def main(start_dt, end_dt, netcdf_ws, ancillary_ws, output_ws,
variables=['etr', 'pr'], extent_path=None, output_extent=None,
stats_flag=True, overwrite_flag=False):
"""Extract GRIDMET temperature
Parameters
----------
start_dt : datetime
Start date.
end_dt : datetime
End date.
netcdf_ws : str
Folder of GRIDMET netcdf files.
ancillary_ws : str
Folder of ancillary rasters.
output_ws : str
Folder of output rasters.
variable : list, optional
GRIDMET variables to download (the default is ['etr', 'pr']).
Choices: 'eto', 'etr', 'pr', 'srad', 'sph', 'tmmn', 'tmmx', 'vs'
Set as ['all'] to process all variables.
extent_path : str, optional
File path defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
Returns
-------
None
"""
logging.info('\nExtracting GRIDMET variables')
logging.debug(' Start date: {}'.format(start_dt))
logging.debug(' End date: {}'.format(end_dt))
# Save GRIDMET lat, lon, and elevation arrays
elev_raster = os.path.join(ancillary_ws, 'gridmet_elev.img')
# GRIDMET rasters to extract
data_full_list = ['eto', 'etr', 'pr', 'srad', 'sph', '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()
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['eto'] = 'potential_evapotranspiration'
gridmet_band_dict['etr'] = 'potential_evapotranspiration'
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 = drigo.raster_ds_osr(gridmet_ds)
gridmet_proj = drigo.osr_proj(gridmet_osr)
gridmet_cs = drigo.raster_ds_cellsize(gridmet_ds, x_only=True)
gridmet_extent = drigo.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 = drigo.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')
if not os.path.isfile(extent_path):
logging.error(
'\nThe extent object does not exist, exiting\n'
' {}'.format(extent_path))
return False
elif extent_path.lower().endswith('.shp'):
gridmet_extent = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
gridmet_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
gridmet_extent = drigo.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 = drigo.array_geo_offsets(
gridmet_full_geo, gridmet_geo, cs=gridmet_cs)
g_rows, g_cols = gridmet_extent.shape(cs=gridmet_cs)
# Flip row indices since GRIDMET arrays are flipped up/down
# Hard coding GRIDMET row count for now
row_a, row_b = 585 - (g_j + g_rows), 585 - g_j,
col_a, col_b = g_i, g_i + g_cols
# Process each variable
logging.info("")
for input_var in variables:
logging.info("\nVariable: {}".format(input_var))
# Rename variables to match cimis
if input_var == 'pr':
output_var = 'ppt'
else:
output_var = 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)
drigo.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
# Immediately 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]][
:, row_a: row_b, col_a: col_b].copy()
input_nc = np.flip(input_nc, 1)
input_nc_f.close()
del input_nc_f
# 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 = _utils.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 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 = drigo.array_to_mem_ds(
input_full_array, output_geo=gridmet_geo,
output_proj=gridmet_proj)
# Then extract the subset from the in memory dataset
output_array = drigo.raster_ds_to_array(
input_full_ds, 1, mask_extent=gridmet_extent,
return_nodata=False)
# Convert Kelvin to Celsius
if input_var in ['tmmx', 'tmmn']:
output_array -= 273.15
# Save the projected array as 32-bit floats
drigo.array_to_comp_raster(
output_array.astype(np.float32), output_path,
band=doy, stats_flag=False)
# drigo.array_to_raster(
# output_array.astype(np.float32), output_path,
# output_geo=gridmet_geo, output_proj=gridmet_proj,
# stats_flag=False)
del output_array
if stats_flag:
drigo.raster_statistics(output_path)
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
Parameters
----------
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, optional
If True, compute alfalfa reference ET (ETr).
eto_flag : bool, optional
If True, compute grass reference ET (ETo).
start_date : str, optional
ISO format date (YYYY-MM-DD).
end_date : str, optional
ISO format date (YYYY-MM-DD).
extent_path : str, optional
File path defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
use_cimis_eto_flag : bool, optional
If True, use CIMIS ETo raster if one of the component rasters is
missing and ETo/ETr cannot be computed (te default is False).
