forked from emmashie/pyscripts
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathusgs_timeseries.py
320 lines (254 loc) · 11 KB
/
usgs_timeseries.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
"""
Validate against time series of salinity from USGS sites.
Data sources:
https://waterdata.usgs.gov/nwis/uv?site_no=11162765
San Mateo Bridge
Specific conductance at two elevations.
(uS/cm at 25degC)
Appears to cover 2007 to present.
https://waterdata.usgs.gov/nwis/uv?site_no=373025122065901
Old Dumbarton Bridge near Newark
Just has a pressure gage
Appears to cover 2010 through present.
On NWIS mapper, this is the eastern station of the two on Dumbarton Br
https://waterdata.usgs.gov/nwis/inventory?agency_code=USGS&site_no=373015122071000
Dumbarton Bridge
This has temp, cond., turbidity, depth, but only turbidity is available before
Oct 2013, so overall not useful.
https://waterdata.usgs.gov/nwis/inventory?agency_code=USGS&site_no=374811122235001
Pier 17, San Francisco
Dec 2013 is earliest data.
https://waterdata.usgs.gov/nwis/uv?site_no=374938122251801
Alcatraz Island
Has salinity, spec. cond., includes all of wy2013.
https://waterdata.usgs.gov/nwis/uv?site_no=375607122264701
Richmond-San Rafael Bridge
Two elevations of temp, cond, 2007 to present.
"""
import sys
import os
if 'DISPLAY' not in os.environ:
import matplotlib
matplotlib.use('Agg')
import numpy as np
import matplotlib.pyplot as plt
from stompy.io.local import usgs_nwis
import stompy.model.delft.io as dio
import seawater
from stompy import utils
import os
import xarray as xr
from scipy.ndimage.filters import percentile_filter
from stompy.spatial import proj_utils
from stompy import filters
##
ll2utm=proj_utils.mapper('WGS84','EPSG:26910')
##
base_path="/opt/data/delft/sfb_dfm_v2/runs/"
run_name="wy2013c"
path = "/opt/data/delft/sfb_dfm_v2/runs/%s/DFM_OUTPUT_%s/"%(run_name,run_name)
hisfile = path + "%s_0000_20120801_000000_his.nc"%run_name
mdufile = os.path.join(path,"..","%s.mdu"%run_name)
mdu=dio.MDUFile(mdufile)
t_ref,t_start,t_stop=mdu.time_range()
#t_spunup=np.datetime64("2012-10-01") # clip to "real" period
t_spunup=t_start # show entire simulation
savepath = os.path.join(path + "/validation_plots/salinity_time_series/")
metric_fn = os.path.join(path + "/validation_metrics/salinity_time_series.tex")
os.path.exists(savepath) or os.makedirs(savepath)
##
station_locs={
# elev_mab: upper sensor first on
# San Mateo Bridge
"11162765":dict(lon=-(122 + 14/60. + 59/3600.),
lat=37+35/60.+4/3600.,
elev_mab=[13.4,3.0]),
# Alcatraz:
"374938122251801":dict(lon=-(122+25/60.+18/3600.),
lat=37+49/60.+38/3600.,
elev_mab=[None] # unknown
),
# Richmond-San Rafael Bridge
"375607122264701":dict(lon=-(122+26/60.+47/3600.),
lat=37+56/60.+7/3600.,
elev_mab=[9.1,1.5] ),
# Alviso Slough
"11169750":dict(lon=-(121+59/60.+54/3600.),
lat=37+26/60.+24/3600.,
elev_mab=[None])
}
def usgs_salinity_time_series(station):
