def write_pli(g, run_base_dir, src_name, j, suffix):
seg = g.nodes['x'][g.edges['nodes'][j]]
src_feat = (src_name, seg, [src_name + "_0001", src_name + "_0002"])
feat_suffix = dio.add_suffix_to_feature(src_feat, suffix)
dio.write_pli(os.path.join(run_base_dir, '%s%s.pli' % (src_name, suffix)),
[feat_suffix])
return feat_suffix
def add_ocean(run_base_dir,
rel_bc_dir,
run_start,
run_stop,
ref_date,
static_dir,
grid,
old_bc_fn,
all_flows_unit=False,
lag_seconds=0.0,
factor=1.0):
"""
Ocean:
Silvia used:
Water level data from station 46214 (apparently from Yi Chao's ROMS?)
no spatial variation
Maybe salinity from Yi Chao ROMS? That's what the thesis says, but the
actual inputs look like constant 33
Here I'm using data from NOAA Point Reyes.
waterlevel, water temperature from Point Reyes.
When temperature is not available, use constant 15 degrees
factor: a scaling factor applied to tide data to adjust amplitude around MSL.
lag_seconds: to shift ocean boundary condition in time, a positive value
applying it later in time.
"""
# get a few extra days of data to allow for transients in the low pass filter.
pad_time = np.timedelta64(5, 'D')
if 1:
if 0: # This was temporary, while NOAA had an issue with their website.
log.warning("TEMPORARILY USING FORT POINT TIDES")
tide_gage = "9414290" # Fort Point
else:
tide_gage = "9415020" # Pt Reyes
if common.cache_dir is None:
tides_raw_fn = os.path.join(run_base_dir, rel_bc_dir,
'tides-%s-raw.nc' % tide_gage)
if not os.path.exists(tides_raw_fn):
tides = noaa_coops.coops_dataset(
tide_gage,
run_start - pad_time,
run_stop + pad_time, ["water_level", "water_temperature"],
days_per_request=30)
tides.to_netcdf(tides_raw_fn, engine='scipy')
else:
tides = xr.open_dataset(tides_raw_fn)
else:
# rely on caching within noaa_coops
tides = noaa_coops.coops_dataset(
tide_gage,
run_start - pad_time,
run_stop + pad_time, ["water_level", "water_temperature"],
days_per_request='M',
cache_dir=common.cache_dir)
# Those retain station as a dimension of length 1 - drop that dimension
# here:
tides = tides.isel(station=0)
# Fort Point mean tide range is 1.248m, vs. 1.193 at Point Reyes.
# apply rough correction to amplitude.
# S2 phase 316.2 at Pt Reyes, 336.2 for Ft. Point.
# 20 deg difference for a 12h tide, or 30 deg/hr, so
# that's a lag of 40 minutes.
# First go I got this backwards, and wound up with lags
# at Presidio and Alameda of 4600 and 4400s. That was
# with lag_seconds -= 40*60.
# Also got amplitudes 13% high at Presidio, so further correction...
if tide_gage == "9414290":
#
factor *= 1.193 / 1.248 * 1.0 / 1.13
lag_seconds += 35 * 60.
if 1:
# Clean that up, fabricate salinity
water_level = utils.fill_tidal_data(tides.water_level)
# IIR butterworth. Nicer than FIR, with minor artifacts at ends
# 3 hours, defaults to 4th order.
water_level[:] = filters.lowpass(water_level[:].values,
utils.to_dnum(water_level.time),
cutoff=3. / 24)
if 1: # apply factor:
msl = 2.152 - 1.214 # MSL(m) - NAVD88(m) for Point Reyes
if factor != 1.0:
log.info("Scaling tidal forcing amplitude by %.3f" % factor)
water_level[:] = msl + factor * (water_level[:].values - msl)
if 1: # apply lag
if lag_seconds != 0.0:
# sign: if lag_seconds is positive, then I want the result
# for time.values[0] to come from original data at time.valules[0]-lag_seconds
if 0: # Why interpolate here? Just alter the timebase.