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 = refet.calcs.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))
refet_obj = refet.Daily(tmin=tmin_test,
tmax=tmax_test,
q=q_test,
rs=rs_test,
u2=u2_test,
zw=zw_test,
elev=elev_test,
doy=doy_test,
lat=lat_test)
etr = float(refet_obj.etr())
eto = float(refet_obj.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 = drigo.raster_ds_osr(cimis_mask_ds)
cimis_proj = drigo.osr_proj(cimis_osr)
cimis_cs = drigo.raster_ds_cellsize(cimis_mask_ds, x_only=True)
cimis_extent = drigo.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 = drigo.Extent((-400000, -650000, 600000, 454000))
# cimis_cs = 2000
# cimis_geo = drigo.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 = drigo.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 = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
cimis_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
cimis_extent = drigo.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 = drigo.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 = drigo.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))
drigo.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))
drigo.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 = drigo.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:
drigo.array_to_comp_raster(1.2 * eto_array,
etr_raster,
band=doy,
stats_flag=False)
# drigo.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:
drigo.array_to_comp_raster(eto_array,
eto_raster,
band=doy,
stats_flag=False)
# drigo.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
tmin_array = drigo.raster_to_array(tmin_path,
1,
cimis_extent,
return_nodata=False)
tmax_array = drigo.raster_to_array(tmax_path,
1,
cimis_extent,
return_nodata=False)
tdew_array = drigo.raster_to_array(tdew_path,
1,
cimis_extent,
return_nodata=False)
# rso_array = drigo.raster_to_array(
# rso_path, 1, cimis_extent, return_nodata=False)
rs_array = drigo.raster_to_array(rs_path,
1,
cimis_extent,
return_nodata=False)
u2_array = drigo.raster_to_array(u2_path,
1,
cimis_extent,
return_nodata=False)
# k_array = drigo.raster_to_array(
# k_path, 1, cimis_extent, return_nodata=False)
# rnl_array = drigo.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')
# Compute Ea from Tdew
ea_array = refet.calcs.saturation_vapor_pressure_func(
tdew_array)
# # Calculate q from tdew by first calculating ea from tdew
# ea_array = refet.calcs.saturation_vapor_pressure_func(tdew_array)
# pair_array = refet.calcs.air_pressure_func(elev_array)
# q_array = 0.622 * ea_array / (pair_array - (0.378 * ea_array))
# del es_array, pair_array, tdew_array
# # Calculate rhmin/rhmax from tdew
# ea_tmax = refet._calcs.saturation_vapor_pressure_func(tmax_array)
# ea_tmin = refet._calcs.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
refet_obj = refet.Daily(tmin=tmin_array,
tmax=tmax_array,
ea=ea_array,
rs=rs_array,
uz=u2_array,
zw=zw,
elev=elev_array,
lat=lat_array,
doy=doy,
method='asce')
# rso_type='ARRAY', rso=rso_array
# ETr
if etr_flag:
drigo.array_to_comp_raster(refet_obj.etr().astype(
np.float32),
etr_raster,
band=doy,
stats_flag=False)
# drigo.array_to_raster(
# refet_obj.etr().astype(np.float32), etr_raster,
# output_geo=cimis_geo, output_proj=cimis_proj,
# stats_flag=stats_flag)
# ETo
if eto_flag:
drigo.array_to_comp_raster(refet_obj.eto().astype(
np.float32),
eto_raster,
band=doy,
stats_flag=False)
# drigo.array_to_raster(
# refet_obj.eto().astype(np.float32), eto_raster,
# output_geo=cimis_geo, output_proj=cimis_proj,
# stats_flag=stats_flag)
# Cleanup
del tmin_array, tmax_array, u2_array, rs_array, ea_array
# del rnl, rs, rso
else:
logging.info(' Skipping date')
continue
if stats_flag and etr_flag:
drigo.raster_statistics(etr_raster)
if stats_flag and eto_flag:
drigo.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
Parameters
----------
netcdf_ws : str
Folder of DAYMET netcdf files.
ancillary_ws : str
Folder of ancillary rasters.
output_ws : str
Folder of output rasters.
variables : list, optional
DAYMET variables to download ('prcp', 'srad', 'vp', 'tmmn', 'tmmx').
Set as ['all'] to process all variables.
daily_flag : bool, optional
If True, compute daily (DOY) climatologies.
monthly_flag : bool, optional
If True, compute monthly climatologies.
annual_flag : bool, optional
If True, compute annual climatologies.
start_year : int, optional
Climatology start year.
end_year : int, optional
Climatology end year.
extent_path : str, optional
File path a raster defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
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 = drigo.raster_ds_osr(daymet_ds)
daymet_proj = drigo.osr_proj(daymet_osr)
daymet_cs = drigo.raster_ds_cellsize(daymet_ds, x_only=True)
daymet_extent = drigo.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 = drigo.project_extent(
drigo.Extent(output_extent), drigo.epsg_osr(4326), daymet_osr, 0.001)
output_extent = drigo.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 = drigo.project_extent(
drigo.raster_path_extent(extent_path),
drigo.raster_path_osr(extent_path), daymet_osr,
drigo.raster_path_cellsize(extent_path, x_only=True))
output_extent = drigo.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 = drigo.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 = _utils.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)
drigo.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)
drigo.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)
drigo.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(grb_ws,
ancillary_ws,
output_ws,
etr_flag=False,
eto_flag=False,
scene_list_path=None,
start_dt=None,
end_dt=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
Parameters
----------
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, optional
If True, compute alfalfa reference ET (ETr).
eto_flag : bool, optional
If True, compute grass reference ET (ETo).
scene_list_path : str, optional
Landsat scene keep list file path.
start_date : str, optional
ISO format date (YYYY-MM-DD).
end_date : str, optional
ISO format date (YYYY-MM-DD).
times : str, optional
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, optional
File path defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
daily_flag : bool, optional
If True, save daily ETr/ETo sum raster (the default is True).
