['sph'] = 'specific_humidity'
# nldas_band_dict['tmmn'] = 'air_temperature'
# nldas_band_dict['tmmx'] = 'air_temperature'
# nldas_band_dict['vs'] = 'wind_speed'
# NLDAS band name dictionary (EarthEngine keys, GRID_ELEMENT values)
# nldas_band_dict = dict()
# nldas_band_dict['total_precipitation'] = 'Total precipitation [kg/m^2]'
# nldas_band_dict['shortwave_radiation'] = 'Downward shortwave radiation flux [W/m^2]'
# nldas_band_dict['specific_humidity'] = 'Specific humidity [kg/kg]'
# nldas_band_dict['pressure'] = 'Pressure [Pa]'
# nldas_band_dict['temperature'] = 'Temperature [C]'
# nldas_band_dict['wind_u'] = 'u-component of wind [m/s]'
# nldas_band_dict['wind_v'] = 'v-component of wind [m/s]'
# Process each variable
logging.info('\nReading NLDAS GRIBs')
for input_var in variables:
logging.info("Variable: {}".format(input_var))
# Build output folder
var_ws = os.path.join(output_ws, input_var)
if not os.path.isdir(var_ws):
os.makedirs(var_ws)
# Each sub folder in the main folde has all imagery for 1 day
# The path for each subfolder is the /YYYY/DOY
# This approach will process files for target dates
# for input_dt in date_range(start_dt, end_dt + dt.timedelta(1)):
# logging.info(input_dt.date())
# Iterate all available files and check dates if necessary
for root, folders, files in os.walk(grb_ws):
root_split = os.path.normpath(root).split(os.sep)
# If the year/doy is outside the range, skip
if (re.match('\d{4}', root_split[-2]) and
re.match('\d{3}', root_split[-1])):
root_dt = dt.datetime.strptime('{}_{}'.format(
root_split[-2], root_split[-1]), '%Y_%j')
logging.info('{}-{:02d}-{:02d}'.format(
root_dt.year, root_dt.month, root_dt.day))
if ((start_dt is not None and root_dt < start_dt) or
(end_dt is not None and root_dt > end_dt)):
continue
elif date_list and root_dt.date().isoformat() not in date_list:
continue
# If the year is outside the range, don't search subfolders
elif re.match('\d{4}', root_split[-1]):
root_year = int(root_split[-1])
logging.info('Year: {}'.format(root_year))
if ((start_dt is not None and root_year < start_dt.year) or
(end_dt is not None and root_year > end_dt.year)):
folders[:] = []
else:
folders[:] = sorted(folders)
continue
else:
continue
# Create a single raster for each day with 24 bands
# Each time step will be stored in a separate band
output_name = output_fmt.format(
input_var, root_dt.year, root_dt.month, root_dt.day)
output_path = os.path.join(
var_ws, str(root_dt.year), output_name)
logging.debug(' {}'.format(output_path))
if os.path.isfile(output_path):
if not overwrite_flag:
logging.debug(' File already exists, skipping')
continue
else:
logging.debug(' File already exists, removing existing')
os.remove(output_path)
logging.debug(' {}'.format(root))
if not os.path.isdir(os.path.dirname(output_path)):
os.makedirs(os.path.dirname(output_path))
gdc.build_empty_raster(
output_path, band_cnt=24, output_dtype=np.float32,
output_proj=nldas_proj, output_cs=nldas_cs,
output_extent=nldas_extent, output_fill_flag=True)
# Iterate through hourly files
for input_name in sorted(files):
logging.info(' {}'.format(input_name))
input_path = os.path.join(root, input_name)
input_match = input_re.match(input_name)
if input_match is None:
logging.debug(
' Regular expression didn\'t match, skipping')
continue
input_dt = dt.datetime(
int(input_match.group('YEAR')),
int(input_match.group('MONTH')),
int(input_match.group('DAY')))
time_str = input_match.group('TIME')
band_num = int(time_str[:2]) + 1
# if start_dt is not None and input_dt < start_dt:
# continue
# elif end_dt is not None and input_dt > end_dt:
# continue
# elif date_list and input_dt.date().isoformat() not in date_list:
# continue
if time_str not in time_list:
logging.debug(' Time not in list, skipping')
continue
logging.debug(' Time: {} {}'.format(
input_dt.date(), time_str))
logging.debug(' Band: {}'.format(band_num))
# Determine band numbering/naming
input_band_dict = grib_band_names(input_path)
# Extract array and save
input_ds = gdal.Open(input_path)
# Convert Kelvin to Celsius (old NLDAS files were in K i think)
if input_var in ['tair', 'tmmx', 'tmmn']:
# Temperature should be in C for et_common.refet_hourly_func()
if 'Temperature [K]' in input_band_dict.keys():
temp_band_units = 'K'
output_array = gdc.raster_ds_to_array(
input_ds, band=input_band_dict['Temperature [K]'],
mask_extent=nldas_extent, return_nodata=False)
elif 'Temperature [C]' in input_band_dict.keys():
temp_band_units = 'C'
output_array = gdc.raster_ds_to_array(
input_ds, band=input_band_dict['Temperature [C]'],
mask_extent=nldas_extent, return_nodata=False)
else:
logging.error('Unknown Temperature units, skipping')
logging.error(' {}'.format(input_band_dict.keys()))
continue
# DEADBEEF - Having issue with T appearing to be C but labeled as K
# Try to determine temperature units from values
temp_mean = float(np.nanmean(output_array))
temp_units_dict = {20: 'C', 293: 'K'}
temp_array_units = temp_units_dict[
min(temp_units_dict, key=lambda x:abs(x - temp_mean))]
if temp_array_units == 'K' and temp_band_units == 'K':
logging.debug(' Converting temperature from K to C')
output_array -= 273.15
elif temp_array_units == 'C' and temp_band_units == 'C':
pass
elif temp_array_units == 'C' and temp_band_units == 'K':
logging.debug(
(' Temperature units are K in the GRB band name, ' +
'but values appear to be C\n Mean temperature: {:.2f}\n' +
' Values will NOT be adjusted').format(temp_mean))
elif temp_array_units == 'K' and temp_band_units == 'C':
logging.debug(
(' Temperature units are C in the GRB band name, ' +
'but values appear to be K\n Mean temperature: {:.2f}\n' +
' Values will be adjusted from K to C').format(temp_mean))
output_array -= 273.15
# Compute wind speed from vectors
elif input_var == 'vs':
wind_u_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['u-component of wind [m/s]'],
mask_extent=nldas_extent, return_nodata=False)
wind_v_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['v-component of wind [m/s]'],
mask_extent=nldas_extent, return_nodata=False)
output_array = np.sqrt(
wind_u_array ** 2 + wind_v_array ** 2)
# Read all other variables directly
else:
output_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict[nldas_band_dict[input_var]],
mask_extent=nldas_extent, return_nodata=False)
# Save the projected array as 32-bit floats
gdc.array_to_comp_raster(
output_array.astype(np.float32), output_path,
band=band_num)
# gdc.block_to_raster(
# ea_array.astype(np.float32), output_path, band=band)
# gdc.array_to_raster(
# output_array.astype(np.float32), output_path,
# output_geo=nldas_geo, output_proj=nldas_proj,
# stats_flag=stats_flag)
del output_array
input_ds = None
if stats_flag:
gdc.raster_statistics(output_path)
logging.debug('\nScript Complete')
def main(netcdf_ws=os.getcwd(), ancillary_ws=os.getcwd(),
output_ws=os.getcwd(), start_date=None, end_date=None,
extent_path=None, output_extent=None,
stats_flag=True, overwrite_flag=False):
"""Extract DAYMET precipitation
Args:
netcdf_ws (str): folder of DAYMET netcdf files
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
extent_path (str): file path defining the output extent
output_extent (list): decimal degrees values defining output extent
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nExtracting DAYMET precipitation')
# If a date is not set, process 2015
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2015, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2015, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Save DAYMET lat, lon, and elevation arrays
mask_raster = os.path.join(ancillary_ws, 'daymet_mask.img')
daymet_re = re.compile('daymet_v3_(?P<VAR>\w+)_(?P<YEAR>\d{4})_na.nc4$')
# DAYMET band name dictionary
# daymet_band_dict = dict()
# daymet_band_dict['prcp'] = 'precipitation_amount'
# daymet_band_dict['srad'] = 'surface_downwelling_shortwave_flux_in_air'
# daymet_band_dict['sph'] = 'specific_humidity'
# daymet_band_dict['tmin'] = 'air_temperature'
# daymet_band_dict['tmax'] = 'air_temperature'
# Get extent/geo from mask raster
daymet_ds = gdal.Open(mask_raster)
daymet_osr = gdc.raster_ds_osr(daymet_ds)
daymet_proj = gdc.osr_proj(daymet_osr)
daymet_cs = gdc.raster_ds_cellsize(daymet_ds, x_only=True)
daymet_extent = gdc.raster_ds_extent(daymet_ds)
daymet_geo = daymet_extent.geo(daymet_cs)
daymet_x, daymet_y = daymet_extent.origin()
daymet_ds = None
logging.debug(' Projection: {}'.format(daymet_proj))
logging.debug(' Cellsize: {}'.format(daymet_cs))
logging.debug(' Geo: {}'.format(daymet_geo))
logging.debug(' Extent: {}'.format(daymet_extent))
logging.debug(' Origin: {} {}'.format(daymet_x, daymet_y))
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
# Assume input extent is in decimal degrees
output_extent = gdc.project_extent(
gdc.Extent(output_extent), gdc.epsg_osr(4326), daymet_osr, 0.001)
output_extent = gdc.intersect_extents([daymet_extent, output_extent])
output_extent.adjust_to_snap('EXPAND', daymet_x, daymet_y, daymet_cs)
output_geo = output_extent.geo(daymet_cs)
logging.debug(' Geo: {}'.format(output_geo))
logging.debug(' Extent: {}'.format(output_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
if extent_path.lower().endswith('.shp'):
output_extent = gdc.feature_path_extent(extent_path)
extent_osr = gdc.feature_path_osr(extent_path)
extent_cs = None
else:
output_extent = gdc.raster_path_extent(extent_path)
extent_osr = gdc.raster_path_osr(extent_path)
extent_cs = gdc.raster_path_cellsize(extent_path, x_only=True)
output_extent = gdc.project_extent(
output_extent, extent_osr, daymet_osr, extent_cs)
output_extent = gdc.intersect_extents([daymet_extent, output_extent])
output_extent.adjust_to_snap('EXPAND', daymet_x, daymet_y, daymet_cs)
output_geo = output_extent.geo(daymet_cs)
logging.debug(' Geo: {}'.format(output_geo))
logging.debug(' Extent: {}'.format(output_extent))
else:
output_extent = daymet_extent.copy()
output_geo = daymet_geo[:]
# output_shape = output_extent.shape(cs=daymet_cs)
xi, yi = gdc.array_geo_offsets(daymet_geo, output_geo, daymet_cs)
output_rows, output_cols = output_extent.shape(daymet_cs)
logging.debug(' Shape: {} {}'.format(output_rows, output_cols))
logging.debug(' Offsets: {} {} (x y)'.format(xi, yi))
# Process each variable
input_var = 'prcp'
output_var = 'ppt'
logging.info("\nVariable: {}".format(input_var))
# Build output folder
var_ws = os.path.join(output_ws, output_var)
if not os.path.isdir(var_ws):
os.makedirs(var_ws)
# Process each file in the input workspace
for input_name in sorted(os.listdir(netcdf_ws)):
logging.debug("{}".format(input_name))
input_match = daymet_re.match(input_name)
if not input_match:
logging.debug(' Regular expression didn\'t match, skipping')
continue
elif input_match.group('VAR') != input_var:
logging.debug(' Variable didn\'t match, skipping')
continue
year_str = input_match.group('YEAR')
logging.info(" Year: {}".format(year_str))
year_int = int(year_str)
year_days = int(dt.datetime(year_int, 12, 31).strftime('%j'))
if start_dt is not None and year_int < start_dt.year:
logging.debug(' Before start date, skipping')
continue
elif end_dt is not None and year_int > end_dt.year:
logging.debug(' After end date, skipping')
continue
# Build input file path
input_raster = os.path.join(netcdf_ws, input_name)
# if not os.path.isfile(input_raster):
# logging.debug(
# ' Input raster doesn\'t exist, skipping {}'.format(
# input_raster))
# continue
# Build output folder
output_year_ws = os.path.join(var_ws, year_str)
if not os.path.isdir(output_year_ws):
os.makedirs(output_year_ws)
# Read in the DAYMET NetCDF file
input_nc_f = netCDF4.Dataset(input_raster, 'r')
# logging.debug(input_nc_f.variables)
# Check all valid dates in the year
year_dates = date_range(
dt.datetime(year_int, 1, 1), dt.datetime(year_int + 1, 1, 1))
for date_dt in year_dates:
if start_dt is not None and date_dt < start_dt:
logging.debug(' {} - before start date, skipping'.format(
date_dt.date()))
continue
elif end_dt is not None and date_dt > end_dt:
logging.debug(' {} - after end date, skipping'.format(
date_dt.date()))
continue
else:
logging.info(' {}'.format(date_dt.date()))
output_path = os.path.join(
output_year_ws, '{}_{}_daymet.img'.format(
output_var, date_dt.strftime('%Y%m%d')))
if os.path.isfile(output_path):
logging.debug(' {}'.format(output_path))
if not overwrite_flag:
logging.debug(' File already exists, skipping')
continue
else:
logging.debug(' File already exists, removing existing')
os.remove(output_path)
doy = int(date_dt.strftime('%j'))
doy_i = range(1, year_days + 1).index(doy)
# Arrays are being read as masked array with a fill value of -9999
# Convert to basic numpy array arrays with nan values
try:
input_ma = input_nc_f.variables[input_var][
doy_i, yi: yi + output_rows, xi: xi + output_cols]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
