def generate_nat_earth_centroids(res_as=360, path=None, dist_coast=False):
"""For reproducibility, this is the function that generates the centroids
files in `NATEARTH_CENTROIDS`. These files are provided with CLIMADA
so that this function should never be called!
Parameters:
res_as (int): Resolution of file in arc-seconds. Default: 360.
path (str, optional): If set, write resulting hdf5 file here instead of
the default location.
dist_coast (bool): If true, read distance from a NASA dataset
(see util.coordinates.dist_to_coast_nasa)
"""
if path is None and res_as not in [150, 360]:
raise ValueError("Only 150 and 360 arc-seconds are supported!")
res_deg = res_as / 3600
lat_dim = np.arange(-90 + res_deg, 90, res_deg)
lon_dim = np.arange(-180 + res_deg, 180 + res_deg, res_deg)
lon, lat = [ar.ravel() for ar in np.meshgrid(lon_dim, lat_dim)]
natids = np.uint16(get_country_code(lat, lon, gridded=False))
cen = Centroids()
cen.set_lat_lon(lat, lon)
cen.region_id = natids
cen.set_lat_lon_to_meta()
cen.lat = np.array([])
cen.lon = np.array([])
if path is None:
path = NATEARTH_CENTROIDS[res_as]
if dist_coast:
cen.set_dist_coast(precomputed=True, signed=False)
cen.dist_coast = np.float16(cen.dist_coast)
cen.write_hdf5(path)
def test_country_code_pass(self):
""" Test set_region_id """
lon = np.array([
-59.6250000000000, -59.6250000000000, -59.6250000000000,
-59.5416666666667, -59.5416666666667, -59.4583333333333,
-60.2083333333333, -60.2083333333333
])
lat = np.array([
13.125, 13.20833333, 13.29166667, 13.125, 13.20833333, 13.125,
12.625, 12.70833333
])
region_id = get_country_code(lat, lon)
region_id_OSLO = get_country_code([59.91], [10.75])
self.assertEqual(np.count_nonzero(region_id), 6)
self.assertTrue(np.allclose(region_id[:6],
np.ones(6) * 52)) # 052 for barbados
self.assertEqual(region_id_OSLO, np.array(578)) # 578 for Norway
def test_country_code_pass(self):
"""Test set_region_id"""
lon = np.array([
-59.6250000000000, -59.6250000000000, -59.6250000000000,
-59.5416666666667, -59.5416666666667, -59.4583333333333,
-60.2083333333333, -60.2083333333333
])
lat = np.array([
13.125, 13.20833333, 13.29166667, 13.125, 13.20833333, 13.125,
12.625, 12.70833333
])
for gridded in [True, False]:
region_id = get_country_code(lat, lon, gridded=gridded)
region_id_OSLO = get_country_code(59.91, 10.75, gridded=gridded)
self.assertEqual(np.count_nonzero(region_id), 6)
# 052 for barbados
self.assertTrue(np.all(region_id[:6] == 52))
# 578 for Norway
self.assertEqual(region_id_OSLO, np.array([578]))
def set_region_id(self, scheduler=None):
"""Set region_id as country ISO numeric code attribute for every pixel
or point
Parameters:
scheduler (str): used for dask map_partitions. “threads”,
“synchronous” or “processes”
"""
ne_geom = self._ne_crs_geom(scheduler)
LOGGER.debug('Setting region_id %s points.', str(self.lat.size))
self.region_id = get_country_code(ne_geom.geometry[:].y.values,
ne_geom.geometry[:].x.values)
def set_from_isimip_netcdf(self, input_dir=None, filename=None, hist_mean=None,
bbox=None, yearrange=None, cl_model=None, scenario=None,
crop=None, irr=None, isimip_version=None,
unit=None, fn_str_var=None):
"""Wrapper to fill exposure from NetCDF file from ISIMIP. Requires historical
mean relative cropyield module as additional input.