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
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
# Only process a specific hours
if not times_str:
time_list = range(0, 24, 1)
else:
time_list = list(_utils.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$')
# # Landsat Collection 1 Product ID
# landsat_re = re.compile(
# '^(?:LT04|LT05|LE07|LC08)_\w{4}_\d{3}\d{3}_(?P<DATE>\d{8})_'
# '\w{8}_\w{2}_\w{2}')
# Landsat Custom Scene ID
landsat_re = re.compile('^(?:LT04|LT05|LE07|LC08)_\d{6}_(?P<DATE>\d{8})')
# 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')
# Process Landsat scene list and start/end input parameters
if not scene_list_path and (not start_dt or not end_dt):
logging.error(
'\nERROR: A Landsat scene list or start/end dates must be set, '
'exiting\n')
return False
if scene_list_path is not None and os.path.isfile(scene_list_path):
# Build a date list from the Landsat scene keep list file
logging.info('\nReading dates from scene keep list file')
logging.info(' {}'.format(scene_list_path))
with open(scene_list_path) as input_f:
keep_list = input_f.readlines()
date_list = sorted([
dt.datetime.strptime(m.group('DATE'),
'%Y%m%d').strftime('%Y-%m-%d')
for image_id in keep_list for m in [landsat_re.match(image_id)]
if m
])
logging.debug(' {}'.format(', '.join(date_list)))
else:
date_list = []
if start_dt and end_dt:
logging.debug(' Start date: {}'.format(start_dt))
logging.debug(' End date: {}'.format(end_dt))
else:
start_dt = dt.datetime.strptime(date_list[0], '%Y-%m-%d')
end_dt = dt.datetime.strptime(date_list[-1], '%Y-%m-%d')
# 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 = drigo.raster_ds_osr(nldas_ds)
nldas_proj = drigo.osr_proj(nldas_osr)
nldas_cs = drigo.raster_ds_cellsize(nldas_ds, x_only=True)
nldas_extent = drigo.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 = drigo.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 not os.path.isfile(extent_path):
logging.error('\nThe extent object does not exist, exiting\n'
' {}'.format(extent_path))
return False
elif extent_path.lower().endswith('.shp'):
nldas_extent = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
nldas_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
nldas_extent = drigo.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 = drigo.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 = drigo.raster_to_array(elev_path,
mask_extent=nldas_extent,
return_nodata=False)
# pair_array = et_common.air_pressure_func(elev_array)
lat_array = drigo.raster_to_array(lat_path,
mask_extent=nldas_extent,
return_nodata=False)
lon_array = drigo.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))
drigo.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))
drigo.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
input_band_dict = grib_band_names(input_path)
# 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 = drigo.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 = drigo.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 = drigo.raster_ds_to_array(
input_ds,
band=input_band_dict['Specific humidity [kg/kg]'],
mask_extent=nldas_extent,
return_nodata=False)
rs_array = drigo.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 = drigo.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 = drigo.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
# Compute vapor pressure from specific humidity
pair_array = refet.calcs._air_pressure(elev=elev_array)
ea_array = refet.calcs._actual_vapor_pressure(q=sph_array,
pair=pair_array)
refet_obj = refet.Hourly(tmean=temp_array,
ea=ea_array,
rs=rs_array,
uz=wind_array,
zw=10,
elev=elev_array,
lat=lat_array,
lon=lon_array,
doy=input_doy,
time=int(time_str) / 100,
method='asce')
# ETr
if etr_flag:
etr_array = refet_obj.etr()
if daily_flag:
etr_day_array += etr_array
if time_str in time_list:
drigo.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 = refet_obj.eto()
if eto_flag and daily_flag:
eto_day_array += eto_array
if eto_flag and time_str in time_list:
drigo.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
del pair_array, ea_array
if stats_flag and etr_flag:
drigo.raster_statistics(etr_hour_path)
if stats_flag and eto_flag:
drigo.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:
drigo.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:
drigo.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(grb_ws,
ancillary_ws,
output_ws,
scene_list_path=None,
start_dt=None,
end_dt=None,
times_str='',
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Extract hourly NLDAS vapour pressure rasters
Parameters
----------
grb_ws : str
Folder of NLDAS GRB files.
ancillary_ws : str
Folder of ancillary rasters.
output_ws : str
Folder of output rasters.
scene_list_path : str, optional
Landsat scene keep list file path.
start_dt : datetime, optional
Start date.
end_dt : datetime, optional
End date.
times : str, optional
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, optional
File path defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
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$')
# # Landsat Collection 1 Product ID
# landsat_re = re.compile(
# '^(?:LT04|LT05|LE07|LC08)_\w{4}_\d{3}\d{3}_(?P<DATE>\d{8})_'
# '\w{8}_\w{2}_\w{2}')
# Landsat Custom Scene ID
landsat_re = re.compile('^(?:LT04|LT05|LE07|LC08)_\d{6}_(?P<DATE>\d{8})')
output_folder = 'ea'
output_fmt = 'ea_{:04d}{:02d}{:02d}_hourly_nldas.img'
# output_fmt = 'ea_{:04d}{:02d}{:02d}_{:04d}_nldas.img'
# Only process a specific hours
if not times_str:
time_list = range(0, 24, 1)
else:
time_list = list(_utils.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')
# Process Landsat scene list and start/end input parameters
if not scene_list_path and (not start_dt or not end_dt):
logging.error(
'\nERROR: A Landsat scene list or start/end dates must be set, '
'exiting\n')
return False
if scene_list_path is not None and os.path.isfile(scene_list_path):
# Build a date list from the Landsat scene keep list file
logging.info('\nReading dates from scene keep list file')
logging.info(' {}'.format(scene_list_path))
with open(scene_list_path) as input_f:
keep_list = input_f.readlines()
date_list = sorted([
dt.datetime.strptime(m.group('DATE'),
'%Y%m%d').strftime('%Y-%m-%d')
for image_id in keep_list for m in [landsat_re.match(image_id)]
if m
])
logging.debug(' {}'.format(', '.join(date_list)))
else:
date_list = []
if start_dt and end_dt:
logging.debug(' Start date: {}'.format(start_dt))
logging.debug(' End date: {}'.format(end_dt))
else:
start_dt = dt.datetime.strptime(date_list[0], '%Y-%m-%d')
end_dt = dt.datetime.strptime(date_list[-1], '%Y-%m-%d')
# 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 = drigo.raster_ds_osr(nldas_ds)
nldas_proj = drigo.osr_proj(nldas_osr)
nldas_cs = drigo.raster_ds_cellsize(nldas_ds, x_only=True)
nldas_extent = drigo.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 = drigo.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 not os.path.isfile(extent_path):
logging.error('\nThe extent object does not exist, exiting\n'
' {}'.format(extent_path))
return False
elif extent_path.lower().endswith('.shp'):
nldas_extent = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
nldas_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
nldas_extent = drigo.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 = drigo.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 = drigo.raster_to_array(elev_path,
mask_extent=nldas_extent,
return_nodata=False)
pair_array = refet.calcs._air_pressure(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))
drigo.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')))
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 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 = drigo.raster_ds_to_array(
input_ds,
band=input_band_dict['Specific humidity [kg/kg]'],
mask_extent=nldas_extent,
return_nodata=False)
ea_array = refet.calcs._actual_vapor_pressure(q=sph_array,
pair=pair_array)
# ea_array = (sph_array * pair_array) / (0.622 + 0.378 * sph_array)
# Save the projected array as 32-bit floats
drigo.array_to_comp_raster(ea_array.astype(np.float32),
output_path,
band=band_num)
# drigo.block_to_raster(
# ea_array.astype(np.float32), output_path, band=band)
# drigo.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:
drigo.raster_statistics(output_path)
logging.debug('\nScript Complete')
def main(grb_ws, ancillary_ws, output_ws, variables=['pr'],
scene_list_path=None, start_dt=None, end_dt=None, times_str='',
extent_path=None, output_extent=None,
stats_flag=True, overwrite_flag=False):
"""Extract NLDAS target variable(s)
Parameters
----------
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 (the default is ['pr']).
