def run_ascat_eval_smos_part(part, parts, ref='ascat'):
periods = [
['2010-04-01', '2020-04-01'],
['2010-04-01', '2015-04-01'],
['2015-04-01', '2020-04-01'],
['2010-04-01', '2012-10-01'],
['2012-10-01', '2015-04-01'],
['2015-04-01', '2017-10-01'],
['2017-10-01', '2020-04-01'],
]
res_path = Path(
f'~/Documents/work/MadKF/CLSM/SMOS40/validation/multiperiod/ascat'
).expanduser()
if not res_path.exists():
Path.mkdir(res_path, parents=True)
result_file = res_path / f'ascat_eval_smos_part{part}.csv'
lut = pd.read_csv(Paths().lut, index_col=0)
# Split grid cell list for parallelization
subs = (np.arange(parts + 1) * len(lut) / parts).astype('int')
subs[-1] = len(lut)
start = subs[part - 1]
end = subs[part]
# Look-up table that contains the grid cells to iterate over
lut = lut.iloc[start:end, :]
names = ['open_loop'] + [f'SMOS40_it62{i}' for i in range(1, 5)]
runs = ['US_M36_SMOS40_TB_OL_noScl'
] + [f'US_M36_SMOS40_TB_MadKF_DA_it62{i}' for i in range(1, 5)]
grid = LDAS_io('ObsFcstAna', runs[0]).grid
dss_xhourly = [LDAS_io('xhourly', run).timeseries for run in runs]
dss_obs_ana = [
LDAS_io('ObsFcstAna', run).timeseries['obs_ana'] for run in runs
]
modes = ['absolute', 'longterm', 'shortterm']
ascat = HSAF_io()
for cnt, (gpi, data) in enumerate(lut.iterrows()):
print('%i / %i' % (cnt, len(lut)))
col = int(data.ease2_col - grid.tilegrids.loc['domain', 'i_offg'])
row = int(data.ease2_row - grid.tilegrids.loc['domain', 'j_offg'])
res = pd.DataFrame(index=(gpi, ))
res['col'] = int(data.ease2_col)
res['row'] = int(data.ease2_row)
res['lcol'] = col
res['lrow'] = row
try:
ts_ascat = ascat.read(
data['ascat_gpi'],
resample_time=False).resample('1d').mean().dropna()
ts_ascat = ts_ascat[~ts_ascat.index.duplicated(keep='first')]
ts_ascat.name = 'ASCAT'
except:
continue
dfs = [
ds.sel(species=[1, 2]).isel(
lat=row, lon=col).to_pandas().resample('1d').mean()
for ds in dss_obs_ana
]
idx = [df[np.any(~np.isnan(df), axis=1)].index for df in dfs]
t_ana = idx[0].intersection(idx[1]).intersection(idx[2]).intersection(
idx[3])
var = 'sm_surface'
for mode in modes:
if mode == 'absolute':
ts_ref = ts_ascat.copy()
else:
ts_ref = calc_anom(ts_ascat.copy(),
longterm=(mode == 'longterm')).dropna()
for run, ts_model in zip(names, dss_xhourly):
ind = (ts_model['snow_mass'][:, row, col].values == 0) & (
ts_model['soil_temp_layer1'][:, row, col].values > 277.15)
ts_mod = ts_model[var][:, row, col].to_series().loc[ind]
ts_mod.index += pd.to_timedelta('2 hours')
if mode == 'absolute':
ts_mod = ts_mod.dropna()
else:
ts_mod = calc_anom(ts_mod,
longterm=mode == 'longterm').dropna()
ts_mod = ts_mod.reindex(t_ana).dropna()
for i, p in enumerate(periods):
tmp = pd.DataFrame({
1: ts_ref,
2: ts_mod
})[p[0]:p[1]].dropna()
res[f'p{i}_len_{run}_{mode}'] = len(tmp)
r, p = pearsonr(
tmp[1], tmp[2]) if len(tmp) > 10 else (np.nan, np.nan)
res[f'p{i}_r_{run}_{mode}'] = r
if not result_file.exists():
res.to_csv(result_file, float_format='%0.3f')
else:
res.to_csv(result_file,
float_format='%0.3f',
mode='a',
header=False)
def run(args, scale_target='SMAP', mode='longterm', use_pc=False):
'''
:param args: summarizes the following three for multiprocessing purposes:
sensor: 'SMOS' or 'SMAP' or 'SMOSSMAP'
date_from: 'yyyy-mm-dd'
date_to: 'yyyy-mm-dd'
:param scale_target: 'SMOS' or 'SMAP'
:param mode: 'longterm' or "shortterm'
:param use_pc: If true, the first principal component of SMOS/SMAP Tb will be used
'''
sensor, date_from, date_to, pc = args
exp_smap = f'NLv4_M36_US_OL_{pc}'
exp_smos = f'NLv4_M36_US_OL_{pc}_SMOS'
if mode == 'shortterm':
ext = '_yearly'
elif mode == 'longterm':
ext = '_daily'
else:
ext = ''
froot = Path(f'~/data_sets/GEOSldas_runs/_scaling_files_{pc}{ext}').expanduser()
if not froot.exists():
Path.mkdir(froot, parents=True)
ios = []
if 'SMAP' in sensor:
ios += [GEOSldas_io('ObsFcstAna', exp=exp_smap)]
if 'SMOS' in sensor:
ios += [GEOSldas_io('ObsFcstAna', exp=exp_smos)]
if not date_from:
date_from = pd.to_datetime(np.min([io.timeseries['time'].values[0] for io in ios]))
else:
date_from = pd.to_datetime(date_from)
if not date_to:
date_to = pd.to_datetime(np.max([io.timeseries['time'].values[-1] for io in ios]))
else:
date_to = pd.to_datetime(date_to)
pent_from = int(np.floor((date_from.dayofyear - 1) / 5.) + 1)
pent_to = int(np.floor((date_to.dayofyear - 1) / 5.) + 1)
fbase = f'Thvf_TbSM_001_src_{sensor}_trg_{scale_target}_{date_from.year}_p{pent_from:02}_{date_to.year}_p{pent_to:02}_W_9p_Nmin_20'
dtype, _, _ = template_scaling(sensor='SMAP')
tiles = ios[0].grid.tilecoord['tile_id'].values.astype('int32')
angles = np.array([40,], 'int')
pols = ['H','V']
orbits = [['A', 'D'],['D', 'A']] # To match SMOS and SMAP species!