Optional Parameters:
input_dir (string): path to input data directory
filename (string): name of the landuse data file to use,
e.g. "histsoc_landuse-15crops_annual_1861_2005.nc""
hist_mean (str or array): historic mean crop yield per centroid (or path)
bbox (list of four floats): bounding box:
[lon min, lat min, lon max, lat max]
yearrange (int tuple): year range for exposure set
e.g., (1990, 2010)
scenario (string): climate change and socio economic scenario
e.g., '1860soc', 'histsoc', '2005soc', 'rcp26soc','rcp60soc','2100rcp26soc'
cl_model (string): abbrev. climate model (only for future projections of lu data)
e.g., 'gfdl-esm2m', 'hadgem2-es', 'ipsl-cm5a-lr','miroc5'
crop (string): crop type
e.g., 'mai', 'ric', 'whe', 'soy'
irr (string): irrigation type, default: 'combined'
f.i 'firr' (full irrigation), 'noirr' (no irrigation) or 'combined'= firr+noirr
isimip_version(str): 'ISIMIP2' (default) or 'ISIMIP3'
unit (string): unit of the exposure (per year)
f.i 't/y' (default), 'USD/y', or 'kcal/y'
fn_str_var (string): FileName STRing depending on VARiable and
ISIMIP simuation round
Returns:
Exposure
"""
# parameters not provided in method call are set to default values:
if irr is None:
irr = 'combined'
if not bbox:
bbox = BBOX
if not input_dir:
input_dir = INPUT_DIR
if hist_mean is None:
hist_mean = HIST_MEAN_PATH
if not fn_str_var:
fn_str_var = FN_STR_VAR
if (not isimip_version) or (isimip_version in ('ISIMIP2a', 'ISIMIP2b')):
isimip_version = 'ISIMIP2'
elif isimip_version in ('ISIMIP3a', 'ISIMIP3b'):
isimip_version = 'ISIMIP3'
if (not scenario) or (scenario in ('historical', 'hist')):
scenario = 'histsoc'
if yearrange is None:
yearrange = YEARCHUNKS[isimip_version][scenario]['yearrange']
if not unit:
unit = 't/y'
#if not soc: soc=''
# The filename is set or other variables (cl_model, scenario) are extracted of the
# specified filename
if filename is None:
yearchunk = YEARCHUNKS[isimip_version][scenario]
# if scenario == 'histsoc' or scenario == '1860soc':
if scenario in ('histsoc', '1860soc'):
string = '{}_{}_{}_{}.nc'
filepath = Path(input_dir, string.format(scenario, fn_str_var,
yearchunk['startyear'],
yearchunk['endyear']))
else:
string = '{}_{}_{}_{}_{}.nc'
filepath = Path(input_dir, string.format(scenario, cl_model, fn_str_var,
yearchunk['startyear'],
yearchunk['endyear']))
elif scenario == 'flexible':
_, _, _, _, _, _, startyear, endyearnc = filename.split('_')
endyear = endyearnc.split('.')[0]
yearchunk = dict()
yearchunk = {'yearrange': (int(startyear), int(endyear)),
'startyear': int(startyear), 'endyear': int(endyear)}
filepath = Path(input_dir, filename)
else:
scenario, *_ = filename.split('_')
yearchunk = YEARCHUNKS[isimip_version][scenario]
filepath = Path(input_dir, filename)
# Dataset is opened and data within the bbox extends is extracted
data_set = xr.open_dataset(filepath, decode_times=False)
[lonmin, latmin, lonmax, latmax] = bbox
data = data_set.sel(lon=slice(lonmin, lonmax), lat=slice(latmax, latmin))
# The latitude and longitude are set; the region_id is determined
lon, lat = np.meshgrid(data.lon.values, data.lat.values)
self.gdf['latitude'] = lat.flatten()
self.gdf['longitude'] = lon.flatten()
self.gdf['region_id'] = u_coord.get_country_code(self.gdf.latitude, self.gdf.longitude)
# The indeces of the yearrange to be extracted are determined
time_idx = (int(yearrange[0] - yearchunk['startyear']),
int(yearrange[1] - yearchunk['startyear']))
# The area covered by a grid cell is calculated depending on the latitude
# 1 degree = 111.12km (at the equator); resolution data: 0.5 degree;
# longitudal distance in km = 111.12*0.5*cos(lat);
# latitudal distance in km = 111.12*0.5;
# area = longitudal distance * latitudal distance;
# 1km2 = 100ha
area = (111.12 * 0.5)**2 * np.cos(np.deg2rad(lat)) * 100
# The area covered by a crop is calculated as the product of the fraction and
# the grid cell size
if irr == 'combined':
irr_types = ['firr', 'noirr']
else:
irr_types = [irr]
area_crop = dict()
for irr_var in irr_types:
area_crop[irr_var] = (
getattr(
data, (CROP_NAME[crop])['input']+'_'+ (IRR_NAME[irr_var])['name']
)[time_idx[0]:time_idx[1], :, :].mean(dim='time')*area
).values
area_crop[irr_var] = np.nan_to_num(area_crop[irr_var]).flatten()
# set historic mean, its latitude, and longitude:
hist_mean_dict = dict()
# if hist_mean is given as np.ndarray or dict,
# code assumes it contains hist_mean as returned by relative_cropyield
# however structured in dictionary as hist_mean_dict, with same
# bbox extensions as the exposure:
if isinstance(hist_mean, dict):
if not ('firr' in hist_mean.keys() or 'noirr' in hist_mean.keys()):
# as a dict hist_mean, needs to contain key 'firr' or 'noirr';
# if irr=='combined', both 'firr' and 'noirr' are required.
LOGGER.error('Invalid hist_mean provided: %s', hist_mean)
raise ValueError('invalid hist_mean.')