input_nodata = float(input_ma.fill_value)
output_array = input_ma.data.astype(np.float32)
output_array[output_array == input_nodata] = np.nan
# Save the array as 32-bit floats
gdc.array_to_raster(
output_array.astype(np.float32), output_path,
output_geo=output_geo, output_proj=daymet_proj,
stats_flag=stats_flag)
del input_ma, output_array
input_nc_f.close()
del input_nc_f
logging.debug('\nScript Complete')
def main(netcdf_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
start_date=None,
end_date=None,
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Extract GRIDMET temperature
Args:
netcdf_ws (str): folder of GRIDMET netcdf files
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
extent_path (str): filepath a raster defining the output extent
output_extent (list): decimal degrees values defining output extent
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nExtracting GRIDMET vapor pressure')
# If a date is not set, process 2017
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2017, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2017, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Save GRIDMET lat, lon, and elevation arrays
elev_raster = os.path.join(ancillary_ws, 'gridmet_elev.img')
output_fmt = '{}_{}_daily_gridmet.img'
gridmet_re = re.compile('(?P<VAR>\w+)_(?P<YEAR>\d{4}).nc$')
# GRIDMET band name dictionary
gridmet_band_dict = dict()
gridmet_band_dict['pr'] = 'precipitation_amount'
gridmet_band_dict['srad'] = 'surface_downwelling_shortwave_flux_in_air'
gridmet_band_dict['sph'] = 'specific_humidity'
gridmet_band_dict['tmmn'] = 'air_temperature'
gridmet_band_dict['tmmx'] = 'air_temperature'
gridmet_band_dict['vs'] = 'wind_speed'
# Get extent/geo from elevation raster
gridmet_ds = gdal.Open(elev_raster)
gridmet_osr = gdc.raster_ds_osr(gridmet_ds)
gridmet_proj = gdc.osr_proj(gridmet_osr)
gridmet_cs = gdc.raster_ds_cellsize(gridmet_ds, x_only=True)
gridmet_extent = gdc.raster_ds_extent(gridmet_ds)
gridmet_full_geo = gridmet_extent.geo(gridmet_cs)
gridmet_x, gridmet_y = gridmet_extent.origin()
gridmet_ds = None
logging.debug(' Projection: {}'.format(gridmet_proj))
logging.debug(' Cellsize: {}'.format(gridmet_cs))
logging.debug(' Geo: {}'.format(gridmet_full_geo))
logging.debug(' Extent: {}'.format(gridmet_extent))
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
gridmet_extent = gdc.Extent(output_extent)
gridmet_extent.adjust_to_snap('EXPAND', gridmet_x, gridmet_y,
gridmet_cs)
gridmet_geo = gridmet_extent.geo(gridmet_cs)
logging.debug(' Geo: {}'.format(gridmet_geo))
logging.debug(' Extent: {}'.format(gridmet_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
gridmet_extent = gdc.raster_path_extent(extent_path)
extent_osr = gdc.raster_path_osr(extent_path)
extent_cs = gdc.raster_path_cellsize(extent_path, x_only=True)
gridmet_extent = gdc.project_extent(gridmet_extent, extent_osr,
gridmet_osr, extent_cs)
gridmet_extent.adjust_to_snap('EXPAND', gridmet_x, gridmet_y,
gridmet_cs)
gridmet_geo = gridmet_extent.geo(gridmet_cs)
logging.debug(' Geo: {}'.format(gridmet_geo))
logging.debug(' Extent: {}'.format(gridmet_extent))
else:
gridmet_geo = gridmet_full_geo
# Get indices for slicing/clipping input arrays
g_i, g_j = gdc.array_geo_offsets(gridmet_full_geo,
gridmet_geo,
cs=gridmet_cs)
g_rows, g_cols = gridmet_extent.shape(cs=gridmet_cs)
# Read the elevation array
elev_array = gdc.raster_to_array(elev_raster,
mask_extent=gridmet_extent,
return_nodata=False)
pair_array = et_common.air_pressure_func(elev_array)
del elev_array
# Process each variable
input_var = 'sph'
output_var = 'ea'
logging.info("\nVariable: {}".format(input_var))
# Build output folder
var_ws = os.path.join(output_ws, output_var)
if not os.path.isdir(var_ws):
os.makedirs(var_ws)
# Process each file in the input workspace
for input_name in sorted(os.listdir(netcdf_ws)):
input_match = gridmet_re.match(input_name)
if not input_match:
logging.debug("{}".format(input_name))
logging.debug(' Regular expression didn\'t match, skipping')
continue
elif input_match.group('VAR') != input_var:
logging.debug("{}".format(input_name))
logging.debug(' Variable didn\'t match, skipping')
continue
else:
logging.info("{}".format(input_name))
year_str = input_match.group('YEAR')
logging.info(" {}".format(year_str))
year_int = int(year_str)
year_days = int(dt.datetime(year_int, 12, 31).strftime('%j'))
if start_dt is not None and year_int < start_dt.year:
logging.debug(' Before start date, skipping')
continue
elif end_dt is not None and year_int > end_dt.year:
logging.debug(' After end date, skipping')
continue
# Build input file path
input_raster = os.path.join(netcdf_ws, input_name)
# if not os.path.isfile(input_raster):
# logging.debug(
# ' Input NetCDF doesn\'t exist, skipping {}'.format(
# input_raster))
# continue
# Create a single raster for each year with 365 bands
# Each day will be stored in a separate band
output_path = os.path.join(var_ws,
output_fmt.format(output_var, year_str))
logging.debug(' {}'.format(output_path))
if os.path.isfile(output_path):
if not overwrite_flag:
logging.debug(' File already exists, skipping')
continue
else:
logging.debug(' File already exists, removing existing')
os.remove(output_path)
gdc.build_empty_raster(output_path,
band_cnt=366,
output_dtype=np.float32,
output_proj=gridmet_proj,
output_cs=gridmet_cs,
output_extent=gridmet_extent,
output_fill_flag=True)
# Read in the GRIDMET NetCDF file
# Immediatly clip input array to save memory
input_nc_f = netCDF4.Dataset(input_raster, 'r')
input_nc = input_nc_f.variables[
gridmet_band_dict[input_var]][:, g_i:g_i + g_cols,
g_j:g_j + g_rows].copy()
input_nc = np.transpose(input_nc, (0, 2, 1))
# A numpy array is returned when slicing a masked array
# if there are no masked pixels
# This is a hack to force the numpy array back to a masked array
if type(input_nc) != np.ma.core.MaskedArray:
input_nc = np.ma.core.MaskedArray(
input_nc, np.zeros(input_nc.shape, dtype=bool))
# Check all valid dates in the year
year_dates = date_range(dt.datetime(year_int, 1, 1),
dt.datetime(year_int + 1, 1, 1))
for date_dt in year_dates:
if start_dt is not None and date_dt < start_dt:
# logging.debug(' before start date, skipping')
continue
elif end_dt is not None and date_dt > end_dt:
# logging.debug(' after end date, skipping')
continue
logging.info(' {}'.format(date_dt.strftime('%Y_%m_%d')))
doy = int(date_dt.strftime('%j'))
doy_i = range(1, year_days + 1).index(doy)
# Arrays are being read as masked array with a fill value of -9999
# Convert to basic numpy array arrays with nan values
try:
input_full_ma = input_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
input_full_array = input_full_ma.data.astype(np.float32)
input_full_nodata = float(input_full_ma.fill_value)
input_full_array[input_full_array == input_full_nodata] = np.nan
# Since inputs are netcdf, need to create GDAL raster
# datasets in order to use gdal_common functions
# Create an in memory dataset of the full ETo array
input_full_ds = gdc.array_to_mem_ds(input_full_array,
output_geo=gridmet_full_geo,
output_proj=gridmet_proj)
# Then extract the subset from the in memory dataset
sph_array = gdc.raster_ds_to_array(input_full_ds,
1,
mask_extent=gridmet_extent,
return_nodata=False)
# Compute ea [kPa] from specific humidity [kg/kg]
ea_array = (sph_array * pair_array) / (0.622 + 0.378 * sph_array)
# Save the projected array as 32-bit floats
gdc.array_to_comp_raster(ea_array.astype(np.float32),
output_path,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# ea_array.astype(np.float32), output_path,
# output_geo=gridmet_geo, output_proj=gridmet_proj,
# stats_flag=False)
del sph_array, ea_array
input_nc_f.close()
del input_nc_f
if stats_flag:
gdc.raster_statistics(output_path)
logging.debug('\nScript Complete')
def main(grb_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
etr_flag=False,
eto_flag=False,
landsat_ws=None,
start_date=None,
end_date=None,
times_str='',
extent_path=None,
output_extent=None,
daily_flag=True,
stats_flag=True,
overwrite_flag=False):
"""Compute hourly ETr/ETo from NLDAS data
Args:
grb_ws (str): folder of NLDAS GRB files
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
etr_flag (bool): if True, compute alfalfa reference ET (ETr)
eto_flag (bool): if True, compute grass reference ET (ETo)
landsat_ws (str): folder of Landsat scenes or tar.gz files
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
times (str): comma separated values and/or ranges of UTC hours
(i.e. "1, 2, 5-8")
Parsed with python_common.parse_int_set()
extent_path (str): file path defining the output extent
output_extent (list): decimal degrees values defining output extent
daily_flag (bool): if True, save daily ETr/ETo sum raster.
Default is True
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nComputing NLDAS hourly ETr/ETo')
np.seterr(invalid='ignore')
# Compute ETr and/or ETo
if not etr_flag and not eto_flag:
logging.info(' ETo/ETr flag(s) not set, defaulting to ETr')
etr_flag = True
# If a date is not set, process 2017
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2017, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2017, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Only process a specific hours
if not times_str:
time_list = range(0, 24, 1)
else:
time_list = list(parse_int_set(times_str))
time_list = ['{:02d}00'.format(t) for t in time_list]
etr_folder = 'etr'
eto_folder = 'eto'
hour_fmt = '{}_{:04d}{:02d}{:02d}_hourly_nldas.img'
# hour_fmt = '{}_{:04d}{:02d}{:02d}_{4:04d}_nldas.img'
day_fmt = '{}_{:04d}{:02d}{:02d}_nldas.img'
# input_fmt = 'NLDAS_FORA0125_H.A{:04d}{:02d}{:02d}.{}.002.grb'
input_re = re.compile('NLDAS_FORA0125_H.A(?P<YEAR>\d{4})(?P<MONTH>\d{2})' +
'(?P<DAY>\d{2}).(?P<TIME>\d{4}).002.grb$')
# Assume NLDAS is NAD83
# input_epsg = 'EPSG:4269'
# Ancillary raster paths
mask_path = os.path.join(ancillary_ws, 'nldas_mask.img')
elev_path = os.path.join(ancillary_ws, 'nldas_elev.img')
lat_path = os.path.join(ancillary_ws, 'nldas_lat.img')
lon_path = os.path.join(ancillary_ws, 'nldas_lon.img')
# Build a date list from landsat_ws scene folders or tar.gz files
date_list = []
if landsat_ws is not None and os.path.isdir(landsat_ws):
logging.info('\nReading dates from Landsat IDs')
logging.info(' {}'.format(landsat_ws))
landsat_re = re.compile(
'^(?:LT04|LT05|LE07|LC08)_(?:\d{3})(?:\d{3})_' +
'(?P<year>\d{4})(?P<month>\d{2})(?P<day>\d{2})')
for root, dirs, files in os.walk(landsat_ws, topdown=True):
# If root matches, don't explore subfolders
try:
landsat_match = landsat_re.match(os.path.basename(root))
date_list.append(
dt.datetime.strptime('_'.join(landsat_match.groups()),
'%Y_%m_%d').date().isoformat())
dirs[:] = []
except:
pass
for file in files:
try:
landsat_match = landsat_re.match(file)
date_list.append(
dt.datetime.strptime('_'.join(landsat_match.groups()),
'%Y_%m_%d').date().isoformat())
except:
pass
date_list = sorted(list(set(date_list)))
# elif landsat_ws is not None and os.path.isfile(landsat_ws):
# with open(landsat_ws) as landsat_f:
# This allows GDAL to throw Python Exceptions
# gdal.UseExceptions()
# mem_driver = gdal.GetDriverByName('MEM')
# Get the NLDAS spatial reference from the mask raster
nldas_ds = gdal.Open(mask_path)
nldas_osr = gdc.raster_ds_osr(nldas_ds)
nldas_proj = gdc.osr_proj(nldas_osr)
nldas_cs = gdc.raster_ds_cellsize(nldas_ds, x_only=True)
nldas_extent = gdc.raster_ds_extent(nldas_ds)
nldas_geo = nldas_extent.geo(nldas_cs)
nldas_x, nldas_y = nldas_extent.origin()
nldas_ds = None
logging.debug(' Projection: {}'.format(nldas_proj))
logging.debug(' Cellsize: {}'.format(nldas_cs))
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(nldas_extent))
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
nldas_extent = gdc.Extent(output_extent)
nldas_extent.adjust_to_snap('EXPAND', nldas_x, nldas_y, nldas_cs)
nldas_geo = nldas_extent.geo(nldas_cs)
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(output_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
if extent_path.lower().endswith('.shp'):
nldas_extent = gdc.feature_path_extent(extent_path)
extent_osr = gdc.feature_path_osr(extent_path)
extent_cs = None
else:
nldas_extent = gdc.raster_path_extent(extent_path)
extent_osr = gdc.raster_path_osr(extent_path)
extent_cs = gdc.raster_path_cellsize(extent_path, x_only=True)
nldas_extent = gdc.project_extent(nldas_extent, extent_osr, nldas_osr,
extent_cs)
nldas_extent.adjust_to_snap('EXPAND', nldas_x, nldas_y, nldas_cs)
nldas_geo = nldas_extent.geo(nldas_cs)
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(nldas_extent))
logging.debug('')
# Read the NLDAS mask array if present
if mask_path and os.path.isfile(mask_path):
mask_array, mask_nodata = gdc.raster_to_array(mask_path,
mask_extent=nldas_extent,
fill_value=0,
return_nodata=True)
mask_array = mask_array != mask_nodata
else:
mask_array = None
# Read ancillary arrays (or subsets?)
elev_array = gdc.raster_to_array(elev_path,
mask_extent=nldas_extent,
return_nodata=False)
# pair_array = et_common.air_pressure_func(elev_array)
lat_array = gdc.raster_to_array(lat_path,
mask_extent=nldas_extent,
return_nodata=False)
lon_array = gdc.raster_to_array(lon_path,
mask_extent=nldas_extent,
return_nodata=False)
# Hourly RefET functions expects lat/lon in radians
lat_array *= (math.pi / 180)
lon_array *= (math.pi / 180)
# Build output folder
etr_ws = os.path.join(output_ws, etr_folder)
eto_ws = os.path.join(output_ws, eto_folder)
if etr_flag and not os.path.isdir(etr_ws):
os.makedirs(etr_ws)
if eto_flag and not os.path.isdir(eto_ws):
os.makedirs(eto_ws)
# DEADBEEF - Instead of processing all available files, the following
# code will process files for target dates
# for input_dt in date_range(start_dt, end_dt + dt.timedelta(1)):
# logging.info(input_dt.date())
# Iterate all available files and check dates if necessary
# Each sub folder in the main folder has all imagery for 1 day
# (in UTC time)
# The path for each subfolder is the /YYYY/DOY
errors = defaultdict(list)
for root, folders, files in os.walk(grb_ws):
root_split = os.path.normpath(root).split(os.sep)
# If the year/doy is outside the range, skip
if (re.match('\d{4}', root_split[-2])
and re.match('\d{3}', root_split[-1])):
root_dt = dt.datetime.strptime(
'{}_{}'.format(root_split[-2], root_split[-1]), '%Y_%j')
logging.info('{}'.format(root_dt.date()))
if ((start_dt is not None and root_dt < start_dt)
or (end_dt is not None and root_dt > end_dt)):
continue
elif date_list and root_dt.date().isoformat() not in date_list:
continue
# If the year is outside the range, don't search subfolders
elif re.match('\d{4}', root_split[-1]):
root_year = int(root_split[-1])
logging.info('Year: {}'.format(root_year))
if ((start_dt is not None and root_year < start_dt.year)
or (end_dt is not None and root_year > end_dt.year)):
folders[:] = []
else:
folders[:] = sorted(folders)
continue
else:
continue
logging.debug(' {}'.format(root))
# Start off assuming every file needs to be processed
day_skip_flag = False
# Build output folders if necessary
etr_year_ws = os.path.join(etr_ws, str(root_dt.year))
eto_year_ws = os.path.join(eto_ws, str(root_dt.year))
if etr_flag and not os.path.isdir(etr_year_ws):
os.makedirs(etr_year_ws)
if eto_flag and not os.path.isdir(eto_year_ws):
os.makedirs(eto_year_ws)
# Build daily total paths
etr_day_path = os.path.join(
etr_year_ws,
day_fmt.format('etr', root_dt.year, root_dt.month, root_dt.day))
eto_day_path = os.path.join(
eto_year_ws,
day_fmt.format('eto', root_dt.year, root_dt.month, root_dt.day))
etr_hour_path = os.path.join(
etr_year_ws,
hour_fmt.format('etr', root_dt.year, root_dt.month, root_dt.day))
eto_hour_path = os.path.join(
eto_year_ws,
hour_fmt.format('eto', root_dt.year, root_dt.month, root_dt.day))
# logging.debug(' {}'.format(etr_hour_path))
# If daily ETr/ETo files are present, day can be skipped
if not overwrite_flag and daily_flag:
if etr_flag and not os.path.isfile(etr_day_path):
pass
elif eto_flag and not os.path.isfile(eto_day_path):
pass
else:
day_skip_flag = True
# If the hour and daily files don't need to be made, skip the day
if not overwrite_flag:
if etr_flag and not os.path.isfile(etr_hour_path):
pass
elif eto_flag and not os.path.isfile(eto_hour_path):
pass
elif day_skip_flag:
logging.debug(' File(s) already exist, skipping')
continue
# Create a single raster for each day with 24 bands
# Each time step will be stored in a separate band
if etr_flag:
logging.debug(' {}'.format(etr_day_path))
gdc.build_empty_raster(etr_hour_path,
band_cnt=24,
output_dtype=np.float32,
output_proj=nldas_proj,
output_cs=nldas_cs,
output_extent=nldas_extent,
output_fill_flag=True)
if eto_flag:
logging.debug(' {}'.format(eto_day_path))
gdc.build_empty_raster(eto_hour_path,
band_cnt=24,
output_dtype=np.float32,
output_proj=nldas_proj,
output_cs=nldas_cs,
output_extent=nldas_extent,
output_fill_flag=True)
# Sum all ETr/ETo images in each folder to generate a UTC day total
etr_day_array = 0
eto_day_array = 0
# Process each hour file
for input_name in sorted(files):
logging.info(' {}'.format(input_name))
input_match = input_re.match(input_name)
if input_match is None:
logging.debug(' Regular expression didn\'t match, skipping')
continue
input_dt = dt.datetime(int(input_match.group('YEAR')),
int(input_match.group('MONTH')),
int(input_match.group('DAY')))
input_doy = int(input_dt.strftime('%j'))
time_str = input_match.group('TIME')
band_num = int(time_str[:2]) + 1
# if start_dt is not None and input_dt < start_dt:
# continue
# elif end_dt is not None and input_dt > end_dt:
# continue
# elif date_list and input_dt.date().isoformat() not in date_list:
# continue
if not daily_flag and time_str not in time_list:
logging.debug(' Time not in list and not daily, skipping')
continue
input_path = os.path.join(root, input_name)
logging.debug(' Time: {} {}'.format(input_dt.date(), time_str))
logging.debug(' Band: {}'.format(band_num))
# Determine band numbering/naming
try:
input_band_dict = grib_band_names(input_path)
except RuntimeError as e:
errors[input_path].append(e)
logging.error(' RuntimeError: {} Skipping: {}'.format(
e, input_path))
continue
# Read input bands
input_ds = gdal.Open(input_path)
# Temperature should be in C for et_common.refet_hourly_func()
if 'Temperature [K]' in input_band_dict.keys():
temp_band_units = 'K'
temp_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['Temperature [K]'],
mask_extent=nldas_extent,
return_nodata=False)
elif 'Temperature [C]' in input_band_dict.keys():
temp_band_units = 'C'
temp_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['Temperature [C]'],
mask_extent=nldas_extent,
return_nodata=False)
else:
logging.error('Unknown Temperature units, skipping')
logging.error(' {}'.format(input_band_dict.keys()))
continue
# DEADBEEF - Having issue with T appearing to be C but labeled as K
# Try to determine temperature units from values
temp_mean = float(np.nanmean(temp_array))
temp_units_dict = {20: 'C', 293: 'K'}
temp_array_units = temp_units_dict[min(
temp_units_dict, key=lambda x: abs(x - temp_mean))]
if temp_array_units == 'K' and temp_band_units == 'K':
logging.debug(' Converting temperature from K to C')
temp_array -= 273.15
elif temp_array_units == 'C' and temp_band_units == 'C':
pass
elif temp_array_units == 'C' and temp_band_units == 'K':
logging.debug((
' Temperature units are K in the GRB band name, ' +
'but values appear to be C\n Mean temperature: {:.2f}\n'
+ ' Values will NOT be adjusted').format(temp_mean))
elif temp_array_units == 'K' and temp_band_units == 'C':
logging.debug((
' Temperature units are C in the GRB band name, ' +
'but values appear to be K\n Mean temperature: {:.2f}\n'
+
' Values will be adjusted from K to C').format(temp_mean))
temp_array -= 273.15
try:
sph_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['Specific humidity [kg/kg]'],
mask_extent=nldas_extent,
return_nodata=False)
rs_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict[
'Downward shortwave radiation flux [W/m^2]'],
mask_extent=nldas_extent,
return_nodata=False)
wind_u_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['u-component of wind [m/s]'],
mask_extent=nldas_extent,
return_nodata=False)
wind_v_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['v-component of wind [m/s]'],
mask_extent=nldas_extent,
return_nodata=False)
input_ds = None
except KeyError as e:
errors[input_path].append(e)
logging.error(' KeyError: {} Skipping: {}'.format(
e, input_ds.GetDescription()))
continue
rs_array *= 0.0036 # W m-2 to MJ m-2 hr-1
wind_array = np.sqrt(wind_u_array**2 + wind_v_array**2)
del wind_u_array, wind_v_array
# ETr
if etr_flag:
etr_array = et_common.refet_hourly_func(temp_array,
sph_array,
rs_array,
wind_array,
zw=10,
elev=elev_array,
lat=lat_array,
lon=lon_array,
doy=input_doy,
time=int(time_str) /
100,
ref_type='ETR')
if daily_flag:
etr_day_array += etr_array
if time_str in time_list:
gdc.array_to_comp_raster(etr_array.astype(np.float32),
etr_hour_path,
band=band_num,
stats_flag=False)
del etr_array
# ETo
if eto_flag:
eto_array = et_common.refet_hourly_func(temp_array,
sph_array,
rs_array,
wind_array,
zw=10,
elev=elev_array,
lat=lat_array,
lon=lon_array,
doy=input_doy,
time=int(time_str) /
100,
ref_type='ETO')
if eto_flag and daily_flag:
eto_day_array += eto_array
if eto_flag and time_str in time_list:
gdc.array_to_comp_raster(eto_array.astype(np.float32),
eto_hour_path,
band=band_num,
stats_flag=False)
del eto_array
del temp_array, sph_array, rs_array, wind_array
if stats_flag and etr_flag:
gdc.raster_statistics(etr_hour_path)
if stats_flag and eto_flag:
gdc.raster_statistics(eto_hour_path)
# Save the projected ETr/ETo as 32-bit floats
if not day_skip_flag and daily_flag:
if etr_flag:
try:
gdc.array_to_raster(etr_day_array.astype(np.float32),
etr_day_path,
output_geo=nldas_geo,
output_proj=nldas_proj,
stats_flag=stats_flag)
except AttributeError:
pass
if eto_flag:
try:
gdc.array_to_raster(eto_day_array.astype(np.float32),
eto_day_path,
output_geo=nldas_geo,
output_proj=nldas_proj,
stats_flag=stats_flag)
except AttributeError:
pass
del etr_day_array, eto_day_array
if len(errors) > 0:
logging.info('\nThe following errors were encountered:')
for key, value in errors.items():
logging.error(' Filepath: {}, error: {}'.format(key, value))
logging.debug('\nScript Complete')
def main(ancillary_ws=os.getcwd(),
zero_elev_nodata_flag=False,
overwrite_flag=False):
"""Process GRIDMET ancillary data
Args:
ancillary_ws (str): folder of ancillary rasters
zero_elev_nodata_flag (bool): if True, set elevation nodata values to 0
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nProcess GRIDMET ancillary rasters')
# Site URL
elev_url = 'https://climate.northwestknowledge.net/METDATA/data/metdata_elevationdata.nc'
# Manually define the spatial reference and extent of the GRIDMET data
# This could be read in from a raster
gridmet_osr = osr.SpatialReference()
# Assume GRIDMET data is in WGS84 not NAD83 (need to check with John)
gridmet_osr.ImportFromEPSG(4326)
# gridmet_osr.ImportFromEPSG(4326)
gridmet_proj = gdc.osr_proj(gridmet_osr)
gridmet_cs = 1. / 24 # 0.041666666666666666
gridmet_x = -125 + gridmet_cs * 5
gridmet_y = 49 + gridmet_cs * 10
# gridmet_y = lon_array[0,0] - 0.5 * gridmet_cs
# gridmet_y = lat_array[0,0] + 0.5 * gridmet_cs
# gridmet_rows, gridmet_cols = elev_array.shape
gridmet_geo = (gridmet_x, gridmet_cs, 0., gridmet_y, 0., -gridmet_cs)
# gridmet_extent = gdc.geo_extent(
# gridmet_geo, gridmet_rows, gridmet_cols)
# Keep track of the original/full geo-transform and extent
# gridmet_full_geo = (
# gridmet_x, gridmet_cs, 0., gridmet_y, 0., -gridmet_cs)
# gridmet_full_extent = gdc.geo_extent(
# gridmet_geo, gridmet_rows, gridmet_cols)
logging.debug(' X/Y: {} {}'.format(gridmet_x, gridmet_y))
logging.debug(' Geo: {}'.format(gridmet_geo))
logging.debug(' Cellsize: {}'.format(gridmet_cs))
# Build output workspace if it doesn't exist
if not os.path.isdir(ancillary_ws):
os.makedirs(ancillary_ws)
# Output paths
elev_nc = os.path.join(ancillary_ws, os.path.basename(elev_url))
elev_raster = os.path.join(ancillary_ws, 'gridmet_elev.img')
lat_raster = os.path.join(ancillary_ws, 'gridmet_lat.img')
lon_raster = os.path.join(ancillary_ws, 'gridmet_lon.img')
# Compute DEM raster
if overwrite_flag or not os.path.isfile(elev_raster):
logging.info('\nGRIDMET DEM')
logging.info(' Downloading')
logging.debug(' {}'.format(elev_url))
logging.debug(' {}'.format(elev_nc))
url_download(elev_url, elev_nc)
# try:
# urllib.urlretrieve(elev_url, elev_nc)
# except:
# logging.error(" ERROR: {}\n FILE: {}".format(
# sys.exc_info()[0], elev_nc))
# # Try to remove the file since it may not have completely downloaded
# os.remove(elev_nc)
logging.info(' Extracting')
logging.debug(' {}'.format(elev_raster))
elev_nc_f = netCDF4.Dataset(elev_nc, 'r')
elev_ma = elev_nc_f.variables['elevation'][0, :, :]
elev_array = elev_ma.data.astype(np.float32)
# elev_nodata = float(elev_ma.fill_value)
elev_array[(elev_array == elev_ma.fill_value) |
(elev_array <= -300)] = np.nan
if zero_elev_nodata_flag:
elev_array[np.isnan(elev_array)] = 0
if np.all(np.isnan(elev_array)):
logging.error(
'\nERROR: The elevation array is all nodata, exiting\n')
sys.exit()
gdc.array_to_raster(elev_array,
elev_raster,
output_geo=gridmet_geo,
output_proj=gridmet_proj)
elev_nc_f.close()
# del elev_nc_f, elev_ma, elev_array, elev_nodata
del elev_nc_f, elev_ma, elev_array
os.remove(elev_nc)
# Compute latitude/longitude rasters
if ((overwrite_flag or not os.path.isfile(lat_raster)
or not os.path.isfile(lat_raster)) and os.path.isfile(elev_raster)):
logging.info('\nGRIDMET Latitude/Longitude')
logging.debug(' {}'.format(lat_raster))
lat_array, lon_array = gdc.raster_lat_lon_func(elev_raster)
# Handle the conversion to radians in the other GRIDMET scripts
# lat_array *= (math.pi / 180)
gdc.array_to_raster(lat_array,
lat_raster,
output_geo=gridmet_geo,
output_proj=gridmet_proj)
logging.debug(' {}'.format(lon_raster))
gdc.array_to_raster(lon_array,
lon_raster,
output_geo=gridmet_geo,
output_proj=gridmet_proj)
del lat_array, lon_array
logging.debug('\nScript Complete')
def main(grb_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
landsat_ws=None,
start_date=None,
end_date=None,
times_str='',
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Extract hourly NLDAS vapour pressure rasters
Args:
grb_ws (str): folder of NLDAS GRB files
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
landsat_ws (str): folder of Landsat scenes or tar.gz files
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
times (str): comma separated values and/or ranges of UTC hours
(i.e. "1, 2, 5-8")
Parsed with python_common.parse_int_set()
extent_path (str): file path defining the output extent
output_extent (list): decimal degrees values defining output extent
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nExtracting NLDAS vapour pressure rasters')
# input_fmt = 'NLDAS_FORA0125_H.A{:04d}{:02d}{:02d}.{}.002.grb'
input_re = re.compile('NLDAS_FORA0125_H.A(?P<YEAR>\d{4})(?P<MONTH>\d{2})' +
'(?P<DAY>\d{2}).(?P<TIME>\d{4}).002.grb$')
output_folder = 'ea'
output_fmt = 'ea_{:04d}{:02d}{:02d}_hourly_nldas.img'
# output_fmt = 'ea_{:04d}{:02d}{:02d}_{:04d}_nldas.img'
# If a date is not set, process 2017
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2017, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2017, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Only process a specific hours
if not times_str:
time_list = range(0, 24, 1)
else:
time_list = list(parse_int_set(times_str))
time_list = ['{:02d}00'.format(t) for t in time_list]
# Assume NLDAS is NAD83
# input_epsg = 'EPSG:4269'
# Ancillary raster paths
mask_path = os.path.join(ancillary_ws, 'nldas_mask.img')
elev_path = os.path.join(ancillary_ws, 'nldas_elev.img')
# Build a date list from landsat_ws scene folders or tar.gz files
date_list = []
if landsat_ws is not None and os.path.isdir(landsat_ws):
logging.info('\nReading dates from Landsat IDs')
logging.info(' {}'.format(landsat_ws))
landsat_re = re.compile(
'^(?:LT04|LT05|LE07|LC08)_(?:\d{3})(?:\d{3})_' +
'(?P<year>\d{4})(?P<month>\d{2})(?P<day>\d{2})')
for root, dirs, files in os.walk(landsat_ws, topdown=True):
# If root matches, don't explore subfolders
try:
landsat_match = landsat_re.match(os.path.basename(root))
date_list.append(
dt.datetime.strptime('_'.join(landsat_match.groups()),
'%Y_%m_%d').date().isoformat())
dirs[:] = []
except:
pass
for file in files:
try:
landsat_match = landsat_re.match(file)
date_list.append(
dt.datetime.strptime('_'.join(landsat_match.groups()),
'%Y_%m_%d').date().isoformat())
except:
pass
date_list = sorted(list(set(date_list)))
# elif landsat_ws is not None and os.path.isfile(landsat_ws):
# with open(landsat_ws) as landsat_f:
# This allows GDAL to throw Python Exceptions
# gdal.UseExceptions()
# mem_driver = gdal.GetDriverByName('MEM')
# Get the NLDAS spatial reference from the mask raster
nldas_ds = gdal.Open(mask_path)
nldas_osr = gdc.raster_ds_osr(nldas_ds)
nldas_proj = gdc.osr_proj(nldas_osr)
nldas_cs = gdc.raster_ds_cellsize(nldas_ds, x_only=True)
nldas_extent = gdc.raster_ds_extent(nldas_ds)
nldas_geo = nldas_extent.geo(nldas_cs)
nldas_x, nldas_y = nldas_extent.origin()
nldas_ds = None
logging.debug(' Projection: {}'.format(nldas_proj))
logging.debug(' Cellsize: {}'.format(nldas_cs))
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(nldas_extent))
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
nldas_extent = gdc.Extent(output_extent)
nldas_extent.adjust_to_snap('EXPAND', nldas_x, nldas_y, nldas_cs)
nldas_geo = nldas_extent.geo(nldas_cs)
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(output_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
if extent_path.lower().endswith('.shp'):
nldas_extent = gdc.feature_path_extent(extent_path)
extent_osr = gdc.feature_path_osr(extent_path)
extent_cs = None
else:
nldas_extent = gdc.raster_path_extent(extent_path)
extent_osr = gdc.raster_path_osr(extent_path)
extent_cs = gdc.raster_path_cellsize(extent_path, x_only=True)
nldas_extent = gdc.project_extent(nldas_extent, extent_osr, nldas_osr,
extent_cs)
nldas_extent.adjust_to_snap('EXPAND', nldas_x, nldas_y, nldas_cs)
nldas_geo = nldas_extent.geo(nldas_cs)
logging.debug(' Geo: {}'.format(nldas_geo))
logging.debug(' Extent: {}'.format(nldas_extent))
logging.debug('')
# Read the NLDAS mask array if present
if mask_path and os.path.isfile(mask_path):
mask_array, mask_nodata = gdc.raster_to_array(mask_path,
mask_extent=nldas_extent,
fill_value=0,
return_nodata=True)
mask_array = mask_array != mask_nodata
else:
mask_array = None
# Read elevation arrays (or subsets?)
elev_array = gdc.raster_to_array(elev_path,
mask_extent=nldas_extent,
return_nodata=False)
pair_array = et_common.air_pressure_func(elev_array)
# Build output folder
var_ws = os.path.join(output_ws, output_folder)
if not os.path.isdir(var_ws):
os.makedirs(var_ws)
# Each sub folder in the main folder has all imagery for 1 day
# The path for each subfolder is the /YYYY/DOY
# This approach will process files for target dates
# for input_dt in date_range(start_dt, end_dt + dt.timedelta(1)):
# logging.info(input_dt.date())
# Iterate all available files and check dates if necessary
for root, folders, files in os.walk(grb_ws):
root_split = os.path.normpath(root).split(os.sep)
# If the year/doy is outside the range, skip
if (re.match('\d{4}', root_split[-2])
and re.match('\d{3}', root_split[-1])):
root_dt = dt.datetime.strptime(
'{}_{}'.format(root_split[-2], root_split[-1]), '%Y_%j')
logging.info('{}'.format(root_dt.date()))
if ((start_dt is not None and root_dt < start_dt)
or (end_dt is not None and root_dt > end_dt)):
continue
elif date_list and root_dt.date().isoformat() not in date_list:
continue
# If the year is outside the range, don't search subfolders
elif re.match('\d{4}', root_split[-1]):
root_year = int(root_split[-1])
logging.info('Year: {}'.format(root_year))
if ((start_dt is not None and root_year < start_dt.year)
or (end_dt is not None and root_year > end_dt.year)):
folders[:] = []
else:
folders[:] = sorted(folders)
continue
else:
continue
# Create a single raster for each day with 24 bands
# Each time step will be stored in a separate band
output_name = output_fmt.format(root_dt.year, root_dt.month,
root_dt.day)
output_path = os.path.join(var_ws, str(root_dt.year), output_name)
logging.debug(' {}'.format(output_path))
if os.path.isfile(output_path):
if not overwrite_flag:
logging.debug(' File already exists, skipping')
continue
else:
logging.debug(' File already exists, removing existing')
os.remove(output_path)
logging.debug(' {}'.format(root))
if not os.path.isdir(os.path.dirname(output_path)):
os.makedirs(os.path.dirname(output_path))
gdc.build_empty_raster(output_path,
band_cnt=24,
output_dtype=np.float32,
output_proj=nldas_proj,
output_cs=nldas_cs,
output_extent=nldas_extent,
output_fill_flag=True)
# Iterate through hourly files
for input_name in sorted(files):
logging.info(' {}'.format(input_name))
input_path = os.path.join(root, input_name)
input_match = input_re.match(input_name)
if input_match is None:
logging.debug(' Regular expression didn\'t match, skipping')
continue
input_dt = dt.datetime(int(input_match.group('YEAR')),
int(input_match.group('MONTH')),
int(input_match.group('DAY')))
time_str = input_match.group('TIME')
band_num = int(time_str[:2]) + 1
# if start_dt is not None and input_dt < start_dt:
# continue
# elif end_dt is not None and input_dt > end_dt:
# continue
# elif date_list and input_dt.date().isoformat() not in date_list:
# continue
if time_str not in time_list:
logging.debug(' Time not in list, skipping')
continue
logging.debug(' Time: {} {}'.format(input_dt.date(), time_str))
logging.debug(' Band: {}'.format(band_num))
# Determine band numbering/naming
input_band_dict = grib_band_names(input_path)
# Compute vapour pressure from specific humidity
input_ds = gdal.Open(input_path)
sph_array = gdc.raster_ds_to_array(
input_ds,
band=input_band_dict['Specific humidity [kg/kg]'],
mask_extent=nldas_extent,
return_nodata=False)
ea_array = (sph_array * pair_array) / (0.622 + 0.378 * sph_array)
# Save the projected array as 32-bit floats
gdc.array_to_comp_raster(ea_array.astype(np.float32),
output_path,
band=band_num)
# gdc.block_to_raster(
# ea_array.astype(np.float32), output_path, band=band)
# gdc.array_to_raster(
# ea_array.astype(np.float32), output_path,
# output_geo=nldas_geo, output_proj=nldas_proj,
# stats_flag=stats_flag)
del sph_array
input_ds = None
if stats_flag:
gdc.raster_statistics(output_path)
logging.debug('\nScript Complete')
def zonal_stats(ini_path=None, overwrite_flag=False):
"""Offline Zonal Stats
Args:
ini_path (str):
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nCompute Offline Zonal Stats')
landsat_flag = True
gridmet_flag = True
pdsi_flag = False
landsat_images_folder = 'landsat'
landsat_tables_folder = 'landsat_tables'
gridmet_images_folder = 'gridmet_monthly'
# Regular expression to pull out Landsat scene_id
landsat_image_re = re.compile('^\d{8}_\d{3}_\w+.\w+.tif$')
gridmet_image_re = re.compile('^\d{6}_gridmet.(eto|ppt).tif$')
# For now, hardcode snap, cellsize and spatial reference
logging.info('\nHardcoding zone/output cellsize and snap')
zone_cs = 30
zone_x, zone_y = 15, 15
logging.debug(' Snap: {} {}'.format(zone_x, zone_y))
logging.debug(' Cellsize: {}'.format(zone_cs))
logging.info('Hardcoding Landsat snap, cellsize and spatial reference')
landsat_x, landsat_y = 15, 15
landsat_cs = 30
landsat_osr = gdc.epsg_osr(32611)
logging.debug(' Snap: {} {}'.format(landsat_x, landsat_y))
logging.debug(' Cellsize: {}'.format(landsat_cs))
logging.debug(' OSR: {}'.format(landsat_osr))
logging.info('Hardcoding GRIDMET snap, cellsize and spatial reference')
gridmet_x, gridmet_y = -124.79299639209513, 49.41685579737572
gridmet_cs = 0.041666001963701
# gridmet_cs = [0.041666001963701, 0.041666001489718]
# gridmet_x, gridmet_y = -124.79166666666666666667, 25.04166666666666666667
# gridmet_cs = 1. / 24
gridmet_osr = gdc.epsg_osr(4326)
# gridmet_osr = gdc.epsg_osr(4269)
logging.debug(' Snap: {} {}'.format(gridmet_x, gridmet_y))
logging.debug(' Cellsize: {}'.format(gridmet_cs))
logging.debug(' OSR: {}'.format(gridmet_osr))
landsat_daily_fields = [
'DATE', 'SCENE_ID', 'LANDSAT', 'PATH', 'ROW',
'YEAR', 'MONTH', 'DAY', 'DOY',
'PIXEL_COUNT', 'FMASK_COUNT', 'DATA_COUNT', 'CLOUD_SCORE',
'TS', 'ALBEDO_SUR', 'NDVI_TOA', 'NDVI_SUR', 'EVI_SUR',
'NDWI_GREEN_NIR_SUR', 'NDWI_GREEN_SWIR1_SUR', 'NDWI_NIR_SWIR1_SUR',
# 'NDWI_GREEN_NIR_TOA', 'NDWI_GREEN_SWIR1_TOA', 'NDWI_NIR_SWIR1_TOA',
# 'NDWI_SWIR1_GREEN_TOA', 'NDWI_SWIR1_GREEN_SUR',
# 'NDWI_TOA', 'NDWI_SUR',
'TC_BRIGHT', 'TC_GREEN', 'TC_WET']
# gridmet_daily_fields = [
# 'DATE', 'YEAR', 'MONTH', 'DAY', 'DOY', 'WATER_YEAR', 'ETO', 'PPT']
gridmet_monthly_fields = [
'DATE', 'YEAR', 'MONTH', 'WATER_YEAR', 'ETO', 'PPT']
pdsi_dekad_fields = [
'DATE', 'YEAR', 'MONTH', 'DAY', 'DOY', 'PDSI']
landsat_int_fields = [
'YEAR', 'MONTH', 'DAY', 'DOY',
'PIXEL_COUNT', 'FMASK_COUNT', 'CLOUD_SCORE']
gridmet_int_fields = ['YEAR', 'MONTH', 'WATER_YEAR']
# To figure out which Landsat and path,
# Compare date to reference dates and look for even multiples of 16
ref_dates = {
datetime.datetime(1985, 3, 31): ['LT5', '039'],
datetime.datetime(1985, 4, 7): ['LT5', '040'],
datetime.datetime(1999, 7, 4): ['LE7', '039'],
datetime.datetime(1999, 7, 27): ['LE7', '040'],
datetime.datetime(2013, 4, 13): ['LC8', '039'],
datetime.datetime(2013, 4, 20): ['LC8', '040']
# datetime.datetime(1984, , ): ['LT4', '039'],
# datetime.datetime(1984, , ): ['LT4', '040'],
}
# Open config file
config = ConfigParser.ConfigParser()
try:
config.readfp(open(ini_path))
except:
logging.error(('\nERROR: Input file could not be read, ' +
'is not an input file, or does not exist\n' +
'ERROR: ini_path = {}\n').format(ini_path))
sys.exit()
logging.debug('\nReading Input File')
# Read in config file
zone_input_ws = config.get('INPUTS', 'zone_input_ws')
zone_filename = config.get('INPUTS', 'zone_filename')
zone_field = config.get('INPUTS', 'zone_field')
zone_path = os.path.join(zone_input_ws, zone_filename)
landsat_daily_fields.insert(0, zone_field)
# gridmet_daily_fields.insert(0, zone_field)
gridmet_monthly_fields.insert(0, zone_field)
pdsi_dekad_fields.insert(0, zone_field)
images_ws = config.get('INPUTS', 'images_ws')
# Build and check file paths
if not os.path.isdir(zone_input_ws):
logging.error(
'\nERROR: The zone workspace does not exist, exiting\n {}'.format(
zone_input_ws))
sys.exit()
elif not os.path.isfile(zone_path):
logging.error(
'\nERROR: The zone shapefile does not exist, exiting\n {}'.format(
zone_path))
sys.exit()
elif not os.path.isdir(images_ws):
logging.error(
'\nERROR: The image workspace does not exist, exiting\n {}'.format(
images_ws))
sys.exit()
# Final output folder
try:
output_ws = config.get('INPUTS', 'output_ws')
if not os.path.isdir(output_ws):
os.makedirs(output_ws)
except:
output_ws = os.getcwd()
logging.debug(' Defaulting output workspace to {}'.format(output_ws))
# Start/end year
try:
start_year = int(config.get('INPUTS', 'start_year'))
except:
start_year = 1984
logging.debug(' Defaulting start_year={}'.format(start_year))
try:
end_year = int(config.get('INPUTS', 'end_year'))
except:
end_year = datetime.datetime.today().year
logging.debug(' Defaulting end year to {}'.format(end_year))
if start_year and end_year and end_year < start_year:
logging.error(
'\nERROR: End year must be >= start year, exiting')
sys.exit()
default_end_year = datetime.datetime.today().year + 1
if (start_year and start_year not in range(1984, default_end_year) or
end_year and end_year not in range(1984, default_end_year)):
logging.error(
('\nERROR: Year must be an integer from 1984-{}, ' +
'exiting').format(default_end_year - 1))
sys.exit()
# Start/end month
try:
start_month = int(config.get('INPUTS', 'start_month'))
except:
start_month = None
logging.debug(' Defaulting start_month=None')
try:
end_month = int(config.get('INPUTS', 'end_month'))
except:
end_month = None
logging.debug(' Defaulting end_month=None')
if start_month and start_month not in range(1, 13):
logging.error(
'\nERROR: Start month must be an integer from 1-12, exiting')
sys.exit()
elif end_month and end_month not in range(1, 13):
logging.error(
'\nERROR: End month must be an integer from 1-12, exiting')
sys.exit()
month_list = common.wrapped_range(start_month, end_month, 1, 12)
# Start/end DOY
try:
start_doy = int(config.get('INPUTS', 'start_doy'))
except:
start_doy = None
logging.debug(' Defaulting start_doy=None')
try:
end_doy = int(config.get('INPUTS', 'end_doy'))
except:
end_doy = None
logging.debug(' Defaulting end_doy=None')
if end_doy and end_doy > 273:
logging.error(
'\nERROR: End DOY must be in the same water year as start DOY, ' +
'exiting')
sys.exit()
if start_doy and start_doy not in range(1, 367):
logging.error(
'\nERROR: Start DOY must be an integer from 1-366, exiting')
sys.exit()
elif end_doy and end_doy not in range(1, 367):
logging.error(
'\nERROR: End DOY must be an integer from 1-366, exiting')
sys.exit()
# if end_doy < start_doy:
# logging.error(
# '\nERROR: End DOY must be >= start DOY')
# sys.exit()
doy_list = common.wrapped_range(start_doy, end_doy, 1, 366)
# Control which Landsat images are used
try:
landsat5_flag = config.getboolean('INPUTS', 'landsat5_flag')
except:
landsat5_flag = False
logging.debug(' Defaulting landsat5_flag=False')
try:
landsat4_flag = config.getboolean('INPUTS', 'landsat4_flag')
except:
landsat4_flag = False
logging.debug(' Defaulting landsat4_flag=False')
try:
landsat7_flag = config.getboolean('INPUTS', 'landsat7_flag')
except:
landsat7_flag = False
logging.debug(' Defaulting landsat7_flag=False')
try:
landsat8_flag = config.getboolean('INPUTS', 'landsat8_flag')
except:
landsat8_flag = False
logging.debug(' Defaulting landsat8_flag=False')
# Cloudmasking
try:
apply_mask_flag = config.getboolean('INPUTS', 'apply_mask_flag')
except:
apply_mask_flag = False
logging.debug(' Defaulting apply_mask_flag=False')
try:
acca_flag = config.getboolean('INPUTS', 'acca_flag')
except:
acca_flag = False
try:
fmask_flag = config.getboolean('INPUTS', 'fmask_flag')
except:
fmask_flag = False
# Intentionally don't apply scene_id skip/keep lists
# Compute zonal stats for all available images
# Filter by scene_id when making summary tables
scene_id_keep_list = []
scene_id_skip_list = []
# # Only process specific Landsat scenes
# try:
# scene_id_keep_path = config.get('INPUTS', 'scene_id_keep_path')
# with open(scene_id_keep_path) as input_f:
# scene_id_keep_list = input_f.readlines()
# scene_id_keep_list = [x.strip()[:16] for x in scene_id_keep_list]
# except IOError:
# logging.error('\nFileIO Error: {}'.format(scene_id_keep_path))
# sys.exit()
# except:
# scene_id_keep_list = []
# # Skip specific landsat scenes
# try:
# scene_id_skip_path = config.get('INPUTS', 'scene_id_skip_path')
# with open(scene_id_skip_path) as input_f:
# scene_id_skip_list = input_f.readlines()
# scene_id_skip_list = [x.strip()[:16] for x in scene_id_skip_list]
# except IOError:
# logging.error('\nFileIO Error: {}'.format(scene_id_skip_path))
# sys.exit()
# except:
# scene_id_skip_list = []
# Only process certain Landsat path/rows
try:
path_keep_list = list(
common.parse_int_set(config.get('INPUTS', 'path_keep_list')))
except:
path_keep_list = []
# try:
# row_keep_list = list(
# common.parse_int_set(config.get('INPUTS', 'row_keep_list')))
# except:
# row_keep_list = []
# Skip or keep certain FID
try:
fid_skip_list = list(
common.parse_int_set(config.get('INPUTS', 'fid_skip_list')))
except:
fid_skip_list = []
try:
fid_keep_list = list(
common.parse_int_set(config.get('INPUTS', 'fid_keep_list')))
except:
fid_keep_list = []
# For now, output projection must be manually set above to match zones
zone_osr = gdc.feature_path_osr(zone_path)
zone_proj = gdc.osr_proj(zone_osr)
logging.info('\nThe zone shapefile must be in a projected coordinate system!')