template = pd.DataFrame(columns=dtype.names, index=tiles).astype('float32')
template['lon'] = ios[0].grid.tilecoord['com_lon'].values.astype('float32')
template['lat'] = ios[0].grid.tilecoord['com_lat'].values.astype('float32')
template['tile_id'] = tiles.astype('int32')
pentads = np.arange(73)+1
if mode == 'longterm':
years = np.arange(date_from.year, date_to.year + 1)
doys = np.arange(1,367)
data_obs = np.full([len(tiles), len(doys), len(years), len(pols), len(orbits[0])], -9999.)
data_mod = data_obs.copy()
# dummy = np.full([len(tiles), len(doys), len(years), len(angles), len(pols), len(orbits[0])], -9999)
# coords = {'tile_id': tiles,
# 'doy': doys,
# 'year': years,
# 'angle': angles,
# 'pol': pols,
# 'orbit': orbits[0]}
# darr = xr.DataArray(dummy, coords=coords, dims=['tile_id', 'doy', 'year', 'angle', 'pol', 'orbit'])
elif mode == 'shortterm':
years = np.arange(date_from.year, date_to.year+1)
data_obs = np.full([len(tiles), len(pentads), len(years), len(pols), len(orbits[0])], -9999.)
data_mod = data_obs.copy()
n_data = np.full([len(tiles), len(pentads), len(years), len(pols), len(orbits[0])], -9999)
# dummy = np.full([len(tiles), len(pentads), len(years), len(angles), len(pols), len(orbits[0])], -9999)
# coords = {'tile_id': tiles,
# 'pentad': pentads,
# 'year': years,
# 'angle': angles,
# 'pol': pols,
# 'orbit': orbits[0]}
# darr = xr.DataArray(dummy, coords=coords, dims=['tile_id', 'pentad', 'year', 'angle', 'pol', 'orbit'])
else:
# TODO: Currently doesn't work anymore because of modification for lt and st
dummy = np.full([len(tiles),len(pentads),len(angles),len(pols),len(orbits[0])],-9999)
coords = {'tile_id': tiles,
'pentad': pentads,
'angle': angles,
'pol': pols,
'orbit': orbits[0]}
darr = xr.DataArray(dummy, coords=coords, dims=['tile_id','pentad','angle','pol','orbit'])
# ----- calculate mean and reshuffle -----
for i_til, til in enumerate(tiles):
logging.info(f'{i_til} / {len(tiles)}')
for i_pol, pol in enumerate(pols):
# for i_ang, ang in enumerate(angles):
ang = angles[0]
for i_orb, (orb1, orb2) in enumerate(zip(orbits[0], orbits[1])):
col, row = ios[0].grid.tileid2colrow(til)
if sensor.upper() == 'SMOSSMAP':
spcs = [io.get_species(pol=pol, ang=ang, orbit=orb) for io, orb in zip(ios,[orb1, orb2])]
# orb = orb2 if scale_target == 'SMAP' else orb1 # POSSIBLY WRONG!!!!
orb = orb1 if scale_target == 'SMAP' else orb2
else:
spcs = [ios[0].get_species(pol=pol, ang=ang, orbit=orb1)]
if sensor.upper() == 'SMAP':
orb = orb1 if scale_target == 'SMAP' else orb2
else:
orb = orb2 if scale_target == 'SMAP' else orb1
if use_pc and (sensor == 'SMOSSMAP'):
dss = [io.timeseries['obs_obs'][:, spc-1, row, col].to_series() for io, spc in zip(ios,spcs)]
obs = PCA(*dss, window=1.5)['PC-1']
dss = [io.timeseries['obs_fcst'][:, spc-1, row, col].to_series() for io, spc in zip(ios,spcs)]
mod = PCA(*dss, window=1.5)['PC-1']
else:
obs = pd.concat([io.timeseries['obs_obs'][:, spc-1, row, col].to_series() for io, spc in zip(ios,spcs)]).sort_index()
mod = pd.concat([io.timeseries['obs_fcst'][:, spc-1, row, col].to_series() for io, spc in zip(ios,spcs)]).sort_index()
if (len(obs) == 0) | (len(mod) == 0):
continue
if mode == 'longterm':
obs_clim = calc_anom(obs, return_clim=True)
mod_clim = calc_anom(mod, return_clim=True)
obs_anom = calc_anom(obs, mode='shortterm')
mod_anom = calc_anom(mod, mode='shortterm')
m_obs = (obs_clim + obs_anom).resample('1D').mean()
m_mod = (mod_clim + mod_anom).resample('1D').mean()
i_yr = m_obs.index.year.values - years.min()
i_doy = m_obs.index.dayofyear.values - 1
data_obs[i_til, i_doy, i_yr, i_pol, i_orb] = m_obs.replace(np.nan, -9999.).values
data_mod[i_til, i_doy, i_yr, i_pol, i_orb] = m_mod.replace(np.nan, -9999.).values
elif mode == 'shortterm':
for i_yr, yr in enumerate(years):
data_obs[i_til, :, i_yr, i_pol, i_orb] = calc_clim_p(obs[obs.index.year==yr][date_from:date_to])[0].replace(np.nan, -9999.).values
data_mod[i_til, :, i_yr, i_pol, i_orb] = calc_clim_p(mod[mod.index.year==yr][date_from:date_to])[0].replace(np.nan, -9999.).values
n_data[i_til, :, i_yr, i_pol, i_orb] = len(obs[obs.index.year==yr][date_from:date_to].dropna())
else:
# TODO: Doesn't work currently!
data['m_obs'].sel(tile_id=til, pol=pol, angle=ang, orbit=orb)[:],\
data['s_obs'].sel(tile_id=til, pol=pol, angle=ang, orbit=orb)[:] = calc_clim_p(obs[date_from:date_to])
data['m_mod'].sel(tile_id=til, pol=pol, angle=ang, orbit=orb)[:],\
data['s_mod'].sel(tile_id=til, pol=pol, angle=ang, orbit=orb)[:] = calc_clim_p(mod[date_from:date_to])
data['N_data'].sel(tile_id=til, pol=pol, angle=ang, orbit=orb)[:] = len(obs[date_from:date_to].dropna())
modes = np.array([0, 0])
sdate = np.array([date_from.year, date_from.month, date_from.day, 0, 0])
edate = np.array([date_to.year, date_to.month, date_to.day, 0, 0])
lengths = np.array([len(tiles), len(angles), 1]) # tiles, incidence angles, whatever
np.save('/Users/u0116961/data_sets/data_mod', data_mod)
np.save('/Users/u0116961/data_sets/data_obs', data_obs)
# ----- write output files -----
if mode == 'longterm':
for i_orb, orb in enumerate(orbits[0]):
# !!! inconsistent with the definition in the obs_paramfile (species) !!!
modes[0] = 1 if orb == 'A' else 0
for i_yr, yr in enumerate(years):
for i_doy, doy in enumerate(doys):
res = template.copy()
# for i_ang, ang in enumerate(angles):
ang = angles[0]
for i_pol, pol in enumerate(pols):
res.loc[:, f'm_obs_{pol}_{ang}'] = data_obs[:, i_doy, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f's_obs_{pol}_{ang}'] = data_obs[:, i_doy, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f'm_mod_{pol}_{ang}'] = data_mod[:, i_doy, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f's_mod_{pol}_{ang}'] = data_mod[:, i_doy, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f'N_data_{pol}_{ang}'] = 999
res.replace(np.nan, -9999, inplace=True)
fdir = froot / f'y{yr:04}'
if not fdir.exists():
Path.mkdir(fdir, parents=True)
fname = fdir / f'{fbase}_{orb}_d{doy:03}.bin'
fid = open(fname, 'wb')
ios[0].write_fortran_block(fid, modes)
ios[0].write_fortran_block(fid, sdate)
ios[0].write_fortran_block(fid, edate)
ios[0].write_fortran_block(fid, lengths)
ios[0].write_fortran_block(fid, angles.astype('float')) # required by LDASsa!!
for f in res.columns.values:
ios[0].write_fortran_block(fid, res[f].values)
fid.close()
else:
for i_pent, pent in enumerate(pentads):
for i_orb, orb in enumerate(orbits[0]):
# !!! inconsistent with the definition in the obs_paramfile (species) !!!
modes[0] = 1 if orb == 'A' else 0
if mode == 'shortterm':
for i_yr, yr in enumerate(years):
res = template.copy()
for ang in angles:
for i_pol, pol in enumerate(pols):
res.loc[:, f'm_obs_{pol}_{ang}'] = data_obs[:, i_pent, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f's_obs_{pol}_{ang}'] = data_obs[:, i_pent, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f'm_mod_{pol}_{ang}'] = data_mod[:, i_pent, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f's_mod_{pol}_{ang}'] = data_mod[:, i_pent, i_yr, i_pol, i_orb].astype('float32')
res.loc[:, f'N_data_{pol}_{ang}'] = n_data[:, i_pent, i_yr, i_pol, i_orb].astype('int32')
res.replace(np.nan, -9999, inplace=True)
fname = froot / f'{fbase}_{orb}_p{pent:02}_y{yr:04}.bin'
fid = open(fname, 'wb')
ios[0].write_fortran_block(fid, modes)
ios[0].write_fortran_block(fid, sdate)
ios[0].write_fortran_block(fid, edate)
ios[0].write_fortran_block(fid, lengths)
ios[0].write_fortran_block(fid, angles.astype('float')) # required by LDASsa!!