water_level[:] = np.interp(
utils.to_dnum(tides.time.values),
utils.to_dnum(tides.time.values) -
lag_seconds / 86400., tides.water_level.values)
else:
# Adjust time base directly.
water_level.time.values[:] = water_level.time.values + np.timedelta64(
lag_seconds, 's')
if 'water_temperature' not in tides:
log.warning(
"Water temperature was not found in NOAA data. Will use constant 15"
)
water_temp = 15 + 0 * tides.water_level
water_temp.name = 'water_temperature'
else:
fill_data(tides.water_temperature)
water_temp = tides.water_temperature
if all_flows_unit:
print("-=-=-=- USING 35 PPT WHILE TESTING! -=-=-=-")
salinity = 35 + 0 * water_level
else:
salinity = 33 + 0 * water_level
salinity.name = 'salinity'
if 1: # Write it all out
# Add a stanza to FlowFMold_bnd.ext:
src_name = 'Sea'
src_feat = dio.read_pli(os.path.join(static_dir,
'%s.pli' % src_name))[0]
forcing_data = [('waterlevelbnd', water_level, '_ssh'),
('salinitybnd', salinity, '_salt'),
('temperaturebnd', water_temp, '_temp')]
for quant, da, suffix in forcing_data:
with open(old_bc_fn, 'at') as fp:
lines = [
"QUANTITY=%s" % quant,
"FILENAME=%s/%s%s.pli" % (rel_bc_dir, src_name, suffix),
"FILETYPE=9", "METHOD=3", "OPERAND=O", ""
]
fp.write("\n".join(lines))
feat_suffix = dio.add_suffix_to_feature(src_feat, suffix)
dio.write_pli(
os.path.join(run_base_dir, rel_bc_dir,
'%s%s.pli' % (src_name, suffix)), [feat_suffix])
# Write the data:
columns = ['elapsed_minutes', da.name]
df = da.to_dataframe().reset_index()
df['elapsed_minutes'] = (df.time.values -
ref_date) / np.timedelta64(60, 's')
if len(feat_suffix) == 3:
node_names = feat_suffix[2]
else:
node_names = [""] * len(feat_suffix[1])
for node_idx, node_name in enumerate(node_names):
# if no node names are known, create the default name of <feature name>_0001
if not node_name:
node_name = "%s%s_%04d" % (src_name, suffix, 1 + node_idx)
tim_fn = os.path.join(run_base_dir, rel_bc_dir,
node_name + ".tim")
df.to_csv(tim_fn,
sep=' ',
index=False,
header=False,
columns=columns)
def add_delta_inflow(mdu,
rel_bc_dir,
static_dir,
grid,
dredge_depth,
all_flows_unit=False,
temp_jersey=True,
temp_rio=True):
"""
Fetch river USGS river flows, add to FlowFM_bnd.ext:
Per Silvia's Thesis:
Jersey: Discharge boundary affected by tides, discharge and temperature taken
from USGS 11337190 SAN JOAQUIN R A JERSEY POINT, 0 salinity
(Note that Dutch Slough should probably be added in here)
Rio Vista: 11455420 SACRAMENTO A RIO VISTA, temperature from DWR station RIV.