logging.info(' Proj4: {}'.format(zone_osr.ExportToProj4()))
logging.info('{}'.format(zone_osr))
# Read in zone shapefile
logging.info('\nRasterizing Zone Shapefile')
zone_name_dict = dict()
zone_extent_dict = dict()
zone_mask_dict = dict()
# First get FIDs and extents
zone_ds = ogr.Open(zone_path, 0)
zone_lyr = zone_ds.GetLayer()
zone_lyr.ResetReading()
for zone_ftr in zone_lyr:
zone_fid = zone_ftr.GetFID()
if zone_field.upper() == 'FID':
zone_name_dict[zone_fid] = str(zone_fid)
else:
zone_name_dict[zone_fid] = zone_ftr.GetField(zone_field)
zone_extent = gdc.Extent(
zone_ftr.GetGeometryRef().GetEnvelope()).ogrenv_swap()
zone_extent.adjust_to_snap('EXPAND', zone_x, zone_y, zone_cs)
zone_extent_dict[zone_fid] = list(zone_extent)
# Rasterize each FID separately
# The RasterizeLayer function wants a "layer"
# There might be an easier way to select each feature as a layer
for zone_fid, zone_extent in sorted(zone_extent_dict.items()):
logging.debug('FID: {}'.format(zone_fid))
logging.debug(' Name: {}'.format(zone_name_dict[zone_fid]))
zone_ds = ogr.Open(zone_path, 0)
zone_lyr = zone_ds.GetLayer()
zone_lyr.ResetReading()
zone_lyr.SetAttributeFilter("{0} = {1}".format('FID', zone_fid))
zone_extent = gdc.Extent(zone_extent)
zone_rows, zone_cols = zone_extent.shape(zone_cs)
logging.debug(' Extent: {}'.format(str(zone_extent)))
logging.debug(' Rows/Cols: {} {}'.format(zone_rows, zone_cols))
# zones_lyr.SetAttributeFilter("{0} = {1}".format('FID', zone_fid))
# Initialize the zone in memory raster
mem_driver = gdal.GetDriverByName('MEM')
zone_raster_ds = mem_driver.Create(
'', zone_cols, zone_rows, 1, gdal.GDT_Byte)
zone_raster_ds.SetProjection(zone_proj)
zone_raster_ds.SetGeoTransform(
gdc.extent_geo(zone_extent, cs=zone_cs))
zone_band = zone_raster_ds.GetRasterBand(1)
zone_band.SetNoDataValue(0)
# Clear the raster before rasterizing
zone_band.Fill(0)
gdal.RasterizeLayer(zone_raster_ds, [1], zone_lyr)
# zones_ftr_ds = None
zone_array = gdc.raster_ds_to_array(
zone_raster_ds, return_nodata=False)
zone_mask = zone_array != 0
logging.debug(' Pixel Count: {}'.format(np.sum(zone_mask)))
# logging.debug(' Mask:\n{}'.format(zone_mask))
# logging.debug(' Array:\n{}'.format(zone_array))
zone_mask_dict[zone_fid] = zone_mask
zone_raster_ds = None
del zone_raster_ds, zone_array, zone_mask
zone_ds = None
del zone_ds, zone_lyr
# Calculate zonal stats for each feature separately
logging.info('')
for fid, zone_str in sorted(zone_name_dict.items()):
if fid_keep_list and fid not in fid_keep_list:
continue
elif fid_skip_list and fid in fid_skip_list:
continue
logging.info('ZONE: {} (FID: {})'.format(zone_str, fid))
if not zone_field or zone_field.upper() == 'FID':
zone_str = 'fid_' + zone_str
else:
zone_str = zone_str.lower().replace(' ', '_')
zone_output_ws = os.path.join(output_ws, zone_str)
if not os.path.isdir(zone_output_ws):
os.makedirs(zone_output_ws)
zone_extent = gdc.Extent(zone_extent_dict[fid])
zone_mask = zone_mask_dict[fid]
# logging.debug(' Extent: {}'.format(zone_extent))
if landsat_flag:
logging.info(' Landsat')
landsat_output_ws = os.path.join(
zone_output_ws, landsat_tables_folder)
if not os.path.isdir(landsat_output_ws):
os.makedirs(landsat_output_ws)
logging.debug(' {}'.format(landsat_output_ws))
# Project the zone extent to the image OSR
clip_extent = gdc.project_extent(
zone_extent, zone_osr, landsat_osr, zone_cs)
# logging.debug(' Extent: {}'.format(clip_extent))
clip_extent.adjust_to_snap('EXPAND', landsat_x, landsat_y, landsat_cs)
logging.debug(' Extent: {}'.format(clip_extent))
# Process date range by year
for year in xrange(start_year, end_year + 1):
images_year_ws = os.path.join(
images_ws, landsat_images_folder, str(year))
if not os.path.isdir(images_year_ws):
logging.debug(
' Landsat year folder doesn\'t exist, skipping\n {}'.format(
images_year_ws))
continue
else:
logging.info(' Year: {}'.format(year))
# Create an empty dataframe
output_path = os.path.join(
landsat_output_ws, '{}_landsat_{}.csv'.format(zone_str, year))
if os.path.isfile(output_path):
if overwrite_flag:
logging.debug(
' Output CSV already exists, removing\n {}'.format(
output_path))
os.remove(output_path)
else:
logging.debug(
' Output CSV already exists, skipping\n {}'.format(
output_path))
continue
output_df = pd.DataFrame(columns=landsat_daily_fields)
output_df[landsat_int_fields] = output_df[
landsat_int_fields].astype(int)
# Get list of all images
year_image_list = [
image for image in os.listdir(images_year_ws)
if landsat_image_re.match(image)]
# Get list of all unique dates (multiple images per date)
year_dt_list = sorted(set([
datetime.datetime.strptime(image[:8], '%Y%m%d')
for image in year_image_list]))
# Filter date lists if necessary
if month_list:
year_dt_list = [
image_dt for image_dt in year_dt_list
if image_dt.month in month_list]
if doy_list:
year_dt_list = [
image_dt for image_dt in year_dt_list
if int(image_dt.strftime('%j')) in doy_list]
output_list = []
for image_dt in year_dt_list:
image_str = image_dt.date().isoformat()
logging.debug('{}'.format(image_dt.date()))
# Get the list of available images
image_list = [
image for image in year_image_list
if image_dt.strftime('%Y%m%d') in image]
# This conditional is probably impossible
if not image_list:
logging.debug(' No images, skipping date')
continue
# Use date offsets to determine the Landsat and Path
ref_match = [
lp for ref_dt, lp in ref_dates.items()
if (((ref_dt - image_dt).days % 16 == 0) and
((lp[0].upper() == 'LT5' and image_dt.year < 2012) or
(lp[0].upper() == 'LC8' and image_dt.year > 2012) or
(lp[0].upper() == 'LE7')))]
if ref_match:
landsat, path = ref_match[0]
else:
landsat, path = 'XXX', '000'
# Get Landsat type from first image in list
# image_dict['LANDSAT'] = image_list[0].split('.')[0].split('_')[2]
image_name_fmt = '{}_{}.{}.tif'.format(
image_dt.strftime('%Y%m%d_%j'), landsat.lower(), '{}')
if not landsat4_flag and landsat.upper() == 'LT4':
logging.debug(' Landsat 4, skipping image')
continue
elif not landsat5_flag and landsat.upper() == 'LT5':
logging.debug(' Landsat 5, skipping image')
continue
elif not landsat7_flag and landsat.upper() == 'LE7':
logging.debug(' Landsat 7, skipping image')
continue
elif not landsat8_flag and landsat.upper() == 'LC8':
logging.debug(' Landsat 8, skipping image')
continue
# Load the "mask" image first if it is available
# The zone_mask could be applied to the mask_array here
# or below where it is used to select from the image_array
mask_name = image_name_fmt.format('mask')
mask_path = os.path.join(images_year_ws, mask_name)
if apply_mask_flag and mask_name in image_list:
logging.info(' Applying mask raster: {}'.format(
mask_path))
mask_input_array, mask_nodata = gdc.raster_to_array(
mask_path, band=1, mask_extent=clip_extent,
fill_value=None, return_nodata=True)
mask_array = gdc.project_array(
mask_input_array, gdal.GRA_NearestNeighbour,
landsat_osr, landsat_cs, clip_extent,
zone_osr, zone_cs, zone_extent,
output_nodata=None)
# Assume 0 and nodata indicate unmasked pixels
# All other pixels are "masked"
mask_array = (mask_array == 0) | (mask_array == mask_nodata)
# Assume 0 and nodata indicate masked pixels
# mask_array = (mask_array != 0) & (mask_array != mask_nodata)
if not np.any(mask_array):
logging.info(' No unmasked values')
else:
mask_array = np.ones(zone_mask.shape, dtype=np.bool)
# Save date specific properties
image_dict = dict()
# Get Fmask and Cloud score separately from other bands
# FMask
image_name = image_name_fmt.format('fmask')
image_path = os.path.join(images_year_ws, image_name)
if not os.path.isfile(image_path):
logging.error(
' Image {} does not exist, skipping date'.format(
image_name))
continue
image_input_array, image_nodata = gdc.raster_to_array(
image_path, band=1, mask_extent=clip_extent,
fill_value=None, return_nodata=True)
fmask_array = gdc.project_array(
image_input_array, gdal.GRA_NearestNeighbour,
landsat_osr, landsat_cs, clip_extent,
zone_osr, zone_cs, zone_extent,
output_nodata=None)
fmask_mask = np.copy(zone_mask) & mask_array
if fmask_array.dtype in [np.float32, np.float64]:
fmask_mask &= np.isfinite(fmask_array)
else:
fmask_mask &= fmask_array != image_nodata
if not np.any(fmask_mask):
logging.debug(' Empty Fmask array, skipping')
continue
# Convert Fmask array into a mask (1 is cloudy, 0 is clear)
fmask_array = (fmask_array > 1.5) & (fmask_array < 4.5)
image_dict['FMASK_COUNT'] = int(np.sum(fmask_array[fmask_mask]))
image_dict['PIXEL_COUNT'] = int(np.sum(fmask_mask))
# image_dict['PIXEL_COUNT'] = int(np.sum(fmask_mask))
image_dict['MASK_COUNT'] = int(np.sum(mask_array))
# Cloud Score
image_name = image_name_fmt.format('cloud_score')
image_path = os.path.join(images_year_ws, image_name)
image_input_array, image_nodata = gdc.raster_to_array(
image_path, band=1, mask_extent=clip_extent,
fill_value=None, return_nodata=True)
cloud_array = gdc.project_array(
image_input_array, gdal.GRA_NearestNeighbour,
landsat_osr, landsat_cs, clip_extent,
zone_osr, zone_cs, zone_extent,
output_nodata=None)
cloud_mask = np.copy(zone_mask) & mask_array
if cloud_array.dtype in [np.float32, np.float64]:
cloud_mask &= np.isfinite(cloud_array)
else:
cloud_mask &= cloud_array != image_nodata
if not np.any(cloud_mask):
logging.debug(' Empty Cloud Score array, skipping')
continue
image_dict['CLOUD_SCORE'] = float(np.mean(cloud_array[cloud_mask]))
# Workflow
zs_list = [
['ts', 1, 'TS'],
['albedo_sur', 1, 'ALBEDO_SUR'],
['ndvi_toa', 1, 'NDVI_TOA'],
['ndvi_sur', 1, 'NDVI_SUR'],
['evi_sur', 1, 'EVI_SUR'],
['ndwi_green_nir_sur', 1, 'NDWI_GREEN_NIR_SUR'],
['ndwi_green_swir1_sur', 1, 'NDWI_GREEN_SWIR1_SUR'],
['ndwi_nir_swir1_sur', 1, 'NDWI_NIR_SWIR1_SUR'],
['tasseled_cap', 1, 'TC_BRIGHT'],
['tasseled_cap', 2, 'TC_GREEN'],
['tasseled_cap', 3, 'TC_WET']
]
for band_name, band_num, field in zs_list:
image_name = image_name_fmt.format(band_name)
logging.debug(' {} {}'.format(image_name, field))
if image_name not in image_list:
logging.debug(' Image doesn\'t exist, skipping')
continue
image_path = os.path.join(images_year_ws, image_name)
# logging.debug(' {}'.format(image_path))
image_input_array, image_nodata = gdc.raster_to_array(
image_path, band=band_num, mask_extent=clip_extent,
fill_value=None, return_nodata=True)
# GRA_NearestNeighbour, GRA_Bilinear, GRA_Cubic,
# GRA_CubicSpline
image_array = gdc.project_array(
image_input_array, gdal.GRA_NearestNeighbour,
landsat_osr, landsat_cs, clip_extent,
zone_osr, zone_cs, zone_extent,
output_nodata=None)
image_mask = np.copy(zone_mask) & mask_array
if image_array.dtype in [np.float32, np.float64]:
image_mask &= np.isfinite(image_array)
else:
image_mask &= image_array != image_nodata
del image_input_array
if fmask_flag:
# Fmask array was converted into a mask
# 1 for cloud, 0 for clear
image_mask &= (fmask_array == 0)
if acca_flag:
image_mask &= (cloud_array < 50)
# Skip fully masked zones
# This would not work for FMASK and CLOUD_SCORE if we
# weren't using nearest neighbor for resampling
if not np.any(image_mask):
logging.debug(' Empty array, skipping')
continue
image_dict[field] = float(np.mean(
image_array[image_mask]))
# Should check "first" image instead of Ts specifically
if band_name == 'ts':
image_dict['DATA_COUNT'] = int(np.sum(image_mask))
del image_array, image_mask
if not image_dict:
logging.debug(
' {} - no image data in zone, skipping'.format(
image_str))
continue
# Save date specific properties
# Change fid zone strings back to integer values
if zone_str.startswith('fid_'):
image_dict[zone_field] = int(zone_str[4:])
else:
image_dict[zone_field] = zone_str
image_dict['DATE'] = image_str
image_dict['LANDSAT'] = landsat.upper()
image_dict['PATH'] = path
image_dict['ROW'] = '000'
image_dict['SCENE_ID'] = '{}{}{}{}'.format(
image_dict['LANDSAT'], image_dict['PATH'],
image_dict['ROW'], image_dt.strftime('%Y%j'))
image_dict['YEAR'] = image_dt.year
image_dict['MONTH'] = image_dt.month
image_dict['DAY'] = image_dt.day
image_dict['DOY'] = int(image_dt.strftime('%j'))
# image_dict['PIXEL_COUNT'] = int(np.sum(zone_mask & mask_array))
# Save each row to a list
output_list.append(image_dict)
# Append all rows for the year to a dataframe
if not output_list:
logging.debug(' Empty output list, skipping')
continue
output_df = output_df.append(output_list, ignore_index=True)
output_df.sort_values(by=['DATE'], inplace=True)
logging.debug(' {}'.format(output_path))
output_df.to_csv(output_path, index=False, columns=landsat_daily_fields)
# Combine/merge annual files into a single CSV
logging.debug('\n Merging annual Landsat CSV files')
output_df = None
for year in xrange(start_year, end_year + 1):
# logging.debug(' {}'.format(year))
input_path = os.path.join(
landsat_output_ws, '{}_landsat_{}.csv'.format(zone_str, year))
try:
input_df = pd.read_csv(input_path)
except:
continue
try:
output_df = output_df.append(input_df)
except:
output_df = input_df.copy()
if output_df is not None and not output_df.empty:
output_path = os.path.join(
zone_output_ws,
'{}_landsat_daily.csv'.format(zone_str))
logging.debug(' {}'.format(output_path))
output_df.sort_values(by=['DATE', 'ROW'], inplace=True)
output_df.to_csv(
output_path, index=False, columns=landsat_daily_fields)
if gridmet_flag:
logging.info(' GRIDMET ETo/PPT')
# Project the zone extent to the image OSR
clip_extent = gdc.project_extent(
zone_extent, zone_osr, gridmet_osr, zone_cs)
logging.debug(' Extent: {}'.format(clip_extent))
# clip_extent.buffer_extent(gridmet_cs)
# logging.debug(' Extent: {}'.format(clip_extent))
clip_extent.adjust_to_snap('EXPAND', gridmet_x, gridmet_y, gridmet_cs)
logging.debug(' Extent: {}'.format(clip_extent))
gridmet_images_ws = os.path.join(images_ws, gridmet_images_folder)