for f in res.columns.values:
ios[0].write_fortran_block(fid, res[f].values)
fid.close()
else:
res = template.copy()
for ang in angles:
for pol in pols:
res.loc[:, f'm_obs_{pol}_{ang}'] = data['m_obs'].sel(pol=pol, angle=ang, orbit=orb, pentad=pent).to_series()
res.loc[:, f's_obs_{pol}_{ang}'] = data['s_obs'].sel(pol=pol, angle=ang, orbit=orb, pentad=pent).to_series()
res.loc[:, f'm_mod_{pol}_{ang}'] = data['m_mod'].sel(pol=pol, angle=ang, orbit=orb, pentad=pent).to_series()
res.loc[:, f's_mod_{pol}_{ang}'] = data['s_mod'].sel(pol=pol, angle=ang, orbit=orb, pentad=pent).to_series()
res.loc[:, f'N_data_{pol}_{ang}'] = data['N_data'].sel(pol=pol, angle=ang, orbit=orb, pentad=pent).to_series()
res.replace(np.nan, -9999, inplace=True)
fname = froot / f'{fbase}_{orb}_p{pent:02}.bin'
fid = open(fname, 'wb')
ios[0].write_fortran_block(fid, modes)
ios[0].write_fortran_block(fid, sdate)
ios[0].write_fortran_block(fid, edate)
ios[0].write_fortran_block(fid, lengths)
ios[0].write_fortran_block(fid, angles.astype('float')) # required by LDASsa!!
for f in res.columns.values:
ios[0].write_fortran_block(fid, res[f].values)
fid.close()
def EC_ascat_smap_ismn_ldas():
result_file = Path('/Users/u0116961/Documents/work/extended_collocation/ec_ascat_smap_ismn_ldas.csv')
names = ['insitu', 'ascat', 'smap', 'ol', 'da']
combs = list(combinations(names, 2))
ds_ol = LDAS_io('xhourly', 'US_M36_SMAP_TB_OL_noScl').timeseries
ds_da = LDAS_io('xhourly', 'US_M36_SMAP_TB_MadKF_DA_it11').timeseries
ds_da_ana = LDAS_io('ObsFcstAna', 'US_M36_SMAP_TB_MadKF_DA_it11').timeseries['obs_ana']
tg = LDAS_io().grid.tilegrids
modes = ['absolute','longterm','shortterm']
ismn = ISMN_io()
ismn.list = ismn.list.iloc[70::]
ascat = HSAF_io()
smap = SMAP_io()
lut = pd.read_csv(Paths().lut, index_col=0)
i = 0
for meta, ts_insitu in ismn.iter_stations(surface_only=True):
i += 1
logging.info('%i/%i' % (i, len(ismn.list)))
try:
if len(ts_insitu := ts_insitu['2015-04-01':'2020-04-01'].resample('1d').mean().dropna()) < 25:
continue
except:
continue
res = pd.DataFrame(meta.copy()).transpose()
col = meta.ease_col
row = meta.ease_row
colg = col + tg.loc['domain', 'i_offg'] # col / lon
rowg = row + tg.loc['domain', 'j_offg'] # row / lat
tmp_lut = lut[(lut.ease2_col == colg) & (lut.ease2_row == rowg)]
if len(tmp_lut) == 0:
continue
gpi_smap = tmp_lut.index.values[0]
gpi_ascat = tmp_lut.ascat_gpi.values[0]
try:
ts_ascat = ascat.read(gpi_ascat, resample_time=False).resample('1d').mean().dropna()
ts_ascat = ts_ascat[~ts_ascat.index.duplicated(keep='first')]
ts_ascat.name = 'ASCAT'
except:
continue
ts_smap = smap.read(gpi_smap)
if (ts_ascat is None) | (ts_smap is None):
continue
ind = (ds_ol['snow_mass'][:, row, col].values == 0)&(ds_ol['soil_temp_layer1'][:, row, col].values > 277.15)
ts_ol = ds_ol['sm_surface'][:, row, col].to_series().loc[ind].dropna()
ts_ol.index += pd.to_timedelta('2 hours')
ind = (ds_da['snow_mass'][:, row, col].values == 0)&(ds_da['soil_temp_layer1'][:, row, col].values > 277.15)
ts_da = ds_da['sm_surface'][:, row, col].to_series().loc[ind].dropna()
ts_da.index += pd.to_timedelta('2 hours')
for mode in modes:
if mode == 'absolute':
ts_ins = ts_insitu.copy()
ts_asc = ts_ascat.copy()
ts_smp = ts_smap.copy()
ts_ol = ts_ol.copy()
ts_da = ts_da.copy()
else:
ts_ins = calc_anom(ts_ins.copy(), longterm=(mode=='longterm')).dropna()
ts_asc = calc_anom(ts_asc.copy(), longterm=(mode == 'longterm')).dropna()
ts_smp = calc_anom(ts_smp.copy(), longterm=(mode == 'longterm')).dropna()
ts_ol = calc_anom(ts_ol.copy(), longterm=(mode == 'longterm')).dropna()
ts_da = calc_anom(ts_da.copy(), longterm=(mode == 'longterm')).dropna()
tmp = pd.DataFrame(dict(zip(names, [ts_ins, ts_asc, ts_smp, ts_ol, ts_da]))).dropna()
corr = tmp.corr()
ec_res = ecol(tmp[['insitu', 'ascat', 'smap', 'ol', 'da']], correlated=[['smap', 'ol'], ['smap', 'da'], ['ol', 'da']])
res[f'len_{mode}'] = len(tmp)
for c in combs:
res[f'corr_{"_".join(c)}'] = corr.loc[c]