0 salinity.
run_base_dir: location of the DFM inputs
run_start,run_stop: target period for therun
statiC_dir: path to static assets, specifically Jersey.pli and RioVista.pli
grid: UnstructuredGrid instance, to be modified at inflow locations
old_bc_fn: path to old-style boundary forcing file
all_flows_unit: if True, override all flows to be 1 m3 s-1 for model diagnostics
"""
# get run directory and time and forcing file info
run_base_dir = mdu.base_path
ref_date, run_start, run_stop = mdu.time_range()
old_bc_fn = mdu.filepath(["external forcing", "ExtForceFile"])
pad = np.timedelta64(3, 'D')
if 1:
# Cache the original data from USGS, then clean it and write to DFM format
jersey_raw_fn = os.path.join(run_base_dir, rel_bc_dir, 'jersey-raw.nc')
if not os.path.exists(jersey_raw_fn):
if temp_jersey == True:
jersey_raw = usgs_nwis.nwis_dataset(
station="11337190",
start_date=run_start - pad,
end_date=run_stop + pad,
products=[
60, # "Discharge, cubic feet per second"
10
], # "Temperature, water, degrees Celsius"
days_per_request=30)
jersey_raw.to_netcdf(jersey_raw_fn, engine='scipy')
if temp_jersey == False:
jersey_raw = usgs_nwis.nwis_dataset(
station="11337190",
start_date=run_start - pad,
end_date=run_stop + pad,
products=[60], # "Discharge, cubic feet per second"
days_per_request=30)
jersey_raw.to_netcdf(jersey_raw_fn, engine='scipy')
rio_vista_raw_fn = os.path.join(run_base_dir, rel_bc_dir,
'rio_vista-raw.nc')
if not os.path.exists(rio_vista_raw_fn):
if temp_rio == True:
rio_vista_raw = usgs_nwis.nwis_dataset(
station="11455420",
start_date=run_start - pad,
end_date=run_stop + pad,
products=[
60, # "Discharge, cubic feet per second"
10
], # "Temperature, water, degrees Celsius"
days_per_request=30)
rio_vista_raw.to_netcdf(rio_vista_raw_fn, engine='scipy')
if temp_rio == False:
rio_vista_raw = usgs_nwis.nwis_dataset(
station="11455420",
start_date=run_start - pad,
end_date=run_stop + pad,
products=[60], # "Discharge, cubic feet per second"
days_per_request=30)
rio_vista_raw.to_netcdf(rio_vista_raw_fn, engine='scipy')
if 1: # Clean and write it all out
jersey_raw = xr.open_dataset(jersey_raw_fn)
rio_vista_raw = xr.open_dataset(rio_vista_raw_fn)
temp_logical = [temp_jersey, temp_rio]
i = 0
for src_name, source in [('Jersey', jersey_raw),
('RioVista', rio_vista_raw)]:
src_feat = dio.read_pli(
os.path.join(static_dir, '%s.pli' % src_name))[0]
dredge_grid.dredge_boundary(grid, src_feat[1], dredge_depth)
if temp_logical[i] == True:
# Add stanzas to FlowFMold_bnd.ext:
for quant, suffix in [('dischargebnd', '_flow'),
('salinitybnd', '_salt'),
('temperaturebnd', '_temp')]:
with open(old_bc_fn, 'at') as fp:
lines = [
"QUANTITY=%s" % quant,
"FILENAME=%s/%s%s.pli" %
(rel_bc_dir, src_name, suffix), "FILETYPE=9",
"METHOD=3", "OPERAND=O", ""
]
fp.write("\n".join(lines))
feat_suffix = dio.add_suffix_to_feature(src_feat, suffix)
dio.write_pli(
os.path.join(run_base_dir, rel_bc_dir,
'%s%s.pli' % (src_name, suffix)),
[feat_suffix])
# Write the data:
if quant == 'dischargebnd':
da = source.stream_flow_mean_daily
da2 = utils.fill_tidal_data(da)
if all_flows_unit:
da2.values[:] = 1.0
else:
# convert ft3/s to m3/s
da2.values[:] *= 0.028316847
elif quant == 'salinitybnd':
da2 = source.stream_flow_mean_daily.copy(deep=True)
da2.values[:] = 0.0
elif quant == 'temperaturebnd':
da = source.temperature_water
da2 = utils.fill_tidal_data(
da) # maybe safer to just interpolate?