if not os.path.isdir(gridmet_images_ws):
logging.debug(
' GRIDMET folder doesn\'t exist, skipping\n {}'.format(
gridmet_images_ws))
continue
else:
logging.info(' {}'.format(gridmet_images_ws))
# Create an empty dataframe
output_path = os.path.join(
zone_output_ws,
'{}_gridmet_monthly.csv'.format(zone_str))
if os.path.isfile(output_path):
if overwrite_flag:
logging.debug(
' Output CSV already exists, removing\n {}'.format(
output_path))
os.remove(output_path)
else:
logging.debug(
' Output CSV already exists, skipping\n {}'.format(
output_path))
continue
output_df = pd.DataFrame(columns=gridmet_monthly_fields)
output_df[gridmet_int_fields] = output_df[gridmet_int_fields].astype(int)
# Get list of all images
image_list = [
image for image in os.listdir(gridmet_images_ws)
if gridmet_image_re.match(image)]
dt_list = sorted(set([
datetime.datetime(int(image[:4]), int(image[4:6]), 1)
for image in image_list]))
output_list = []
for image_dt in dt_list:
image_str = image_dt.date().isoformat()
logging.debug('{}'.format(image_dt.date()))
image_name_fmt = '{}_gridmet.{}.tif'.format(
image_dt.strftime('%Y%m'), '{}')
# Save date specific properties
image_dict = dict()
# Workflow
zs_list = [
['eto', 'ETO'],
['ppt', 'PPT'],
]
for band_name, field in zs_list:
image_name = image_name_fmt.format(band_name)
logging.debug(' {} {}'.format(image_name, field))
if image_name not in image_list:
logging.debug(' Image doesn\'t exist, skipping')
continue
image_path = os.path.join(gridmet_images_ws, image_name)
# logging.debug(' {}'.format(image_path))
image_input_array, image_nodata = gdc.raster_to_array(
image_path, band=1, mask_extent=clip_extent,
fill_value=None, return_nodata=True)
# GRA_NearestNeighbour, GRA_Bilinear, GRA_Cubic,
# GRA_CubicSpline
image_array = gdc.project_array(
image_input_array, gdal.GRA_NearestNeighbour,
gridmet_osr, gridmet_cs, clip_extent,
zone_osr, zone_cs, zone_extent,
output_nodata=None)
del image_input_array
# Skip fully masked zones
if (np.all(np.isnan(image_array)) or
np.all(image_array == image_nodata)):
logging.debug(' Empty array, skipping')
continue
image_dict[field] = np.mean(image_array[zone_mask])
del image_array
if not image_dict:
logging.debug(
' {} - no image data in zone, skipping'.format(
image_str))
continue
# Save date specific properties
# Change fid zone strings back to integer values
if zone_str.startswith('fid_'):
image_dict[zone_field] = int(zone_str[4:])
else:
image_dict[zone_field] = zone_str
image_dict['DATE'] = image_str
image_dict['YEAR'] = image_dt.year
image_dict['MONTH'] = image_dt.month
image_dict['WATER_YEAR'] = (image_dt + relativedelta(months=3)).year
# Save each row to a list
output_list.append(image_dict)
# Append all rows for the year to a dataframe
if not output_list:
logging.debug(' Empty output list, skipping')
continue
output_df = output_df.append(output_list, ignore_index=True)
output_df.sort_values(by=['DATE'], inplace=True)
logging.debug(' {}'.format(output_path))
output_df.to_csv(
output_path, index=False, columns=gridmet_monthly_fields)
if pdsi_flag:
logging.info(' GRIDMET PDSI')
logging.info(' Not currently implemented')
def main(netcdf_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
etr_flag=False,
eto_flag=False,
start_date=None,
end_date=None,
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Compute daily ETr/ETo from GRIDMET data
Args:
netcdf_ws (str): folder of GRIDMET netcdf files
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
etr_flag (bool): if True, compute alfalfa reference ET (ETr)
eto_flag (bool): if True, compute grass reference ET (ETo)
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
extent_path (str): file path defining the output extent
output_extent (list): decimal degrees values defining output extent
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nComputing GRIDMET ETo/ETr')
np.seterr(invalid='ignore')
# Compute ETr and/or ETo
if not etr_flag and not eto_flag:
logging.info(' ETo/ETr flag(s) not set, defaulting to ETr')
etr_flag = True
# If a date is not set, process 2017
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2017, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2017, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Save GRIDMET lat, lon, and elevation arrays
elev_raster = os.path.join(ancillary_ws, 'gridmet_elev.img')
lat_raster = os.path.join(ancillary_ws, 'gridmet_lat.img')
# Wind speed is measured at 2m
zw = 10
etr_fmt = 'etr_{}_daily_gridmet.img'
eto_fmt = 'eto_{}_daily_gridmet.img'
# gridmet_re = re.compile('(?P<VAR>\w+)_(?P<YEAR>\d{4}).nc')
# GRIDMET band name dictionary
gridmet_band_dict = dict()
gridmet_band_dict['pr'] = 'precipitation_amount'
gridmet_band_dict['srad'] = 'surface_downwelling_shortwave_flux_in_air'
gridmet_band_dict['sph'] = 'specific_humidity'
gridmet_band_dict['tmmn'] = 'air_temperature'
gridmet_band_dict['tmmx'] = 'air_temperature'
gridmet_band_dict['vs'] = 'wind_speed'
# Get extent/geo from elevation raster
gridmet_ds = gdal.Open(elev_raster)
gridmet_osr = gdc.raster_ds_osr(gridmet_ds)
gridmet_proj = gdc.osr_proj(gridmet_osr)
gridmet_cs = gdc.raster_ds_cellsize(gridmet_ds, x_only=True)
gridmet_extent = gdc.raster_ds_extent(gridmet_ds)
gridmet_full_geo = gridmet_extent.geo(gridmet_cs)
gridmet_x, gridmet_y = gridmet_extent.origin()
gridmet_ds = None
logging.debug(' Projection: {}'.format(gridmet_proj))
logging.debug(' Cellsize: {}'.format(gridmet_cs))
logging.debug(' Geo: {}'.format(gridmet_full_geo))
logging.debug(' Extent: {}'.format(gridmet_extent))
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
gridmet_extent = gdc.Extent(output_extent)
gridmet_extent.adjust_to_snap('EXPAND', gridmet_x, gridmet_y,
gridmet_cs)
gridmet_geo = gridmet_extent.geo(gridmet_cs)
logging.debug(' Geo: {}'.format(gridmet_geo))
logging.debug(' Extent: {}'.format(output_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
if extent_path.lower().endswith('.shp'):
gridmet_extent = gdc.feature_path_extent(extent_path)
extent_osr = gdc.feature_path_osr(extent_path)
extent_cs = None
else:
gridmet_extent = gdc.raster_path_extent(extent_path)
extent_osr = gdc.raster_path_osr(extent_path)
extent_cs = gdc.raster_path_cellsize(extent_path, x_only=True)
gridmet_extent = gdc.project_extent(gridmet_extent, extent_osr,
gridmet_osr, extent_cs)
gridmet_extent.adjust_to_snap('EXPAND', gridmet_x, gridmet_y,
gridmet_cs)
gridmet_geo = gridmet_extent.geo(gridmet_cs)
logging.debug(' Geo: {}'.format(gridmet_geo))
logging.debug(' Extent: {}'.format(gridmet_extent))
else:
gridmet_geo = gridmet_full_geo
# Get indices for slicing/clipping input arrays
g_i, g_j = gdc.array_geo_offsets(gridmet_full_geo,
gridmet_geo,
cs=gridmet_cs)
g_rows, g_cols = gridmet_extent.shape(cs=gridmet_cs)
# Read the elevation and latitude arrays
elev_array = gdc.raster_to_array(elev_raster,
mask_extent=gridmet_extent,
return_nodata=False)
lat_array = gdc.raster_to_array(lat_raster,
mask_extent=gridmet_extent,
return_nodata=False)
lat_array *= math.pi / 180
# Check elevation and latitude arrays
if np.all(np.isnan(elev_array)):
logging.error('\nERROR: The elevation array is all nodata, exiting\n')
sys.exit()
elif np.all(np.isnan(lat_array)):
logging.error('\nERROR: The latitude array is all nodata, exiting\n')
sys.exit()
# Build output folder
etr_ws = os.path.join(output_ws, 'etr')
eto_ws = os.path.join(output_ws, 'eto')
if etr_flag and not os.path.isdir(etr_ws):
os.makedirs(etr_ws)
if eto_flag and not os.path.isdir(eto_ws):
os.makedirs(eto_ws)
# By default, try to process all possible years
if start_dt.year == end_dt.year:
year_list = [str(start_dt.year)]
year_list = sorted(map(str, range((start_dt.year), (end_dt.year + 1))))
# Process each year separately
for year_str in year_list:
logging.info("\nYear: {}".format(year_str))
year_int = int(year_str)
year_days = int(dt.datetime(year_int, 12, 31).strftime('%j'))
if start_dt is not None and year_int < start_dt.year:
logging.debug(' Before start date, skipping')
continue
elif end_dt is not None and year_int > end_dt.year:
logging.debug(' After end date, skipping')
continue
# Build input file path
tmin_path = os.path.join(netcdf_ws, 'tmmn_{}.nc'.format(year_str))
tmax_path = os.path.join(netcdf_ws, 'tmmx_{}.nc'.format(year_str))
sph_path = os.path.join(netcdf_ws, 'sph_{}.nc'.format(year_str))
rs_path = os.path.join(netcdf_ws, 'srad_{}.nc'.format(year_str))
wind_path = os.path.join(netcdf_ws, 'vs_{}.nc'.format(year_str))
# Check that all input files are present
missing_flag = False
for input_path in [tmin_path, tmax_path, sph_path, rs_path, wind_path]:
if not os.path.isfile(input_path):
logging.debug(
' Input NetCDF doesn\'t exist\n {}'.format(input_path))
missing_flag = True
if missing_flag:
logging.debug(' skipping')
continue
logging.debug(" {}".format(tmin_path))
logging.debug(" {}".format(tmax_path))
logging.debug(" {}".format(sph_path))
logging.debug(" {}".format(rs_path))
logging.debug(" {}".format(wind_path))
# Create a single raster for each year with 365 bands
# Each day will be stored in a separate band
etr_raster = os.path.join(etr_ws, etr_fmt.format(year_str))
eto_raster = os.path.join(eto_ws, eto_fmt.format(year_str))
if etr_flag and (overwrite_flag or not os.path.isfile(etr_raster)):
logging.debug(' {}'.format(etr_raster))
gdc.build_empty_raster(etr_raster,
band_cnt=366,
output_dtype=np.float32,
output_proj=gridmet_proj,
output_cs=gridmet_cs,
output_extent=gridmet_extent,
output_fill_flag=True)
if eto_flag and (overwrite_flag or not os.path.isfile(eto_raster)):
logging.debug(' {}'.format(eto_raster))
gdc.build_empty_raster(eto_raster,
band_cnt=366,
output_dtype=np.float32,
output_proj=gridmet_proj,
output_cs=gridmet_cs,
output_extent=gridmet_extent,
output_fill_flag=True)
# DEADBEEF - Need to find a way to test if both of these conditionals
# did not pass and pass logging debug message to user
# Read in the GRIDMET NetCDF file
tmin_nc_f = netCDF4.Dataset(tmin_path, 'r')
tmax_nc_f = netCDF4.Dataset(tmax_path, 'r')
sph_nc_f = netCDF4.Dataset(sph_path, 'r')
rs_nc_f = netCDF4.Dataset(rs_path, 'r')
wind_nc_f = netCDF4.Dataset(wind_path, 'r')
logging.info(' Reading NetCDFs into memory')
# Immediatly clip input arrays to save memory
tmin_nc = tmin_nc_f.variables[
gridmet_band_dict['tmmn']][:, g_i:g_i + g_cols,
g_j:g_j + g_rows].copy()
tmax_nc = tmax_nc_f.variables[
gridmet_band_dict['tmmx']][:, g_i:g_i + g_cols,
g_j:g_j + g_rows].copy()
sph_nc = sph_nc_f.variables[gridmet_band_dict['sph']][:,
g_i:g_i + g_cols,
g_j:g_j +
g_rows].copy()
rs_nc = rs_nc_f.variables[gridmet_band_dict['srad']][:,
g_i:g_i + g_cols,
g_j:g_j +
g_rows].copy()
wind_nc = wind_nc_f.variables[gridmet_band_dict['vs']][:, g_i:g_i +
g_cols,
g_j:g_j +
g_rows].copy()
# tmin_nc = tmin_nc_f.variables[gridmet_band_dict['tmmn']][:]
# tmax_nc = tmax_nc_f.variables[gridmet_band_dict['tmmx']][:]
# sph_nc = sph_nc_f.variables[gridmet_band_dict['sph']][:]
# rs_nc = rs_nc_f.variables[gridmet_band_dict['srad']][:]
# wind_nc = wind_nc_f.variables[gridmet_band_dict['vs']][:]
# Transpose arrays back to row x col
tmin_nc = np.transpose(tmin_nc, (0, 2, 1))
tmax_nc = np.transpose(tmax_nc, (0, 2, 1))
sph_nc = np.transpose(sph_nc, (0, 2, 1))
rs_nc = np.transpose(rs_nc, (0, 2, 1))
wind_nc = np.transpose(wind_nc, (0, 2, 1))
# A numpy array is returned when slicing a masked array
# if there are no masked pixels
# This is a hack to force the numpy array back to a masked array
# For now assume all arrays need to be converted
if type(tmin_nc) != np.ma.core.MaskedArray:
tmin_nc = np.ma.core.MaskedArray(
tmin_nc, np.zeros(tmin_nc.shape, dtype=bool))
if type(tmax_nc) != np.ma.core.MaskedArray:
tmax_nc = np.ma.core.MaskedArray(
tmax_nc, np.zeros(tmax_nc.shape, dtype=bool))
if type(sph_nc) != np.ma.core.MaskedArray:
sph_nc = np.ma.core.MaskedArray(sph_nc,
np.zeros(sph_nc.shape, dtype=bool))
if type(rs_nc) != np.ma.core.MaskedArray:
rs_nc = np.ma.core.MaskedArray(rs_nc,
np.zeros(rs_nc.shape, dtype=bool))
if type(wind_nc) != np.ma.core.MaskedArray:
wind_nc = np.ma.core.MaskedArray(
wind_nc, np.zeros(wind_nc.shape, dtype=bool))
# Check all valid dates in the year
year_dates = date_range(dt.datetime(year_int, 1, 1),
dt.datetime(year_int + 1, 1, 1))
for date_dt in year_dates:
if start_dt is not None and date_dt < start_dt:
logging.debug(' {} - before start date, skipping'.format(
date_dt.date()))
continue
elif end_dt is not None and date_dt > end_dt:
logging.debug(' {} - after end date, skipping'.format(
date_dt.date()))
continue
else:
logging.info(' {}'.format(date_dt.date()))
doy = int(date_dt.strftime('%j'))
doy_i = range(1, year_days + 1).index(doy)
# Arrays are being read as masked array with a fill value of -9999
# Convert to basic numpy array arrays with nan values
try:
tmin_ma = tmin_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
tmin_array = tmin_ma.data.astype(np.float32)
tmin_nodata = float(tmin_ma.fill_value)
tmin_array[tmin_array == tmin_nodata] = np.nan
try:
tmax_ma = tmax_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
tmax_array = tmax_ma.data.astype(np.float32)
tmax_nodata = float(tmax_ma.fill_value)
tmax_array[tmax_array == tmax_nodata] = np.nan
try:
sph_ma = sph_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
sph_array = sph_ma.data.astype(np.float32)
sph_nodata = float(sph_ma.fill_value)
sph_array[sph_array == sph_nodata] = np.nan
try:
rs_ma = rs_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
rs_array = rs_ma.data.astype(np.float32)
rs_nodata = float(rs_ma.fill_value)
rs_array[rs_array == rs_nodata] = np.nan
try:
wind_ma = wind_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
wind_array = wind_ma.data.astype(np.float32)