res[f'err_corr_smap_ol_{mode}'] = ec_res['err_corr_smap_ol']
res[f'err_corr_smap_da_{mode}'] = ec_res['err_corr_smap_da']
res[f'err_corr_ol_da_{mode}'] = ec_res['err_corr_ol_da']
if not result_file.exists():
res.to_csv(result_file, float_format='%0.4f')
else:
res.to_csv(result_file, float_format='%0.4f', mode='a', header=False)
def run():
anom = False
longterm = False
fcst_err_corrected = False
exp = 'US_M36_SMAP_TB_MadKF_OL_it11'
io = LDAS_io('ObsFcstAna', exp)
froot = Path(
'/Users/u0116961/Documents/work/MadKF/CLSM/SMAP/rmsd_pert/error_files')
fbase = 'SMOS_fit_Tb_'
dir_out = froot / ((('anom_' +
('lt' if longterm else 'st')) if anom else 'abs') +
('_fcst_corr' if fcst_err_corrected else '_uncorr'))
if not dir_out.exists():
Path.mkdir(dir_out, parents=True)
dtype = template_error_Tb40()[0]
angles = np.array([
40.,
])
orbits = ['A', 'D']
tiles = io.grid.tilecoord['tile_id'].values.astype('int32')
ind_lat = io.grid.tilecoord.loc[:,
'j_indg'].values - io.grid.tilegrids.loc[
'domain', 'j_offg']
ind_lon = io.grid.tilecoord.loc[:,
'i_indg'].values - io.grid.tilegrids.loc[
'domain', 'i_offg']
template = pd.DataFrame(columns=dtype.names, index=tiles).astype('float32')
template['lon'] = io.grid.tilecoord['com_lon'].values.astype('float32')
template['lat'] = io.grid.tilecoord['com_lat'].values.astype('float32')
modes = np.array([0, 0])
sdate = np.array([2015, 4, 1, 0, 0])
edate = np.array([2020, 4, 31, 0, 0])
lengths = np.array([len(tiles),
len(angles)]) # tiles, incidence angles, whatever
dims = io.timeseries['obs_obs'].shape
obs_errstd = np.full(dims[1::], np.nan)
# ----- Calculate anomalies -----
cnt = 0
for spc in np.arange(dims[1]):
for lat in np.arange(dims[2]):
for lon in np.arange(dims[3]):
cnt += 1
logging.info('%i / %i' % (cnt, np.prod(dims[1::])))
try:
if anom:
obs = calc_anom(io.timeseries['obs_obs']
[:, spc, lat,
lon].to_dataframe()['obs_obs'],
longterm=longterm)
fcst = calc_anom(io.timeseries['obs_fcst']
[:, spc, lat,
lon].to_dataframe()['obs_fcst'],
longterm=longterm)
else:
obs = io.timeseries['obs_obs'][:, spc,
lat, lon].to_dataframe(
)['obs_obs']
fcst = io.timeseries['obs_fcst'][:, spc, lat,
lon].to_dataframe(
)['obs_fcst']
fcst_errvar = np.nanmean(
io.timeseries['obs_fcstvar']
[:, spc, lat, lon].values) if fcst_err_corrected else 0
tmp_obs_errstd = (((obs - fcst)**2).mean() -
fcst_errvar)**0.5
if not np.isnan(tmp_obs_errstd):
obs_errstd[spc, lat, lon] = tmp_obs_errstd
except:
pass
np.place(obs_errstd, obs_errstd < 0, 0)
np.place(obs_errstd, obs_errstd > 20, 20)
# ----- write output files -----
for orb in orbits:
# !!! inconsistent with the definition in the obs_paramfile (species) !!!
modes[0] = 1 if orb == 'A' else 0
res = template.copy()
res.index = np.arange(len(res)) + 1
res['row'] = ind_lat
res['col'] = ind_lon
spc = 0 if orb == 'A' else 1
res['err_Tbh'] = obs_errstd[spc, ind_lat, ind_lon]
spc = 2 if orb == 'A' else 3
res['err_Tbv'] = obs_errstd[spc, ind_lat, ind_lon]
res = fill_gaps(res, ['err_Tbh', 'err_Tbv'],
smooth=False,
grid=io.grid)
fname = os.path.join(dir_out, fbase + orb + '.bin')
fid = open(fname, 'wb')
io.write_fortran_block(fid, modes)
io.write_fortran_block(fid, sdate)
io.write_fortran_block(fid, edate)
io.write_fortran_block(fid, lengths)
io.write_fortran_block(fid, angles)
for f in res.drop(['row', 'col'], axis='columns').columns.values:
io.write_fortran_block(fid, res[f].values)
fid.close()
def run_ismn_eval():
experiments = [['SMOSSMAP', 'short']]
names = ['open_loop'] + ['MadKF_SMOS40'
] + ['_'.join(exp) for exp in experiments]
runs = ['US_M36_SMAP_TB_OL_noScl'] + [
'US_M36_SMOS40_TB_MadKF_DA_it613'
] + [f'US_M36_SMAP_TB_DA_scl_{name}' for name in names[2::]]
dss = [LDAS_io('xhourly', run).timeseries for run in runs]
result_file = Path(
'/Users/u0116961/Documents/work/LDAS/2020-03_scaling/validation/ismn_eval.csv'
)
t_ana = pd.DatetimeIndex(
LDAS_io('ObsFcstAna', runs[0]).timeseries.time.values).sort_values()
variables = ['sm_surface', 'sm_rootzone', 'sm_profile']