# A little tricky - there are two elevations, which have the same parameter
# code of 95 for specific conductance, but ts_id's of 14739 and 14741.
# requesting the parameter once does return an RDB with both in there.
time_labels=[utils.to_datetime(t).strftime('%Y%m%d')
for t in [t_start,t_stop]]
cache_fn="usgs%s-%s_%s-salinity.nc"%(station,time_labels[0],time_labels[1])
if not os.path.exists(cache_fn):
# 95: specific conductance
# 90860: salinity
ds=usgs_nwis.nwis_dataset(station,
t_start,t_stop,
products=[95,90860],
days_per_request=20)
usgs_nwis.add_salinity(ds)
ds.to_netcdf(cache_fn)
ds.close()
##
ds=xr.open_dataset(cache_fn)
ds.attrs['lon']=station_locs[station]['lon']
ds.attrs['lat']=station_locs[station]['lat']
ds.salinity.attrs['elev_mab']=station_locs[station]['elev_mab'][0]
if 'salinity_01' in ds:
ds.salinity_01.attrs['elev_mab']=station_locs[station]['elev_mab'][1]
xy=ll2utm( [ds.attrs['lon'],ds.attrs['lat']] )
ds.attrs['x']=xy[0]
ds.attrs['y']=xy[1]
return ds
usgs_salinity_time_series(station="11169750")
##
# Minor tweaks to model output:
his=xr.open_dataset(hisfile)
his_xy=np.c_[his.station_x_coordinate.isel(time=0).values,
his.station_y_coordinate.isel(time=0).values]
his_dt_s=np.median(np.diff(his.time)) / np.timedelta64(1,'s')
mod_stride=slice(None,None,max(1,int(3600./his_dt_s)))
##
def extract_at_zab(his,field,z_mab,**sel_kw):
depths=his.waterdepth.isel(**sel_kw)
mean_depth=depths.mean()
z_bed=his.zcoordinate_w.isel(time=0,laydimw=0,**sel_kw)
z_sel=float(z_bed+z_mab)
his_z=his.zcoordinate_c.isel(**sel_kw).values
his_values=his[field].isel(**sel_kw).values
values_at_z=np.array( [ np.interp(z_sel,
his_z[i,:],his_values[i,:])
for i in range(len(his.time)) ] )
return values_at_z
tex_fp=None
def figure_usgs_salinity_time_series(station,station_name):
mod_lp_win=usgs_lp_win=40 # 40h lowpass
# Gather USGS data:
ds=usgs_salinity_time_series(station)
usgs_dt_s=np.median(np.diff(ds.time)) / np.timedelta64(1,'s')
usgs_stride=slice(None,None,max(1,int(3600./usgs_dt_s)))
if 'salinity_01' in ds:
obs_salt_davg=np.c_[ds.salinity.values[usgs_stride],
ds.salinity_01.values[usgs_stride]]
obs_salt_davg=np.nanmean(obs_salt_davg,axis=1)
else:
obs_salt_davg=ds.salinity.values[usgs_stride]
dists= utils.dist( his_xy, [ds.x,ds.y] )
station_idx=np.argmin(dists)
print("Nearest model station is %.0f m away from observation"%(dists[station_idx]))
def low_high(d,winsize):
high=percentile_filter(d,95,winsize)
low=percentile_filter(d,5,winsize)
high=filters.lowpass_fir(high,winsize)
low=filters.lowpass_fir(low,winsize)
return low,high
obs_salt_range=low_high(obs_salt_davg,usgs_lp_win)
mod_salt_davg=his.salinity.isel(stations=station_idx).mean(dim='laydim')
mod_salt_range=low_high(mod_salt_davg,mod_lp_win)
# Try picking out a reasonable depth in the model
surf_label="Surface"
bed_label="Bed"
if ds.salinity.attrs['elev_mab'] is not None:
z_mab=ds.salinity.attrs['elev_mab']
surf_label="%.1f mab"%z_mab
mod_salt_surf=extract_at_zab(his,"salinity",z_mab,stations=station_idx)
else:
mod_salt_surf=his.salinity.isel(stations=station_idx,laydim=-1)
if ('salinity_01' in ds) and (ds.salinity_01.attrs['elev_mab'] is not None):
z_mab=ds.salinity_01.attrs['elev_mab']
bed_label="%.1f mab"%z_mab
mod_salt_bed=extract_at_zab(his,"salinity",z_mab,stations=station_idx)
else:
mod_salt_bed=his.salinity.isel(stations=station_idx,laydim=0)
mod_deltaS=mod_salt_bed - mod_salt_surf
if 'salinity_01' in ds:
obs_deltaS=ds.salinity_01.values - ds.salinity.values
else:
obs_deltaS=None
if 1: # plotting time series
plt.figure(1).clf()
fig,ax=plt.subplots(num=1)
fig.set_size_inches([10,4.75],forward=True)