wind_nodata = float(wind_ma.fill_value)
wind_array[wind_array == wind_nodata] = np.nan
del tmin_ma, tmax_ma, sph_ma, rs_ma, wind_ma
# Since inputs are netcdf, need to create GDAL raster
# datasets in order to use gdal_common functions
# Create an in memory dataset of the full ETo array
tmin_ds = gdc.array_to_mem_ds(
tmin_array,
output_geo=gridmet_geo,
# tmin_array, output_geo=gridmet_full_geo,
output_proj=gridmet_proj)
tmax_ds = gdc.array_to_mem_ds(
tmax_array,
output_geo=gridmet_geo,
# tmax_array, output_geo=gridmet_full_geo,
output_proj=gridmet_proj)
sph_ds = gdc.array_to_mem_ds(
sph_array,
output_geo=gridmet_geo,
# sph_array, output_geo=gridmet_full_geo,
output_proj=gridmet_proj)
rs_ds = gdc.array_to_mem_ds(
rs_array,
output_geo=gridmet_geo,
# rs_array, output_geo=gridmet_full_geo,
output_proj=gridmet_proj)
wind_ds = gdc.array_to_mem_ds(
wind_array,
output_geo=gridmet_geo,
# wind_array, output_geo=gridmet_full_geo,
output_proj=gridmet_proj)
# Then extract the subset from the in memory dataset
tmin_array = gdc.raster_ds_to_array(tmin_ds,
1,
mask_extent=gridmet_extent,
return_nodata=False)
tmax_array = gdc.raster_ds_to_array(tmax_ds,
1,
mask_extent=gridmet_extent,
return_nodata=False)
sph_array = gdc.raster_ds_to_array(sph_ds,
1,
mask_extent=gridmet_extent,
return_nodata=False)
rs_array = gdc.raster_ds_to_array(rs_ds,
1,
mask_extent=gridmet_extent,
return_nodata=False)
wind_array = gdc.raster_ds_to_array(wind_ds,
1,
mask_extent=gridmet_extent,
return_nodata=False)
del tmin_ds, tmax_ds, sph_ds, rs_ds, wind_ds
# Adjust units
tmin_array -= 273.15
tmax_array -= 273.15
rs_array *= 0.0864
# ETr/ETo
if etr_flag:
etr_array = et_common.refet_daily_func(tmin_array, tmax_array,
sph_array, rs_array,
wind_array, zw,
elev_array, lat_array,
doy, 'ETR')
if eto_flag:
eto_array = et_common.refet_daily_func(tmin_array, tmax_array,
sph_array, rs_array,
wind_array, zw,
elev_array, lat_array,
doy, 'ETO')
# del tmin_array, tmax_array, sph_array, rs_array, wind_array
# Save the projected array as 32-bit floats
if etr_flag:
gdc.array_to_comp_raster(etr_array.astype(np.float32),
etr_raster,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# etr_array.astype(np.float32), etr_raster,
# output_geo=gridmet_geo, output_proj=gridmet_proj,
# stats_flag=stats_flag)
del etr_array
if eto_flag:
gdc.array_to_comp_raster(eto_array.astype(np.float32),
eto_raster,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# eto_array.astype(np.float32), eto_raster,
# output_geo=gridmet_geo, output_proj=gridmet_proj,
# stats_flag=stats_flag)
del eto_array
del tmin_nc
del tmax_nc
del sph_nc
del rs_nc
del wind_nc
tmin_nc_f.close()
tmax_nc_f.close()
sph_nc_f.close()
rs_nc_f.close()
wind_nc_f.close()
del tmin_nc_f, tmax_nc_f, sph_nc_f, rs_nc_f, wind_nc_f
if stats_flag and etr_flag:
gdc.raster_statistics(etr_raster)
if stats_flag and eto_flag:
gdc.raster_statistics(eto_raster)
logging.debug('\nScript Complete')
def main(netcdf_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
variables=['prcp'],
daily_flag=False,
monthly_flag=True,
annual_flag=False,
start_year=1981,
end_year=2010,
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Extract DAYMET temperature
Args:
netcdf_ws (str): folder of DAYMET netcdf files
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
variables (list): DAYMET variables to download
('prcp', 'srad', 'vp', 'tmmn', 'tmmx')
Set as ['all'] to process all variables
daily_flag (bool): if True, compute daily (DOY) climatologies
monthly_flag (bool): if True, compute monthly climatologies
annual_flag (bool): if True, compute annual climatologies
start_year (int): YYYY
end_year (int): YYYY
extent_path (str): filepath a raster defining the output extent
output_extent (list): decimal degrees values defining output extent
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): if True, overwrite existing files
Returns:
None
"""
logging.info('\nGenerating DAYMET climatologies')
daily_fmt = 'daymet_{var}_30yr_normal_{doy:03d}.img'
monthly_fmt = 'daymet_{var}_30yr_normal_{month:02d}.img'
annual_fmt = 'daymet_{var}_30yr_normal.img'
# daily_fmt = 'daymet_{var}_normal_{start}_{end}_{doy:03d}.img'
# monthly_fmt = 'daymet_{var}_normal_{start}_{end}_{month:02d}.img'
# annual_fmt = 'daymet_{var}_normal_{start}_{end}.img'
# If a date is not set, process 1981-2010 climatology
try:
start_dt = dt.datetime(start_year, 1, 1)
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(1981, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime(end_year, 12, 31)
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2010, 12, 31)
logging.info(' End date: {}'.format(end_dt))
# Get DAYMET spatial reference from an ancillary raster
mask_raster = os.path.join(ancillary_ws, 'daymet_mask.img')
daymet_re = re.compile('daymet_v3_(?P<VAR>\w+)_(?P<YEAR>\d{4})_na.nc4$')
# DAYMET rasters to extract
var_full_list = ['prcp', 'tmmn', 'tmmx']
# data_full_list = ['prcp', 'srad', 'vp', 'tmmn', 'tmmx']
if not variables:
logging.error('\nERROR: variables parameter is empty\n')
sys.exit()
elif type(variables) is not list:
# DEADBEEF - I could try converting comma separated strings to lists?
logging.warning('\nERROR: variables parameter must be a list\n')
sys.exit()
elif 'all' in variables:
logging.error('\nDownloading all variables\n {}'.format(
','.join(var_full_list)))
var_list = var_full_list[:]
elif not set(variables).issubset(set(var_full_list)):
logging.error(
'\nERROR: variables parameter is invalid\n {}'.format(variables))
sys.exit()
else:
var_list = variables[:]
# Get extent/geo from mask raster
daymet_ds = gdal.Open(mask_raster)
daymet_osr = gdc.raster_ds_osr(daymet_ds)
daymet_proj = gdc.osr_proj(daymet_osr)
daymet_cs = gdc.raster_ds_cellsize(daymet_ds, x_only=True)
daymet_extent = gdc.raster_ds_extent(daymet_ds)
daymet_geo = daymet_extent.geo(daymet_cs)
daymet_x, daymet_y = daymet_extent.origin()
daymet_ds = None
logging.debug(' Projection: {}'.format(daymet_proj))
logging.debug(' Cellsize: {}'.format(daymet_cs))
logging.debug(' Geo: {}'.format(daymet_geo))
logging.debug(' Extent: {}'.format(daymet_extent))
logging.debug(' Origin: {} {}'.format(daymet_x, daymet_y))
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
# Assume input extent is in decimal degrees
output_extent = gdc.project_extent(gdc.Extent(output_extent),
gdc.epsg_osr(4326), daymet_osr,
0.001)
output_extent = gdc.intersect_extents([daymet_extent, output_extent])
output_extent.adjust_to_snap('EXPAND', daymet_x, daymet_y, daymet_cs)
output_geo = output_extent.geo(daymet_cs)
logging.debug(' Geo: {}'.format(output_geo))
logging.debug(' Extent: {}'.format(output_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
output_extent = gdc.project_extent(
gdc.raster_path_extent(extent_path),
gdc.raster_path_osr(extent_path), daymet_osr,
gdc.raster_path_cellsize(extent_path, x_only=True))
output_extent = gdc.intersect_extents([daymet_extent, output_extent])
output_extent.adjust_to_snap('EXPAND', daymet_x, daymet_y, daymet_cs)
output_geo = output_extent.geo(daymet_cs)
logging.debug(' Geo: {}'.format(output_geo))
logging.debug(' Extent: {}'.format(output_extent))
else:
output_extent = daymet_extent.copy()
output_geo = daymet_geo[:]
output_shape = output_extent.shape(cs=daymet_cs)
xi, yi = gdc.array_geo_offsets(daymet_geo, output_geo, daymet_cs)
output_rows, output_cols = output_extent.shape(daymet_cs)
logging.debug(' Shape: {} {}'.format(output_rows, output_cols))
logging.debug(' Offsets: {} {} (x y)'.format(xi, yi))
# Process each variable
for input_var in var_list:
logging.info("\nVariable: {}".format(input_var))
# Rename variables to match cimis
if input_var == 'prcp':
output_var = 'ppt'
else:
output_var = input_var
logging.debug("Output name: {}".format(output_var))
# Build output folder
var_ws = os.path.join(output_ws, output_var)
if not os.path.isdir(var_ws):
os.makedirs(var_ws)
# Build output arrays
logging.debug(' Building arrays')
if daily_flag:
daily_sum = np.full((365, output_shape[0], output_shape[1]), 0,
np.float64)
daily_count = np.full((365, output_shape[0], output_shape[1]), 0,
np.uint8)
if monthly_flag:
monthly_sum = np.full((12, output_shape[0], output_shape[1]), 0,
np.float64)
monthly_count = np.full((12, output_shape[0], output_shape[1]), 0,
np.uint8)
if monthly_flag:
annual_sum = np.full((output_shape[0], output_shape[1]), 0,
np.float64)
annual_count = np.full((output_shape[0], output_shape[1]), 0,
np.uint8)
# Process each file/year separately
for input_name in sorted(os.listdir(netcdf_ws)):
logging.debug(" {}".format(input_name))
input_match = daymet_re.match(input_name)
if not input_match:
logging.debug(' Regular expression didn\'t match, skipping')
continue
elif input_match.group('VAR') != input_var:
logging.debug(' Variable didn\'t match, skipping')
continue
year_str = input_match.group('YEAR')
logging.info(" Year: {}".format(year_str))
year_int = int(year_str)
year_days = int(dt.datetime(year_int, 12, 31).strftime('%j'))
if start_dt is not None and year_int < start_dt.year:
logging.debug(' Before start date, skipping')
continue
elif end_dt is not None and year_int > end_dt.year:
logging.debug(' After end date, skipping')
continue
# Build input file path
input_raster = os.path.join(netcdf_ws, input_name)
if not os.path.isfile(input_raster):
logging.debug(
' Input raster doesn\'t exist, skipping {}'.format(
input_raster))
continue
# Build output folder
if daily_flag:
daily_ws = os.path.join(var_ws, 'daily')
if not os.path.isdir(daily_ws):
os.makedirs(daily_ws)
if monthly_flag:
monthly_temp_sum = np.full(
(12, output_shape[0], output_shape[1]), 0, np.float64)
monthly_temp_count = np.full(
(12, output_shape[0], output_shape[1]), 0, np.uint8)
# Read in the DAYMET NetCDF file
input_nc_f = netCDF4.Dataset(input_raster, 'r')
# logging.debug(input_nc_f.variables)
# Check all valid dates in the year
year_dates = date_range(dt.datetime(year_int, 1, 1),
dt.datetime(year_int + 1, 1, 1))
for date_dt in year_dates:
logging.debug(' {}'.format(date_dt.date()))
# if start_dt is not None and date_dt < start_dt:
# logging.debug(
# ' {} - before start date, skipping'.format(
# date_dt.date()))
# continue
# elif end_dt is not None and date_dt > end_dt:
# logging.debug(' {} - after end date, skipping'.format(
# date_dt.date()))
# continue
# else:
# logging.info(' {}'.format(date_dt.date()))
doy = int(date_dt.strftime('%j'))
doy_i = range(1, year_days + 1).index(doy)
month_i = date_dt.month - 1
# Arrays are being read as masked array with a -9999 fill value
# Convert to basic numpy array arrays with nan values
try:
input_ma = input_nc_f.variables[input_var][doy_i, yi:yi +
output_rows,
xi:xi +
output_cols]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
input_nodata = float(input_ma.fill_value)
output_array = input_ma.data.astype(np.float32)
output_array[output_array == input_nodata] = np.nan
output_mask = np.isfinite(output_array)
# Convert Kelvin to Celsius
if input_var in ['tmax', 'tmin']:
output_array -= 273.15
# Save values
if daily_flag:
daily_sum[doy_i, :, :] += output_array
daily_count[doy_i, :, :] += output_mask
if monthly_flag:
monthly_temp_sum[month_i, :, :] += output_array
monthly_temp_count[month_i, :, :] += output_mask
if annual_flag:
annual_sum[:, :] += output_array
annual_count[:, :] += output_mask
# Cleanup
# del input_ds, input_array
del input_ma, output_array, output_mask
# Compute mean monthly for the year
if monthly_flag:
# Sum precipitation
if input_var == 'prcp':
monthly_sum += monthly_temp_sum
else:
monthly_sum += monthly_temp_sum / monthly_temp_count
# Is this the right count?
monthly_count += np.any(monthly_temp_count, axis=0)
del monthly_temp_sum, monthly_temp_count
input_nc_f.close()
del input_nc_f
# Save the projected climatology arrays
if daily_flag:
for doy_i in range(daily_sum.shape[0]):
daily_name = daily_fmt.format(var=output_var,
start=start_year,
end=end_year,
doy=doy_i + 1)
daily_path = os.path.join(daily_ws, daily_name)
gdc.array_to_raster(daily_sum[doy_i, :, :] /
daily_count[doy_i, :, :],
daily_path,
output_geo=output_geo,
output_proj=daymet_proj,
stats_flag=stats_flag)
del daily_sum, daily_count
if monthly_flag:
for month_i in range(monthly_sum.shape[0]):
monthly_name = monthly_fmt.format(var=output_var,
start=start_year,
end=end_year,
month=month_i + 1)
monthly_path = os.path.join(var_ws, monthly_name)
gdc.array_to_raster(monthly_sum[month_i, :, :] /
monthly_count[month_i, :, :],
monthly_path,
output_geo=output_geo,
output_proj=daymet_proj,
stats_flag=stats_flag)
del monthly_sum, monthly_count
if annual_flag:
annual_name = annual_fmt.format(var=output_var,
start=start_year,
end=end_year)
annual_path = os.path.join(var_ws, annual_name)
gdc.array_to_raster(annual_sum / annual_count,
annual_path,
output_geo=output_geo,
output_proj=daymet_proj,
stats_flag=stats_flag)
del annual_sum, annual_count
logging.debug('\nScript Complete')
def main(img_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
etr_flag=False,
eto_flag=False,
start_date=None,
end_date=None,
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False,
use_cimis_eto_flag=False):
"""Compute daily ETr/ETo from CIMIS data
Args:
img_ws (str): root folder of GRIDMET data
ancillary_ws (str): folder of ancillary rasters
output_ws (str): folder of output rasters
etr_flag (bool): if True, compute alfalfa reference ET (ETr)
eto_flag (bool): if True, compute grass reference ET (ETo)
start_date (str): ISO format date (YYYY-MM-DD)
end_date (str): ISO format date (YYYY-MM-DD)
extent_path (str): file path defining the output extent
output_extent (list): decimal degrees values defining output extent
stats_flag (bool): if True, compute raster statistics.