Choices: 'ppt', 'srad', 'sph', 'tair', tmmn', 'tmmx', 'vs'.
keep_list_path : str, optional
Landsat scene keep list file path.
start_dt : datetime, optional
Start date.
end_dt : datetime, optional
End date.
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, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
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'
# # Landsat Collection 1 Product ID
# landsat_re = re.compile(
# '^(?:LT04|LT05|LE07|LC08)_\w{4}_\d{3}\d{3}_(?P<DATE>\d{8})_'
# '\w{8}_\w{2}_\w{2}')
# Landsat Custom Scene ID
landsat_re = re.compile(
'^(?:LT04|LT05|LE07|LC08)_\d{6}_(?P<DATE>\d{8})')
# Only process a specific hours
if not times_str:
time_list = range(0, 24, 1)
else:
time_list = list(_utils.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')
# Process Landsat scene list and start/end input parameters
if not scene_list_path and (not start_dt or not end_dt):
logging.error(
'\nERROR: A Landsat scene list or start/end dates must be set, '
'exiting\n')
return False
if scene_list_path is not None and os.path.isfile(scene_list_path):
# Build a date list from the Landsat scene keep list file
logging.info('\nReading dates from scene keep list file')
logging.info(' {}'.format(scene_list_path))
with open(scene_list_path) as input_f:
keep_list = input_f.readlines()
date_list = sorted([
dt.datetime.strptime(m.group('DATE'), '%Y%m%d').strftime('%Y-%m-%d')
for image_id in keep_list
for m in [landsat_re.match(image_id)] if m])
logging.debug(' {}'.format(', '.join(date_list)))
else:
date_list = []
if start_dt and end_dt:
logging.debug(' Start date: {}'.format(start_dt))
logging.debug(' End date: {}'.format(end_dt))
else:
start_dt = dt.datetime.strptime(date_list[0], '%Y-%m-%d')
end_dt = dt.datetime.strptime(date_list[-1], '%Y-%m-%d')
# 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 = drigo.raster_ds_osr(nldas_ds)
nldas_proj = drigo.osr_proj(nldas_osr)
nldas_cs = drigo.raster_ds_cellsize(nldas_ds, x_only=True)
nldas_extent = drigo.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 = drigo.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 not os.path.isfile(extent_path):
logging.error(
'\nThe extent object does not exist, exiting\n'
' {}'.format(extent_path))
return False
elif extent_path.lower().endswith('.shp'):
nldas_extent = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
nldas_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
nldas_extent = drigo.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 = drigo.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))
drigo.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 = drigo.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 = drigo.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 = drigo.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 = drigo.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 = drigo.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
drigo.array_to_comp_raster(
output_array.astype(np.float32), output_path,
band=band_num)
# drigo.block_to_raster(
# ea_array.astype(np.float32), output_path, band=band)
# drigo.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:
drigo.raster_statistics(output_path)
logging.debug('\nScript Complete')
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
Parameters
----------
netcdf_ws : str
Folder of GRIDMET netcdf files.
ancillary_ws : str
Folder of ancillary rasters.
output_ws : str
Folder of output rasters.
etr_flag : str, optional
If True, compute alfalfa reference ET (ETr) (the default is False).
eto_flag : str, optional
If True, compute grass reference ET (ETo) (the default is False).
start_date : str, optional
ISO format date (YYYY-MM-DD).
end_date : str, optional
ISO format date (YYYY-MM-DD).