# These roughly mimic the style of water level plots in the validation report.
obs_color='cornflowerblue'
obs_lw=1.5
mod_color='k'
mod_lw=0.8
if 'salinity_01' in ds:
ax.plot(utils.to_dnum(ds.time)[usgs_stride],
filters.lowpass_fir(ds.salinity[usgs_stride],usgs_lp_win),
label='Obs. Upper',lw=obs_lw,color=obs_color)
ax.plot(utils.to_dnum(ds.time)[usgs_stride],
filters.lowpass_fir(ds.salinity_01[usgs_stride],usgs_lp_win),
label='Obs. Lower',lw=obs_lw,color=obs_color,ls='--')
else:
ax.plot(utils.to_dnum(ds.time)[usgs_stride],
filters.lowpass_fir(ds.salinity[usgs_stride],usgs_lp_win),
label='Obs.',lw=obs_lw,color=obs_color)
ax.plot(utils.to_dnum(his.time),
filters.lowpass_fir(mod_salt_surf,40),
label='Model %s'%surf_label,lw=mod_lw,color=mod_color)
ax.plot(utils.to_dnum(his.time),
filters.lowpass_fir(mod_salt_bed,40),
label='Model %s'%bed_label,lw=mod_lw,color=mod_color,ls='--')
if 1: # is it worth showing tidal variability?
ax.fill_between(utils.to_dnum(ds.time)[usgs_stride],
obs_salt_range[0],obs_salt_range[1],
color=obs_color,alpha=0.3,zorder=-1,lw=0)
ax.fill_between(utils.to_dnum(his.time),
mod_salt_range[0],mod_salt_range[1],
color='0.3',alpha=0.3,zorder=-1,lw=0)
ax.set_title(station_name)
ax.xaxis.axis_date()
fig.autofmt_xdate()
ax.set_ylabel('Salinity (ppt)')
ax.legend(fontsize=10,loc='lower left')
ax.axis(xmin=utils.to_dnum(t_spunup),
xmax=utils.to_dnum(t_stop))
fig.tight_layout()
safe_station=station_name.replace(' ','_')
fig.savefig(os.path.join(savepath,"%s.png"%safe_station),
dpi=100)
fig.savefig(os.path.join(savepath,"%s.pdf"%safe_station))
if tex_fp is not None: # metrics
target_time_dnum=utils.to_dnum(his.time.values)
obs_time_dnum=utils.to_dnum(ds.time.values)
obs_salt_davg_intp=utils.interp_near( target_time_dnum,
obs_time_dnum[usgs_stride], obs_salt_davg,
1.5/24 )
valid=np.isfinite(mod_salt_davg*obs_salt_davg_intp).values
valid=( valid
& (target_time_dnum>=utils.to_dnum(t_spunup))
& (target_time_dnum<=utils.to_dnum(t_stop)) )
dnum=target_time_dnum[valid]
mod_values=mod_salt_davg[valid].values
obs_values=obs_salt_davg_intp[valid]
bias=np.mean(mod_values - obs_values)
ms=utils.model_skill(mod_values,obs_values)
r2=np.corrcoef(mod_values,obs_values)[0,1]
rmse=utils.rms(mod_values - obs_values)
tex_fp.write( ("%-16s " # station name
" & %7.3f" # skill
" & %11.2f" # bias
" & %7.3f" # r2
" & %10.2f" # rmse
" \\\ \\hline \n")%( station_name,ms,bias,r2,rmse) )
##
tex_fp=open(metric_fn,"wt")
tex_fp.write("%% output from %s\n"%metric_fn)
tex_fp.write("% Name & Skill & Bias (ppt) & \(r^2\) & RMSE (ppt) \\\ \\hline \n")
# San Mateo Salt:
figure_usgs_salinity_time_series(station="11162765",station_name="San Mateo Bridge")
#
# Alcatraz:
figure_usgs_salinity_time_series(station="374938122251801",station_name="Alcatraz")
# Richmond/San Rafael Bridge
figure_usgs_salinity_time_series(station="375607122264701",station_name="Richmond Bridge")
figure_usgs_salinity_time_series(station="11169750",station_name="Alviso Slough")
if tex_fp != sys.stdout:
tex_fp.close()