Default is True.
overwrite_flag (bool): If True, overwrite existing files
use_cimis_eto_flag (bool): if True, use CIMIS ETo raster if one of
the component rasters is missing and ETo/ETr cannot be computed
Returns:
None
"""
logging.info('\nComputing CIMIS ETo/ETr')
np.seterr(invalid='ignore')
# Use CIMIS ETo raster directly instead of computing from components
# Currently this will only be applied if one of the inputs is missing
use_cimis_eto_flag = True
# Compute ETr and/or ETo
if not etr_flag and not eto_flag:
logging.info(' ETo/ETr flag(s) not set, defaulting to ETr')
etr_flag = True
# If a date is not set, process 2017
try:
start_dt = dt.datetime.strptime(start_date, '%Y-%m-%d')
logging.debug(' Start date: {}'.format(start_dt))
except:
start_dt = dt.datetime(2017, 1, 1)
logging.info(' Start date: {}'.format(start_dt))
try:
end_dt = dt.datetime.strptime(end_date, '%Y-%m-%d')
logging.debug(' End date: {}'.format(end_dt))
except:
end_dt = dt.datetime(2017, 12, 31)
logging.info(' End date: {}'.format(end_dt))
etr_folder = 'etr'
eto_folder = 'eto'
etr_fmt = 'etr_{}_daily_cimis.img'
eto_fmt = 'eto_{}_daily_cimis.img'
# DEM for air pressure calculation
mask_raster = os.path.join(ancillary_ws, 'cimis_mask.img')
dem_raster = os.path.join(ancillary_ws, 'cimis_elev.img')
lat_raster = os.path.join(ancillary_ws, 'cimis_lat.img')
# lon_raster = os.path.join(ancillary_ws, 'cimis_lon.img')
# Interpolate zero windspeed pixels
# interpolate_zero_u2_flag = False
# Interpolate edge and coastal cells
# interpolate_edge_flag = False
# Resample type
# 0 = GRA_NearestNeighbour, Nearest neighbour (select on one input pixel)
# 1 = GRA_Bilinear,Bilinear (2x2 kernel)
# 2 = GRA_Cubic, Cubic Convolution Approximation (4x4 kernel)
# 3 = GRA_CubicSpline, Cubic B-Spline Approximation (4x4 kernel)
# 4 = GRA_Lanczos, Lanczos windowed sinc interpolation (6x6 kernel)
# 5 = GRA_Average, Average (computes the average of all non-NODATA contributing pixels)
# 6 = GRA_Mode, Mode (selects the value which appears most often of all the sampled points)
resample_type = gdal.GRA_CubicSpline
# Wind speed is measured at 2m
zw = 2
# Output workspaces
etr_ws = os.path.join(output_ws, etr_folder)
eto_ws = os.path.join(output_ws, eto_folder)
if etr_flag and not os.path.isdir(etr_ws):
os.makedirs(etr_ws)
if eto_flag and not os.path.isdir(eto_ws):
os.makedirs(eto_ws)
# Check ETr/ETo functions
test_flag = False
# Check that the daily_refet_func produces the correct values
if test_flag:
doy_test = 245
elev_test = 1050.0
lat_test = 39.9396 * math.pi / 180
tmin_test = 11.07
tmax_test = 34.69
rs_test = 22.38
u2_test = 1.94
zw_test = 2.5
tdew_test = -3.22
ea_test = et_common.saturation_vapor_pressure_func(tdew_test)
pair_test = 101.3 * np.power((285 - 0.0065 * elev_test) / 285, 5.26)
q_test = 0.622 * ea_test / (pair_test - (0.378 * ea_test))
etr = float(
et_common.daily_refet_func(tmin_test, tmax_test, q_test, rs_test,
u2_test, zw_test, elev_test, doy_test,
lat_test, 'ETR'))
eto = float(
et_common.daily_refet_func(tmin_test, tmax_test, q_test, rs_test,
u2_test, zw_test, elev_test, doy_test,
lat_test, 'ETO'))
print('ETr: 8.89', etr)
print('ETo: 6.16', eto)
sys.exit()
# Get CIMIS grid properties from mask
cimis_mask_ds = gdal.Open(mask_raster)
cimis_osr = gdc.raster_ds_osr(cimis_mask_ds)
cimis_proj = gdc.osr_proj(cimis_osr)
cimis_cs = gdc.raster_ds_cellsize(cimis_mask_ds, x_only=True)
cimis_extent = gdc.raster_ds_extent(cimis_mask_ds)
cimis_full_geo = cimis_extent.geo(cimis_cs)
cimis_x, cimis_y = cimis_extent.origin()
cimis_mask_ds = None
logging.debug(' Projection: {}'.format(cimis_proj))
logging.debug(' Cellsize: {}'.format(cimis_cs))
logging.debug(' Geo: {}'.format(cimis_full_geo))
logging.debug(' Extent: {}'.format(cimis_extent))
# Manually set CIMIS grid properties
# cimis_extent = gdc.Extent((-400000, -650000, 600000, 454000))
# cimis_cs = 2000
# cimis_geo = gdc.extent_geo(cimis_extent, cellsize)
# cimis_epsg = 3310 # NAD_1983_California_Teale_Albers
# cimis_x, cimis_y = (0,0)
# Subset data to a smaller extent
if output_extent is not None:
logging.info('\nComputing subset extent & geo')
logging.debug(' Extent: {}'.format(output_extent))
cimis_extent = gdc.Extent(output_extent)
cimis_extent.adjust_to_snap('EXPAND', cimis_x, cimis_y, cimis_cs)
cimis_geo = cimis_extent.geo(cimis_cs)
logging.debug(' Geo: {}'.format(cimis_geo))
logging.debug(' Extent: {}'.format(output_extent))
elif extent_path is not None:
logging.info('\nComputing subset extent & geo')
if extent_path.lower().endswith('.shp'):
cimis_extent = gdc.feature_path_extent(extent_path)
extent_osr = gdc.feature_path_osr(extent_path)
extent_cs = None
else:
cimis_extent = gdc.raster_path_extent(extent_path)
extent_osr = gdc.raster_path_osr(extent_path)
extent_cs = gdc.raster_path_cellsize(extent_path, x_only=True)
cimis_extent = gdc.project_extent(cimis_extent, extent_osr, cimis_osr,
extent_cs)
cimis_extent.adjust_to_snap('EXPAND', cimis_x, cimis_y, cimis_cs)
cimis_geo = cimis_extent.geo(cimis_cs)
logging.debug(' Geo: {}'.format(cimis_geo))
logging.debug(' Extent: {}'.format(cimis_extent))
else:
cimis_geo = cimis_full_geo
# Latitude
lat_array = gdc.raster_to_array(lat_raster,
mask_extent=cimis_extent,
return_nodata=False)
lat_array = lat_array.astype(np.float32)
lat_array *= math.pi / 180
# Elevation data
elev_array = gdc.raster_to_array(dem_raster,
mask_extent=cimis_extent,
return_nodata=False)
elev_array = elev_array.astype(np.float32)
# Process each year in the input workspace
logging.info("")
for year_str in sorted(os.listdir(img_ws)):
logging.debug('{}'.format(year_str))
if not re.match('^\d{4}$', year_str):
logging.debug(' Not a 4 digit year folder, skipping')
continue
year_ws = os.path.join(img_ws, year_str)
year_int = int(year_str)
# year_days = int(dt.datetime(year_int, 12, 31).strftime('%j'))
if start_dt is not None and year_int < start_dt.year:
logging.debug(' Before start date, skipping')
continue
elif end_dt is not None and year_int > end_dt.year:
logging.debug(' After end date, skipping')
continue
logging.info('{}'.format(year_str))
# Output paths
etr_raster = os.path.join(etr_ws, etr_fmt.format(year_str))
eto_raster = os.path.join(eto_ws, eto_fmt.format(year_str))
if etr_flag and (overwrite_flag or not os.path.isfile(etr_raster)):
logging.debug(' {}'.format(etr_raster))
gdc.build_empty_raster(etr_raster,
band_cnt=366,
output_dtype=np.float32,
output_proj=cimis_proj,
output_cs=cimis_cs,
output_extent=cimis_extent,
output_fill_flag=True)
if eto_flag and (overwrite_flag or not os.path.isfile(eto_raster)):
logging.debug(' {}'.format(eto_raster))
gdc.build_empty_raster(eto_raster,
band_cnt=366,
output_dtype=np.float32,
output_proj=cimis_proj,
output_cs=cimis_cs,
output_extent=cimis_extent,
output_fill_flag=True)
# Process each date in the year
for date_str in sorted(os.listdir(year_ws)):
logging.debug('{}'.format(date_str))
try:
date_dt = dt.datetime.strptime(date_str, '%Y_%m_%d')
except ValueError:
logging.debug(
' Invalid folder date format (YYYY_MM_DD), skipping')
continue
if start_dt is not None and date_dt < start_dt:
logging.debug(' Before start date, skipping')
continue
elif end_dt is not None and date_dt > end_dt:
logging.debug(' After end date, skipping')
continue
logging.info(date_str)
date_ws = os.path.join(year_ws, date_str)
doy = int(date_dt.strftime('%j'))
# Set file paths
tmax_path = os.path.join(date_ws, 'Tx.img')
tmin_path = os.path.join(date_ws, 'Tn.img')
tdew_path = os.path.join(date_ws, 'Tdew.img')
rso_path = os.path.join(date_ws, 'Rso.img')
rs_path = os.path.join(date_ws, 'Rs.img')
u2_path = os.path.join(date_ws, 'U2.img')
eto_path = os.path.join(date_ws, 'ETo.img')
# k_path = os.path.join(date_ws, 'K.img')
# rnl_path = os.path.join(date_ws, 'Rnl.img')
input_list = [
tmin_path, tmax_path, tdew_path, u2_path, rs_path, rso_path
]
# If any input raster is missing, skip the day
# Unless ETo is present (and use_cimis_eto_flag is True)
day_skip_flag = False
for t_path in input_list:
if not os.path.isfile(t_path):
logging.info(' {} is missing'.format(t_path))
day_skip_flag = True
if (day_skip_flag and use_cimis_eto_flag
and os.path.isfile(eto_path)):
logging.info(' Using CIMIS ETo directly')
eto_array = gdc.raster_to_array(eto_path,
1,
cimis_extent,
return_nodata=False)
eto_array = eto_array.astype(np.float32)
if not np.any(eto_array):
logging.info(' {} is empty or missing'.format(eto_path))
logging.info(' Skipping date')
continue
# ETr
if etr_flag:
gdc.array_to_comp_raster(1.2 * eto_array,
etr_raster,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# 1.2 * eto_array, etr_raster,
# output_geo=cimis_geo, output_proj=cimis_proj,
# stats_flag=stats_flag)
# ETo
if eto_flag:
gdc.array_to_comp_raster(eto_array,
eto_raster,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# eto_array, eto_raster,
# output_geo=cimis_geo, output_proj=cimis_proj,
# stats_flag=stats_flag)
del eto_array
continue
elif not day_skip_flag:
# Read in rasters
# DEADBEEF - Read with extent since some arrays are too big
# i.e. 2012-03-21, 2013-03-20, 2014-02-27
tmin_array = gdc.raster_to_array(tmin_path,
1,
cimis_extent,
return_nodata=False)
tmax_array = gdc.raster_to_array(tmax_path,
1,
cimis_extent,
return_nodata=False)
tdew_array = gdc.raster_to_array(tdew_path,
1,
cimis_extent,
return_nodata=False)
rso_array = gdc.raster_to_array(rso_path,
1,
cimis_extent,
return_nodata=False)
rs_array = gdc.raster_to_array(rs_path,
1,
cimis_extent,
return_nodata=False)
u2_array = gdc.raster_to_array(u2_path,
1,
cimis_extent,
return_nodata=False)
# k_array = gdc.raster_to_array(
# k_path, 1, cimis_extent, return_nodata=False)
# rnl_array = gdc.raster_to_array(
# rnl_path, 1, cimis_extent, return_nodata=False)
# Check that all input arrays have data
for t_name, t_array in [[tmin_path, tmin_array],
[tmax_path, tmax_array],
[tdew_path, tdew_array],
[u2_path, u2_array],
[rs_path, rs_array]]:
if not np.any(t_array):
logging.warning(
' {} is empty or missing'.format(t_name))
day_skip_flag = True
if day_skip_flag:
logging.warning(' Skipping date')
continue
# DEADBEEF - Some arrays have a 500m cellsize
# i.e. 2011-07-25, 2010-01-01 -> 2010-07-27
tmin_array = rescale_array_func(tmin_array, elev_array, 'tmin')
tmax_array = rescale_array_func(tmax_array, elev_array, 'tmax')
tdew_array = rescale_array_func(tdew_array, elev_array, 'tdew')
rso_array = rescale_array_func(rso_array, elev_array, 'rso')
rs_array = rescale_array_func(rs_array, elev_array, 'rs')
u2_array = rescale_array_func(u2_array, elev_array, 'u2')
# k_array = rescale_array_func(k_array, elev_array, 'k')
# rnl_array = rescale_array_func(rnl_array, elev_array, 'rnl')
# Back calculate q from tdew by first calculating ea from tdew
es_array = et_common.saturation_vapor_pressure_func(tdew_array)
pair_array = et_common.air_pressure_func(elev_array)
q_array = 0.622 * es_array / (pair_array - (0.378 * es_array))
del es_array, pair_array, tdew_array
# Back calculate rhmin/rhmax from tdew
# ea_tmax = et_common.saturation_vapor_pressure_func(tmax_array)
# ea_tmin = et_common.saturation_vapor_pressure_func(tmin_array)
# rhmin = ea_tdew * 2 / (ea_tmax + ea_tmin);
# rhmax = ea_tdew * 2 / (ea_tmax + ea_tmin);
# del ea_tmax, ea_tmin
# ETr
if etr_flag:
etr_array = et_common.refet_daily_func(tmin_array,
tmax_array,
q_array,
rs_array,
u2_array,
zw,
elev_array,
lat_array,
doy,
ref_type='ETR',
rso_type='ARRAY',
rso=rso_array)
gdc.array_to_comp_raster(etr_array.astype(np.float32),
etr_raster,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# etr_array.astype(np.float32), etr_raster,
# output_geo=cimis_geo, output_proj=cimis_proj,
# stats_flag=stats_flag)
del etr_array
# ETo
if eto_flag:
eto_array = et_common.refet_daily_func(tmin_array,
tmax_array,
q_array,
rs_array,
u2_array,
zw,
elev_array,
lat_array,
doy,
ref_type='ETO',
rso_type='ARRAY',
rso=rso_array)
gdc.array_to_comp_raster(eto_array.astype(np.float32),
eto_raster,
band=doy,
stats_flag=False)
# gdc.array_to_raster(
# eto_array.astype(np.float32), eto_raster,
# output_geo=cimis_geo, output_proj=cimis_proj,
# stats_flag=stats_flag)
del eto_array
# Cleanup
del tmin_array, tmax_array, u2_array, rs_array, q_array
# del rnl, rs, rso
else:
logging.info(' Skipping date')
continue
if stats_flag and etr_flag:
gdc.raster_statistics(etr_raster)
if stats_flag and eto_flag:
gdc.raster_statistics(eto_raster)
logging.debug('\nScript Complete')