modes = ['absolute', 'longterm', 'shortterm']
ismn = ISMN_io()
ismn.list = ismn.list.iloc[70::]
i = 0
for meta, ts_insitu in ismn.iter_stations(surface_only=False):
i += 1
logging.info('%i/%i' % (i, len(ismn.list)))
if len(ts_insitu := ts_insitu['2015-04-01':'2020-04-01']) < 50:
continue
res = pd.DataFrame(meta.copy()).transpose()
col = meta.ease_col
row = meta.ease_row
for var in variables:
for mode in modes:
if mode == 'absolute':
ts_ref = ts_insitu[var].dropna()
else:
ts_ref = calc_anom(ts_insitu[var],
longterm=(mode == 'longterm')).dropna()
for run, ts_model in zip(names, dss):
ind = (ts_model['snow_mass'][:, row, col].values == 0) & (
ts_model['soil_temp_layer1'][:, row,
col].values > 277.15)
ts_mod = ts_model[var][:, row, col].to_series().loc[ind]
ts_mod.index += pd.to_timedelta('2 hours')
if mode == 'absolute':
ts_mod = ts_mod.dropna()
else:
ts_mod = calc_anom(
ts_mod, longterm=mode == 'longterm').dropna()
tmp = pd.DataFrame({1: ts_ref, 2: ts_mod}).dropna()
res['len_' + mode + '_' + var] = len(tmp)
r, p = pearsonr(
tmp[1], tmp[2]) if len(tmp) > 10 else (np.nan, np.nan)
res['r_' + run + '_' + mode + '_' + var] = r
# res['p_' + run +'_' + mode + '_' + var] = p
# res['rmsd_' + run +'_' + mode + '_' + var] = np.sqrt(((tmp[1]-tmp[2])**2).mean())
res['ubrmsd_' + run + '_' + mode + '_' + var] = np.sqrt(
(((tmp[1] - tmp[1].mean()) -
(tmp[2] - tmp[2].mean()))**2).mean())
tmp = pd.DataFrame({
1: ts_ref,
2: ts_mod
}).reindex(t_ana).dropna()
res['ana_len_' + mode + '_' + var] = len(tmp)
r, p = pearsonr(
tmp[1], tmp[2]) if len(tmp) > 10 else (np.nan, np.nan)
res['ana_r_' + run + '_' + mode + '_' + var] = r
# res['ana_p_' + run + '_' + mode + '_' + var] = p
# res['ana_rmsd_' + run +'_' + mode + '_' + var] = np.sqrt(((tmp[1]-tmp[2])**2).mean())
res['ana_ubrmsd_' + run + '_' + mode + '_' +
var] = np.sqrt((((tmp[1] - tmp[1].mean()) -
(tmp[2] - tmp[2].mean()))**2).mean())
if not result_file.exists():
res.to_csv(result_file, float_format='%0.4f')
else:
res.to_csv(result_file,
float_format='%0.4f',
mode='a',
header=False)
def run_ascat_eval_part(part, parts):
res_path = Path(
'/Users/u0116961/Documents/work/LDAS/2020-03_scaling/validation')
result_file = res_path / ('ascat_eval_part%i.csv' % part)
lut = pd.read_csv(Paths().lut, index_col=0)
# Split grid cell list for parallelization
subs = (np.arange(parts + 1) * len(lut) / parts).astype('int')
subs[-1] = len(lut)
start = subs[part - 1]
end = subs[part]
# Look-up table that contains the grid cells to iterate over
lut = lut.iloc[start:end, :]
names = ['open_loop', 'SMOSSMAP_short', 'MadKF_SMOS40']
runs = [
'US_M36_SMAP_TB_OL_noScl', 'US_M36_SMAP_TB_DA_scl_SMOSSMAP_short',
'US_M36_SMOS40_TB_MadKF_DA_it613'
]
dss = [LDAS_io('xhourly', run).timeseries for run in runs]
grid = LDAS_io().grid
# t_ana = pd.DatetimeIndex(LDAS_io('ObsFcstAna', runs[0]).timeseries.time.values).sort_values()
ds_obs_smap = (LDAS_io('ObsFcstAna',
'US_M36_SMAP_TB_OL_noScl').timeseries['obs_ana'])
ds_obs_smos = (LDAS_io(
'ObsFcstAna', 'US_M36_SMOS40_TB_MadKF_DA_it613').timeseries['obs_ana'])
modes = ['absolute', 'longterm', 'shortterm']
ascat = HSAF_io()
for cnt, (gpi, data) in enumerate(lut.iterrows()):
print('%i / %i' % (cnt, len(lut)))
col = int(data.ease2_col - grid.tilegrids.loc['domain', 'i_offg'])
row = int(data.ease2_row - grid.tilegrids.loc['domain', 'j_offg'])
res = pd.DataFrame(index=(gpi, ))
res['col'] = int(data.ease2_col)
res['row'] = int(data.ease2_row)
res['lcol'] = col
res['lrow'] = row
try:
ts_ascat = ascat.read(
data['ascat_gpi'],
resample_time=False).resample('1d').mean().dropna()
ts_ascat = ts_ascat[~ts_ascat.index.duplicated(keep='first')]
ts_ascat.name = 'ASCAT'
except:
continue
t_df_smap = ds_obs_smap.sel(species=[1, 2]).isel(lat=row,
lon=col).to_pandas()
t_df_smos = ds_obs_smos.sel(species=[1, 2]).isel(lat=row,
lon=col).to_pandas()
t_ana_smap = t_df_smap[~np.isnan(t_df_smap[1])
| ~np.isnan(t_df_smap[2])].resample(
'1d').mean().index
t_ana_smos = t_df_smos[~np.isnan(t_df_smos[1])