extent_path : str, optional
File path defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
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['eto'] = 'potential_evapotranspiration'
gridmet_band_dict['etr'] = 'potential_evapotranspiration'
# 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 = drigo.raster_ds_osr(gridmet_ds)
gridmet_proj = drigo.osr_proj(gridmet_osr)
gridmet_cs = drigo.raster_ds_cellsize(gridmet_ds, x_only=True)
gridmet_extent = drigo.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 = drigo.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 not os.path.isfile(extent_path):
logging.error('\nThe extent object not exist, exiting\n'
' {}'.format(extent_path))
return False
elif extent_path.lower().endswith('.shp'):
gridmet_extent = drigo.feature_path_extent(extent_path)
# DEADBEEF - Consider moving call into a try/except block
# logging.error(
# '\nThere was a problem reading the extent object'
# '\nThe file path may be invalid or the file may not exist '
# 'or be corrupt.\n{}'.format(extent_path))
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
gridmet_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
gridmet_extent = drigo.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 = drigo.array_geo_offsets(gridmet_full_geo,
gridmet_geo,
cs=gridmet_cs)
g_rows, g_cols = gridmet_extent.shape(cs=gridmet_cs)
# Flip row indices since GRIDMET arrays are flipped up/down
# Hard coding GRIDMET row count for now
row_a, row_b = 585 - (g_j + g_rows), 585 - g_j,
col_a, col_b = g_i, g_i + g_cols
# Read the elevation and latitude arrays
elev_array = drigo.raster_to_array(elev_raster,
mask_extent=gridmet_extent,
return_nodata=False)
lat_array = drigo.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
eto_path = os.path.join(netcdf_ws, 'eto_{}.nc'.format(year_str))
etr_path = os.path.join(netcdf_ws, 'etr_{}.nc'.format(year_str))
if eto_flag and not os.path.isfile(eto_path):
logging.debug(
' ETo NetCDF doesn\'t exist\n {}'.format(eto_path))
continue
if etr_flag and not os.path.isfile(etr_path):
logging.debug(
' ETr NetCDF doesn\'t exist\n {}'.format(etr_path))
continue
# 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))
drigo.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))
drigo.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
# Immediately clip input arrays to save memory
# Transpose arrays back to row x col
logging.info(' Reading NetCDFs into memory')
if eto_flag:
logging.debug(" {}".format(eto_path))
eto_nc_f = netCDF4.Dataset(eto_path, 'r')
eto_nc = eto_nc_f.variables[
gridmet_band_dict['eto']][:, row_a:row_b, col_a:col_b].copy()
eto_nc = np.flip(eto_nc, 1)
eto_nc_f.close()
del eto_nc_f
if etr_flag:
logging.debug(" {}".format(etr_path))
etr_nc_f = netCDF4.Dataset(etr_path, 'r')
etr_nc = etr_nc_f.variables[
gridmet_band_dict['etr']][:, row_a:row_b, col_a:col_b].copy()
etr_nc = np.flip(etr_nc, 1)
etr_nc_f.close()
del etr_nc_f
# 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 eto_flag and type(eto_nc) != np.ma.core.MaskedArray:
eto_nc = np.ma.core.MaskedArray(eto_nc,
np.zeros(eto_nc.shape, dtype=bool))
if etr_flag and type(etr_nc) != np.ma.core.MaskedArray:
etr_nc = np.ma.core.MaskedArray(etr_nc,
np.zeros(etr_nc.shape, dtype=bool))
# Check all valid dates in the year
year_dates = _utils.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)
if eto_flag:
# Arrays are being read as masked array with a fill value of -9999
# Convert to basic numpy array arrays with nan values
try:
eto_ma = eto_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
eto_array = eto_ma.data.astype(np.float32)
eto_nodata = float(eto_ma.fill_value)
eto_array[eto_array == eto_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
eto_ds = drigo.array_to_mem_ds(eto_array,
output_geo=gridmet_geo,
output_proj=gridmet_proj)
# Then extract the subset from the in memory dataset
eto_array = drigo.raster_ds_to_array(
eto_ds, 1, mask_extent=gridmet_extent, return_nodata=False)
# Save
drigo.array_to_comp_raster(eto_array.astype(np.float32),
eto_raster,
band=doy,
stats_flag=False)
# drigo.array_to_raster(
# eto_array.astype(np.float32), eto_raster,
# output_geo=gridmet_geo, output_proj=gridmet_proj,
# stats_flag=stats_flag)
# Cleanup
del eto_ds, eto_array
if etr_flag:
try:
etr_ma = etr_nc[doy_i, :, :]
except IndexError:
logging.info(' date not in netcdf, skipping')
continue
etr_array = etr_ma.data.astype(np.float32)
etr_nodata = float(etr_ma.fill_value)
etr_array[etr_array == etr_nodata] = np.nan
etr_ds = drigo.array_to_mem_ds(etr_array,
output_geo=gridmet_geo,
output_proj=gridmet_proj)
etr_array = drigo.raster_ds_to_array(
etr_ds, 1, mask_extent=gridmet_extent, return_nodata=False)
drigo.array_to_comp_raster(etr_array.astype(np.float32),
etr_raster,
band=doy,
stats_flag=False)
# drigo.array_to_raster(
# etr_array.astype(np.float32), etr_raster,
# output_geo=gridmet_geo, output_proj=gridmet_proj,
# stats_flag=stats_flag)
del etr_ds, etr_array
if stats_flag and eto_flag:
drigo.raster_statistics(eto_raster)
if stats_flag and etr_flag:
drigo.raster_statistics(etr_raster)