hist_mean_dict = hist_mean
lat_mean = self.gdf.latitude.values
elif isinstance(hist_mean, np.ndarray) or isinstance(hist_mean, list):
hist_mean_dict[irr_types[0]] = np.array(hist_mean)
lat_mean = self.gdf.latitude.values
elif Path(hist_mean).is_dir(): # else if hist_mean is given as path to directory
# The adequate file from the directory (depending on crop and irrigation) is extracted
# and the variables hist_mean, lat_mean and lon_mean are set accordingly
for irr_var in irr_types:
filename = str(Path(hist_mean, 'hist_mean_%s-%s_%i-%i.hdf5' %(
crop, irr_var, yearrange[0], yearrange[1])))
hist_mean_dict[irr_var] = (h5py.File(filename, 'r'))['mean'][()]
lat_mean = (h5py.File(filename, 'r'))['lat'][()]
lon_mean = (h5py.File(filename, 'r'))['lon'][()]
elif Path(input_dir, hist_mean).is_file(): # file path
# Hist_mean, lat_mean and lon_mean are extracted from the given file
if len(irr_types) > 1:
LOGGER.error("For irr=='combined', hist_mean can not be single file. Aborting.")
raise ValueError('Wrong combination of parameters irr and hist_mean.')
hist_mean = h5py.File(str(Path(input_dir, hist_mean)), 'r')
hist_mean_dict[irr_types[0]] = hist_mean['mean'][()]
lat_mean = hist_mean['lat'][()]
lon_mean = hist_mean['lon'][()]
else:
LOGGER.error('Invalid hist_mean provided: %s', hist_mean)
raise ValueError('invalid hist_mean.')
# The bbox is cut out of the hist_mean data file if needed
if len(lat_mean) != len(self.gdf.latitude.values):
idx_mean = np.zeros(len(self.gdf.latitude.values), dtype=int)
for i in range(len(self.gdf.latitude.values)):
idx_mean[i] = np.where(
(lat_mean == self.gdf.latitude.values[i])
& (lon_mean == self.gdf.longitude.values[i])
)[0][0]
else:
idx_mean = np.arange(0, len(lat_mean))
# The exposure [t/y] is computed per grid cell as the product of the area covered
# by a crop [ha] and its yield [t/ha/y]
self.gdf['value'] = np.squeeze(area_crop[irr_types[0]] * \
hist_mean_dict[irr_types[0]][idx_mean])
self.gdf['value'] = np.nan_to_num(self.gdf.value) # replace NaN by 0.0
for irr_val in irr_types[1:]: # add other irrigation types if irr=='combined'
value_tmp = np.squeeze(area_crop[irr_val]*hist_mean_dict[irr_val][idx_mean])
value_tmp = np.nan_to_num(value_tmp) # replace NaN by 0.0
self.gdf['value'] += value_tmp
self.tag = Tag()
self.tag.description = ("Crop production exposure from ISIMIP " +
(CROP_NAME[crop])['print'] + ' ' +
irr + ' ' + str(yearrange[0]) + '-' + str(yearrange[-1]))
self.value_unit = 't/y' # input unit, will be reset below if required by user
self.crop = crop
self.ref_year = yearrange
try:
rows, cols, ras_trans = pts_to_raster_meta(
(self.gdf.longitude.min(), self.gdf.latitude.min(),
self.gdf.longitude.max(), self.gdf.latitude.max()),
get_resolution(self.gdf.longitude, self.gdf.latitude))
self.meta = {
'width': cols,
'height': rows,
'crs': self.crs,
'transform': ras_trans,
}
except ValueError:
LOGGER.warning('Could not write attribute meta, because exposure'
' has only 1 data point')
self.meta = {}
if 'USD' in unit:
# set_value_to_usd() is called to compute the exposure in USD/y (country specific)
self.set_value_to_usd(input_dir=input_dir)
elif 'kcal' in unit:
# set_value_to_kcal() is called to compute the exposure in kcal/y
self.set_value_to_kcal()
self.check()
return self