| ~np.isnan(t_df_smos[2])].resample(
'1d').mean().index
var = 'sm_surface'
for mode in modes:
if mode == 'absolute':
ts_ref = ts_ascat.copy()
else:
ts_ref = calc_anom(ts_ascat.copy(),
longterm=(mode == 'longterm')).dropna()
for run, ts_model in zip(names, dss):
t_ana = t_ana_smos if run == 'MadKF_SMOS40' else t_ana_smap
ind = (ts_model['snow_mass'][:, row, col].values == 0) & (
ts_model['soil_temp_layer1'][:, row, col].values > 277.15)
ts_mod = ts_model[var][:, row, col].to_series().loc[ind]
ts_mod.index += pd.to_timedelta('2 hours')
if mode == 'absolute':
ts_mod = ts_mod.dropna()
else:
ts_mod = calc_anom(ts_mod,
longterm=mode == 'longterm').dropna()
ts_mod = ts_mod.resample('1d').mean()
tmp = pd.DataFrame({1: ts_ref, 2: ts_mod}).dropna()
res['len_' + run + '_' + mode] = len(tmp)
r, p = pearsonr(tmp[1], tmp[2]) if len(tmp) > 10 else (np.nan,
np.nan)
res['r_' + run + '_' + mode] = r
# res['p_' + run + '_' + mode] = p
# res['rmsd_' + run + '_' + mode] = np.sqrt(((tmp[1] - tmp[2]) ** 2).mean())
res['ubrmsd_' + run + '_' + mode] = np.sqrt(
(((tmp[1] - tmp[1].mean()) -
(tmp[2] - tmp[2].mean()))**2).mean())
tmp = pd.DataFrame({
1: ts_ref,
2: ts_mod
}).reindex(t_ana).dropna()
res['ana_len_' + run + '_' + mode] = len(tmp)
r, p = pearsonr(tmp[1], tmp[2]) if len(tmp) > 10 else (np.nan,
np.nan)
res['ana_r_' + run + '_' + mode] = r
# res['ana_p_' + run + '_' + mode] = p
# res['ana_rmsd_' + run + '_' + mode] = np.sqrt(((tmp[1] - tmp[2]) ** 2).mean())
res['ana_ubrmsd_' + run + '_' + mode] = np.sqrt(
(((tmp[1] - tmp[1].mean()) -
(tmp[2] - tmp[2].mean()))**2).mean())
if not result_file.exists():
res.to_csv(result_file, float_format='%0.3f')
else:
res.to_csv(result_file,
float_format='%0.3f',
mode='a',
header=False)
def plot_suspicious_stations(root):
statlist = pd.read_csv('/Users/u0116961/Documents/work/MadKF/CLSM/suspicious_stations/station_list_r_diff.csv', index_col=0)
rmsd_root = 'US_M36_SMAP_TB_DA_SM_PROXY_'
rmsd_exps = list(np.sort([x.name.split(rmsd_root)[1] for x in Path('/Users/u0116961/data_sets/LDASsa_runs').glob('*SM_PROXY*')]))
ds_ol = LDAS_io('xhourly', 'US_M36_SMAP_TB_OL_scaled_4K_obserr').timeseries
ds_da = LDAS_io('xhourly', 'US_M36_SMAP_TB_DA_scaled_4K_obserr').timeseries
ts_ana = LDAS_io('ObsFcstAna', 'US_M36_SMAP_TB_DA_scaled_4K_obserr').timeseries['obs_obs']
t_ana = pd.DatetimeIndex(ts_ana.time.values).sort_values()
ascat = HSAF_io()
gpi_list = pd.read_csv(ascat.root / 'warp5_grid' / 'pointlist_warp_conus.csv', index_col=0)
ismn = ISMN_io()
variables = ['sm_surface', 'sm_rootzone']
modes = ['absolute', 'longterm', 'shortterm']
ismn.list.index = ismn.list.network + '_' + ismn.list.station
ismn.list.reindex(statlist.index)
ismn.list = ismn.list.reindex(statlist.index)
for i, (meta, ts_insitu) in enumerate(ismn.iter_stations(surface_only=False)):
if 'tmp_res' in locals():
if (meta.network in tmp_res) & (meta.station in tmp_res):
print(f'Skipping {i}')
continue
try:
res = pd.DataFrame(meta.copy()).transpose()
col = meta.ease_col
row = meta.ease_row
gpi = lonlat2gpi(meta.lon, meta.lat, gpi_list)
ts_ascat = ascat.read(gpi) / 100 * 0.6
if ts_ascat is None:
continue
for mode in modes:
for var in variables:
tmp = statlist[(statlist.network==meta.network)&(statlist.station==meta.station)]
dpr = tmp[f'diff_pearsonr2_{mode}_{var}'].values[0]
dtr = tmp[f'diff_tcar2_{mode}_{var}'].values[0]
if not ((dtr < 0) & (dpr > 0)):
continue
if mode == 'absolute':
ts_asc = ts_ascat.dropna()
else:
ts_asc = calc_anom(ts_ascat, longterm=(mode == 'longterm')).dropna()
ts_asc.name = 'ascat'
ts_asc = pd.DataFrame(ts_asc)
if mode == 'absolute':
ts_ins = ts_insitu[var].dropna()
else:
ts_ins = calc_anom(ts_insitu[var], longterm=(mode == 'longterm')).dropna()
ts_ins.name = 'insitu'
ts_ins = pd.DataFrame(ts_ins)
ind = (ds_ol['snow_mass'].isel(lat=row, lon=col).values == 0) & \
(ds_ol['soil_temp_layer1'].isel(lat=row, lon=col).values > 277.15)
ts_ol = ds_ol[var].isel(lat=row, lon=col).to_series().loc[ind]