# DEADBEEF - Code for computing ETo/ETr from the component variables
# # 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
#
# # 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))
# drigo.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))
# drigo.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
# # Immediately clip input arrays to save memory
# # Transpose arrays back to row x col
# logging.info(' Reading NetCDFs into memory')
# logging.debug(" {}".format(tmin_path))
# tmin_nc_f = netCDF4.Dataset(tmin_path, 'r')
# tmin_nc = tmin_nc_f.variables[gridmet_band_dict['tmmn']][
# :, row_a: row_b, col_a: col_b].copy()
# tmin_nc = np.flip(tmin_nc, 1)
# tmin_nc_f.close()
# del tmin_nc_f
#
# logging.debug(" {}".format(tmax_path))
# tmax_nc_f = netCDF4.Dataset(tmax_path, 'r')
# tmax_nc = tmax_nc_f.variables[gridmet_band_dict['tmmx']][
# :, row_a: row_b, col_a: col_b].copy()
# tmax_nc = np.flip(tmax_nc, 1)
# tmax_nc_f.close()
# del tmax_nc_f
#
# logging.debug(" {}".format(sph_path))
# sph_nc_f = netCDF4.Dataset(sph_path, 'r')
# sph_nc = sph_nc_f.variables[gridmet_band_dict['sph']][
# :, row_a: row_b, col_a: col_b].copy()
# sph_nc = np.flip(sph_nc, 1)
# sph_nc_f.close()
# del sph_nc_f
#
# logging.debug(" {}".format(rs_path))
# rs_nc_f = netCDF4.Dataset(rs_path, 'r')
# rs_nc = rs_nc_f.variables[gridmet_band_dict['srad']][
# :, row_a: row_b, col_a: col_b].copy()
# rs_nc = np.flip(rs_nc, 1)
# rs_nc_f.close()
# del rs_nc_f
#
# logging.debug(" {}".format(wind_path))
# wind_nc_f = netCDF4.Dataset(wind_path, 'r')
# wind_nc = wind_nc_f.variables[gridmet_band_dict['vs']][
# :, row_a: row_b, col_a: col_b].copy()
# wind_nc = np.flip(wind_nc, 1)
# wind_nc_f.close()
# del wind_nc_f
#
# # 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(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 = _utils.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 = drigo.array_to_mem_ds(
# tmin_array, output_geo=gridmet_geo,
# # tmin_array, output_geo=gridmet_full_geo,
# output_proj=gridmet_proj)
# tmax_ds = drigo.array_to_mem_ds(
# tmax_array, output_geo=gridmet_geo,
# # tmax_array, output_geo=gridmet_full_geo,
# output_proj=gridmet_proj)
# sph_ds = drigo.array_to_mem_ds(
# sph_array, output_geo=gridmet_geo,
# # sph_array, output_geo=gridmet_full_geo,
# output_proj=gridmet_proj)
# rs_ds = drigo.array_to_mem_ds(
# rs_array, output_geo=gridmet_geo,
# # rs_array, output_geo=gridmet_full_geo,
# output_proj=gridmet_proj)
# wind_ds = drigo.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 = drigo.raster_ds_to_array(
# tmin_ds, 1, mask_extent=gridmet_extent, return_nodata=False)
# tmax_array = drigo.raster_ds_to_array(
# tmax_ds, 1, mask_extent=gridmet_extent, return_nodata=False)
# sph_array = drigo.raster_ds_to_array(
# sph_ds, 1, mask_extent=gridmet_extent, return_nodata=False)
# rs_array = drigo.raster_ds_to_array(
# rs_ds, 1, mask_extent=gridmet_extent, return_nodata=False)
# wind_array = drigo.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
#
# # Compute vapor pressure from specific humidity
# pair_array = refet.calcs._air_pressure(elev=elev_array)
# ea_array = refet.calcs._actual_vapor_pressure(
# q=sph_array, pair=pair_array)
#
# # ETr/ETo
# refet_obj = refet.Daily(
# tmin=tmin_array, tmax=tmax_array, ea=ea_array, rs=rs_array,
# uz=wind_array, zw=zw, elev=elev_array, lat=lat_array, doy=doy,
# method='asce')
# if etr_flag:
# etr_array = refet_obj.etr()
# if eto_flag:
# eto_array = refet_obj.eto()
#
# # Cleanup
# del tmin_array, tmax_array, sph_array, rs_array, wind_array
# del pair_array, ea_array
#
# # Save the projected array as 32-bit floats
# if etr_flag:
# drigo.array_to_comp_raster(
# etr_array.astype(np.float32), etr_raster,
# band=doy, stats_flag=False)
# # drigo.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:
# drigo.array_to_comp_raster(
# eto_array.astype(np.float32), eto_raster,
# band=doy, stats_flag=False)
# # drigo.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
#
# if stats_flag and etr_flag:
# drigo.raster_statistics(etr_raster)
# if stats_flag and eto_flag:
# drigo.raster_statistics(eto_raster)
logging.debug('\nScript Complete')
def main(netcdf_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
variables=['prcp'],
start_date=None,
end_date=None,
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Extract DAYMET temperature
Parameters
----------
netcdf_ws : str
Folder of DAYMET netcdf files.
ancillary_ws : str
Folder of ancillary rasters.
output_ws : str
Folder of output rasters.
variables : list, optional
DAYMET variables to download ('prcp', 'srad', 'vp', 'tmmn', 'tmmx').
Set as ['all'] to process all variables.
start_date : str, optional
ISO format date (YYYY-MM-DD).
end_date : str, optional
ISO format date (YYYY-MM-DD).
extent_path : str, optional
File path defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
Returns
-------
None
"""
logging.info('\nExtracting DAYMET variables')
# 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))
# 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', '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[:]
# 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 = drigo.raster_ds_osr(daymet_ds)
daymet_proj = drigo.osr_proj(daymet_osr)
daymet_cs = drigo.raster_ds_cellsize(daymet_ds, x_only=True)
daymet_extent = drigo.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 = drigo.project_extent(drigo.Extent(output_extent),
drigo.epsg_osr(4326), daymet_osr,
0.001)
output_extent = drigo.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 = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
output_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
output_extent = drigo.project_extent(output_extent, extent_osr,
daymet_osr, extent_cs)
output_extent = drigo.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 = drigo.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
# 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 = _utils.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
# Convert Kelvin to Celsius
if input_var in ['tmax', 'tmin']:
output_array -= 273.15
# Save the array as 32-bit floats
drigo.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(start_dt,
end_dt,
netcdf_ws,
ancillary_ws,
output_ws,
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Extract DAYMET temperature
Parameters
----------
start_dt : datetime
Start date.
end_dt : datetime
End date.
netcdf_ws : str
Folder of DAYMET netcdf files.
ancillary_ws : str
Folder of ancillary rasters.
output_ws : str
Folder of output rasters.
extent_path : str, optional
File path defining the output extent.
output_extent : list, optional
Decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
Returns
-------
None
"""
logging.info('\nExtracting DAYMET vapor pressure')
logging.debug(' Start date: {}'.format(start_dt))
logging.debug(' End date: {}'.format(end_dt))
# Get DAYMET spatial reference from an ancillary raster
mask_raster = os.path.join(ancillary_ws, 'daymet_mask.img')
elev_raster = os.path.join(ancillary_ws, 'daymet_elev.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 = drigo.raster_ds_osr(daymet_ds)
daymet_proj = drigo.osr_proj(daymet_osr)
daymet_cs = drigo.raster_ds_cellsize(daymet_ds, x_only=True)
daymet_extent = drigo.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 = drigo.project_extent(drigo.Extent(output_extent),
drigo.epsg_osr(4326), daymet_osr,
0.001)
output_extent = drigo.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 = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
output_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
output_extent = drigo.project_extent(output_extent, extent_osr,
daymet_osr, extent_cs)
output_extent = drigo.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 = drigo.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))
# Read the elevation array
elev_array = drigo.raster_to_array(elev_raster,
mask_extent=output_extent,
return_nodata=False)
pair_array = refet.calcs._air_pressure_func(elev_array)
del elev_array
# Process each variable
input_var = 'vp'
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)):
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 = _utils.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)
sph_array = input_ma.data.astype(np.float32)
sph_array[sph_array == input_nodata] = np.nan
# Compute ea [kPa] from specific humidity [kg/kg]
ea_array = (sph_array * pair_array) / (0.622 + 0.378 * sph_array)
# Save the array as 32-bit floats
drigo.array_to_raster(ea_array.astype(np.float32),
output_path,
output_geo=output_geo,
output_proj=daymet_proj,
stats_flag=stats_flag)
del input_ma, ea_array, sph_array
input_nc_f.close()
del input_nc_f
logging.debug('\nScript Complete')
def main(ancillary_ws, overwrite_flag=False):
"""Process CIMIS ancillary data
Parameters
----------
ancillary_ws : str
Folder of ancillary rasters.
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
Returns
-------
None
"""
logging.info('\nProcess CIMIS ancillary data')
# Site URL
site_url = 'http://cimis.casil.ucdavis.edu/cimis/'
# DEM for air pressure calculation
# http://topotools.cr.usgs.gov/gmted_viewer/gmted2010_global_grids.php
elev_full_url = 'http://edcintl.cr.usgs.gov/downloads/sciweb1/shared/topo/downloads/GMTED/Grid_ZipFiles/mn30_grd.zip'
elev_full_zip = os.path.join(ancillary_ws, 'mn30_grd.zip')
elev_full_raster = os.path.join(ancillary_ws, 'mn30_grd')
# Get CIMIS grid properties from 2010/01/01 ETo raster
# Grid of the spatial cimis input rasters
# cimis_extent = drigo.Extent((-410000, -660000, 610000, 460000))
# cimis_cs = 2000
# cimis_geo = drigo.extent_geo(cimis_extent, cimis_cs)
# Spatial reference parameters
cimis_proj4 = (
'+proj=aea +lat_1=34 +lat_2=40.5 +lat_0=0 +lon_0=-120 +x_0=0 '
'+y_0=-4000000 +ellps=GRS80 +datum=NAD83 +units=m +no_defs')
cimis_osr = drigo.proj4_osr(cimis_proj4)
# cimis_epsg = 3310 # NAD_1983_California_Teale_Albers
# cimis_osr = drigo.epsg_osr(cimis_epsg)
# Comment this line out if building GeoTIFF instead of IMG
cimis_osr.MorphToESRI()
cimis_proj = cimis_osr.ExportToWkt()
# snap_xmin, snap_ymin = (0, 0)
# Build output workspace if it doesn't exist
if not os.path.isdir(ancillary_ws):
os.makedirs(ancillary_ws)
# File paths
mask_url = site_url + '/2010/01/01/ETo.asc.gz'
# mask_gz = os.path.join(ancillary_ws, 'cimis_mask.asc.gz')
mask_ascii = os.path.join(ancillary_ws, 'cimis_mask.asc')
mask_raster = os.path.join(ancillary_ws, 'cimis_mask.img')
elev_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')
# Download an ETo ASCII raster to generate the mask raster
if overwrite_flag or not os.path.isfile(mask_raster):
logging.info('\nCIMIS mask')
logging.debug(' Downloading')
logging.debug(" {}".format(mask_url))
logging.debug(" {}".format(mask_ascii))
_utils.url_download(mask_url, mask_ascii)
# DEADBEEF - The files do not appeared to be compressed even though
# they have a .asc.gz file extension on the server.
# logging.debug(" {}".format(mask_gz))
# _utils.url_download(mask_url, mask_gz)
#
# they are named .asc.gz
# # Uncompress '.gz' file to a new file
# logging.debug(' Uncompressing')
# logging.debug(' {}'.format(mask_ascii))
# try:
# input_f = gzip.open(mask_gz, 'rb')
# output_f = open(mask_ascii, 'wb')
# output_f.write(input_f.read())
# output_f.close()
# input_f.close()
# del input_f, output_f
# except:
# logging.error(" ERROR EXTRACTING FILE")
# os.remove(mask_gz)
# # Set spatial reference of the ASCII files
# if build_prj_flag:
# prj_file = open(mask_asc.replace('.asc','.prj'), 'w')
# prj_file.write(output_proj)
# prj_file.close()
# Convert the ASCII raster to a IMG raster
logging.debug(' Computing mask')
logging.debug(' {}'.format(mask_raster))
mask_array = drigo.raster_to_array(mask_ascii, return_nodata=False)
cimis_geo = drigo.raster_path_geo(mask_ascii)
# cimis_extent = drigo.raster_path_extent(mask_ascii)
logging.debug(' {}'.format(cimis_geo))
mask_array = np.isfinite(mask_array).astype(np.uint8)
drigo.array_to_raster(mask_array,
mask_raster,
output_geo=cimis_geo,
output_proj=cimis_proj,
output_nodata=0)
# drigo.ascii_to_raster(
# mask_ascii, mask_raster, np.float32, cimis_proj)
os.remove(mask_ascii)
# 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(mask_raster)):
logging.info('\nCIMIS latitude/longitude')
logging.debug(' {}'.format(lat_raster))
lat_array, lon_array = drigo.raster_lat_lon_func(mask_raster)