ts_ol.index += pd.to_timedelta('2 hours')
ind_obs = np.bitwise_or.reduce(~np.isnan(ts_ana[:, :, row, col].values), 1)
if mode == 'absolute':
ts_ol = ts_ol.reindex(t_ana[ind_obs]).dropna()
else:
ts_ol = calc_anom(ts_ol.reindex(t_ana[ind_obs]), longterm=(mode == 'longterm')).dropna()
ts_ol.name = 'open_loop'
ts_ol = pd.DataFrame(ts_ol)
ind = (ds_da['snow_mass'].isel(lat=row, lon=col).values == 0) & \
(ds_da['soil_temp_layer1'].isel(lat=row, lon=col).values > 277.15)
ts_da = ds_da[var].isel(lat=row, lon=col).to_series().loc[ind]
ts_da.index += pd.to_timedelta('2 hours')
ind_obs = np.bitwise_or.reduce(~np.isnan(ts_ana[:, :, row, col].values), 1)
if mode == 'absolute':
ts_da = ts_da.reindex(t_ana[ind_obs]).dropna()
else:
ts_da = calc_anom(ts_da.reindex(t_ana[ind_obs]), longterm=(mode == 'longterm')).dropna()
ts_da.name = 'DA_4K'
ts_da = pd.DataFrame(ts_da)
matched = df_match(ts_ol, ts_da, ts_asc, ts_ins, window=0.5)
data = ts_ol.join(matched[0]['DA_4K']).join(matched[1]['ascat']).join(matched[2]['insitu']).dropna()
dpr_triplets = data.corr()['DA_4K']['insitu'] - data.corr()['open_loop']['insitu']
if dpr_triplets < 0:
continue
f = plt.figure(figsize=(15, 5))
sns.lineplot(data=data[['open_loop', 'DA_4K', 'insitu']], dashes=False, linewidth=1.5, axes=plt.gca())
plt.title(f'{meta.network} / {meta.station} ({var}): d(Pearson R2) = {dpr_triplets:.3f} , d(TCA R2) = {dtr:.3f}')
fbase = Path('/Users/u0116961/Documents/work/MadKF/CLSM/suspicious_stations/timeseries')
fname = fbase / f'{mode}_{var}_{meta.network}_{meta.station}.png'
f.savefig(fname, dpi=300, bbox_inches='tight')
plt.close()
except:
continue
def noahmp_version_comparison(part, parts):
result_file = Path(
f'/Users/u0116961/Documents/work/LIS/noahmp_version_comparison/result_part{part}.csv'
)
if not result_file.parent.exists():
Path.mkdir(result_file.parent, parents=True)
ascat = HSAF_io()
smap = SMAP_io()
noah3 = Dataset('/Users/u0116961/data_sets/LIS/noahmp36/timeseries.nc')
noah4 = Dataset('/Users/u0116961/data_sets/LIS/noahmp401/timeseries.nc')
lats = noah3['lat'][:, :]
lons = noah3['lon'][:, :]
ind_lat, ind_lon = np.where(~lats.mask)
# Split grid cell list for parallelization
subs = (np.arange(parts + 1) * len(ind_lat) / parts).astype('int')
subs[-1] = len(ind_lat)
start = subs[part - 1]
end = subs[part]
# Look-up table that contains the grid cells to iterate over
ind_lat = ind_lat[start:end]
ind_lon = ind_lon[start:end]
for i, (i_r, i_c) in enumerate(zip(ind_lat, ind_lon)):
i += 1
logging.info(f'{i} / {len(ind_lat)}')
lat = lats[i_r, i_c]
lon = lons[i_r, i_c]
res = pd.DataFrame({'lat': lat, 'lon': lon}, index=(i, ))
for v in [
'SM1', 'SM2', 'SM3', 'SM4', 'ST1', 'ST2', 'ST3', 'ST4', 'LAI',
'SWE'
]:
if ('SM' in v) | ('ST' in v):
res[f'mdiff_{v}'], res[f'sdiff_{v}'], res[f'r2_{v}'] = \
stats(noah4[v[0:2]][:, int(v[-1])-1, i_r, i_c], noah3[v[0:2]][:, int(v[-1])-1, i_r, i_c])
else:
res[f'mdiff_{v}'], res[f'sdiff_{v}'], res[f'r2_{v}'] = \
stats(noah4[v][:, i_r, i_c], noah3[v][:, i_r, i_c])
time = pd.DatetimeIndex(
num2date(noah3['time'][:],
units=noah3['time'].units,
only_use_python_datetimes=True,
only_use_cftime_datetimes=False))
df = pd.DataFrame(
{
'noahmp36': noah3['SM'][:, 0, i_r, i_c],
'noahmp401': noah4['SM'][:, 0, i_r, i_c]
},
index=time)
ts_ascat = ascat.read(lat, lon)
if ts_ascat is None:
ts_ascat = pd.Series(name='ascat')
ts_smap = smap.read(lat, lon)
if ts_smap is None:
ts_smap = pd.Series(name='smap')
df = pd.concat((df, ts_ascat, ts_smap), axis='columns').dropna()
for mode in ['abs', 'anom']:
if mode == 'anom':
for c in df.columns.values:
df[c] = calc_anom(df[c], longterm=False)
res[f'len_{mode}'] = len(df)
ec_res = ecol(df, correlated=[['noahmp36', 'noahmp401']])
for c in df.columns.values:
snr = 10**(ec_res[f'snr_{c}'] / 10)
res[f'tcr2_{mode}_{c}'] = snr / (1 + snr)
if not result_file.exists():
res.to_csv(result_file, float_format='%0.4f')
else:
res.to_csv(result_file,
float_format='%0.4f',
mode='a',
header=False)