drigo.array_to_raster(lat_array,
lat_raster,
output_geo=cimis_geo,
output_proj=cimis_proj)
logging.debug(' {}'.format(lon_raster))
drigo.array_to_raster(lon_array,
lon_raster,
output_geo=cimis_geo,
output_proj=cimis_proj)
# Compute DEM raster
if overwrite_flag or not os.path.isfile(elev_raster):
logging.info('\nCIMIS DEM')
logging.debug(' Downloading GMTED2010 DEM')
logging.debug(" {}".format(elev_full_url))
logging.debug(" {}".format(elev_full_zip))
if overwrite_flag or not os.path.isfile(elev_full_zip):
_utils.url_download(elev_full_url, elev_full_zip)
# Uncompress '.gz' file to a new file
logging.debug(' Uncompressing')
logging.debug(' {}'.format(elev_full_raster))
if overwrite_flag or not os.path.isfile(elev_full_raster):
try:
with zipfile.ZipFile(elev_full_zip, "r") as z:
z.extractall(ancillary_ws)
except:
logging.error(" ERROR EXTRACTING FILE")
os.remove(elev_full_zip)
# Get the extent and cellsize from the mask
logging.debug(' Projecting to CIMIS grid')
cimis_cs = drigo.raster_path_cellsize(mask_raster)[0]
cimis_extent = drigo.raster_path_extent(mask_raster)
logging.debug(' Extent: {}'.format(cimis_extent))
logging.debug(' Cellsize: {}'.format(cimis_cs))
logging.info(' {}'.format(mask_ascii))
if overwrite_flag and os.path.isfile(elev_raster):
subprocess.call(['gdalmanage', 'delete', elev_raster])
if not os.path.isfile(elev_raster):
subprocess.call([
'gdalwarp', '-r', 'average', '-t_srs', cimis_proj4, '-te',
str(cimis_extent.xmin),
str(cimis_extent.ymin),
str(cimis_extent.xmax),
str(cimis_extent.ymax), '-tr',
str(cimis_cs),
str(cimis_cs), '-of', 'HFA', '-co', 'COMPRESSED=TRUE',
elev_full_raster, elev_raster
],
cwd=ancillary_ws)
logging.debug('\nScript Complete')
def main(grb_ws=os.getcwd(),
ancillary_ws=os.getcwd(),
output_ws=os.getcwd(),
keep_list_path=None,
start_date=None,
end_date=None,
times_str='',
extent_path=None,
output_extent=None,
stats_flag=True,
overwrite_flag=False):
"""Extract hourly NLDAS wind rasters
Parameters
----------
grb_ws : str
Folder of NLDAS GRB files.
ancillary_ws : str
Folder of ancillary rasters.
output_ws : str
Folder of output rasters.
keep_list_path : str, optional
Landsat scene keep list file path.
start_date : str, optional
ISO format date (YYYY-MM-DD).
end_date : str, optional
ISO format date (YYYY-MM-DD).
times : str, optional
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, optional
File path defining the output extent.
output_extent : ?, optional
List decimal degrees values defining output extent.
stats_flag : bool, optional
If True, compute raster statistics (the default is True).
overwrite_flag : bool, optional
If True, overwrite existing files (the default is False).
Returns
-------
None
"""
logging.info('\nExtracting NLDAS wind 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 = 'wind'
output_fmt = 'wind_{:04d}{:02d}{:02d}_hourly_nldas.img'
# output_fmt = 'wind_{: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(_utils.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')
# Build a date list from the Landsat scene keep list file
date_list = []
if keep_list_path is not None and os.path.isfile(keep_list_path):
logging.info('\nReading dates from scene keep list file')
logging.info(' {}'.format(keep_list_path))
landsat_re = re.compile(
'^(?:LT04|LT05|LE07|LC08)_(?:\d{3})(?:\d{3})_' +
'(?P<year>\d{4})(?P<month>\d{2})(?P<day>\d{2})')
with open(keep_list_path) as input_f:
keep_list = input_f.readlines()
keep_list = [
image_id.strip() for image_id in keep_list
if landsat_re.match(image_id.strip())
]
date_list = [
dt.datetime.strptime(image_id[12:20],
'%Y%m%d').strftime('%Y-%m-%d')
for image_id in keep_list
]
logging.debug(' {}'.format(', '.join(date_list)))
# DEADBEE
# # 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)))
# 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 = drigo.raster_ds_osr(nldas_ds)
nldas_proj = drigo.osr_proj(nldas_osr)
nldas_cs = drigo.raster_ds_cellsize(nldas_ds, x_only=True)
nldas_extent = drigo.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 = drigo.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 = drigo.feature_path_extent(extent_path)
extent_osr = drigo.feature_path_osr(extent_path)
extent_cs = None
else:
nldas_extent = drigo.raster_path_extent(extent_path)
extent_osr = drigo.raster_path_osr(extent_path)
extent_cs = drigo.raster_path_cellsize(extent_path, x_only=True)
nldas_extent = drigo.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 = drigo.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
# 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 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
logging.info('\nReading NLDAS GRIBs')
for root, folders, files in os.walk(grb_ws, topdown=True):
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(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))
drigo.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 magnitude of wind from components
input_ds = gdal.Open(input_path)
wind_u_array = drigo.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 = drigo.raster_ds_to_array(
input_ds,
band=input_band_dict['v-component of wind [m/s]'],
mask_extent=nldas_extent,
return_nodata=False)
wind_array = np.sqrt(wind_u_array**2 + wind_v_array**2)
# Save the projected array as 32-bit floats
drigo.array_to_comp_raster(wind_array.astype(np.float32),
output_path,
band=band_num)
# drigo.block_to_raster(
# ea_array.astype(np.float32), output_path, band=band_num)
# drigo.array_to_raster(
# wind_array.astype(np.float32), output_path,
# output_geo=nldas_geo, output_proj=nldas_proj,
# stats_flag=stats_flag)
del wind_array, wind_u_array, wind_v_array
input_ds = None
if stats_flag:
drigo.raster_statistics(output_path)
logging.debug('\nScript Complete')