if all_flows_unit:
da2.values[:] = 20.0
df = da2.to_dataframe().reset_index()
df['elapsed_minutes'] = (
df.time.values - ref_date) / np.timedelta64(60, 's')
columns = ['elapsed_minutes', da2.name]
if len(feat_suffix) == 3:
node_names = feat_suffix[2]
else:
node_names = [""] * len(feat_suffix[1])
for node_idx, node_name in enumerate(node_names):
# if no node names are known, create the default name of <feature name>_0001
if not node_name:
node_name = "%s%s_%04d" % (src_name, suffix,
1 + node_idx)
tim_fn = os.path.join(run_base_dir, rel_bc_dir,
node_name + ".tim")
df.to_csv(tim_fn,
sep=' ',
index=False,
header=False,
columns=columns)
if temp_logical[i] == False:
# Add stanzas to FlowFMold_bnd.ext:
for quant, suffix in [('dischargebnd', '_flow'),
('salinitybnd', '_salt')]:
with open(old_bc_fn, 'at') as fp:
lines = [
"QUANTITY=%s" % quant,
"FILENAME=%s/%s%s.pli" %
(rel_bc_dir, src_name, suffix), "FILETYPE=9",
"METHOD=3", "OPERAND=O", ""
]
fp.write("\n".join(lines))
feat_suffix = dio.add_suffix_to_feature(src_feat, suffix)
dio.write_pli(
os.path.join(run_base_dir, rel_bc_dir,
'%s%s.pli' % (src_name, suffix)),
[feat_suffix])
# Write the data:
if quant == 'dischargebnd':
da = source.stream_flow_mean_daily
da2 = utils.fill_tidal_data(da)
if all_flows_unit:
da2.values[:] = 1.0
else:
# convert ft3/s to m3/s
da2.values[:] *= 0.028316847
elif quant == 'salinitybnd':
da2 = source.stream_flow_mean_daily.copy(deep=True)
da2.values[:] = 0.0
df = da2.to_dataframe().reset_index()
df['elapsed_minutes'] = (
df.time.values - ref_date) / np.timedelta64(60, 's')
columns = ['elapsed_minutes', da2.name]
if len(feat_suffix) == 3:
node_names = feat_suffix[2]
else:
node_names = [""] * len(feat_suffix[1])
for node_idx, node_name in enumerate(node_names):
# if no node names are known, create the default name of <feature name>_0001
if not node_name:
node_name = "%s%s_%04d" % (src_name, suffix,
1 + node_idx)
tim_fn = os.path.join(run_base_dir, rel_bc_dir,
node_name + ".tim")
df.to_csv(tim_fn,
sep=' ',
index=False,
header=False,
columns=columns)
i += 1
def add_sfbay_freshwater(mdu,
adjusted_pli_fn,
freshwater_dir,
grid,
dredge_depth,
all_flows_unit=False,
time_offset=None):
"""
Add freshwater flows from sfbay_freshwater git submodule.
run_base_dir: location of DFM input files
run_start,run_stop: target period for run, as np.datetime64
ref_date: DFM reference date, as np.datetime64[D]
adjusted_pli_fn: path to pli file to override source locations
freshwater_dir: path to sfbay_freshwater git submodule
grid: UnstructuredGrid instance to be modified at input locations
old_bc_fn: path to old-style forcing input file
time_offset: pull freshwater flows from this timedelta off from the
specified. I.e. if your run is really 2016, but you want 2015 flows,
specify np.timedelta64(-365,'D').
Slightly safer to use days than years here.
"""
run_base_dir = mdu.base_path
ref_date, run_start, run_stop = mdu.time_range()
old_bc_fn = mdu.filepath(["external forcing", "ExtForceFile"])
if time_offset is not None:
run_start = run_start + time_offset
run_stop = run_stop + time_offset
ref_date = ref_date + time_offset
def write_flow_data(stn_ds, src_name, flow_scale=1.0):
df = stn_ds.to_dataframe().reset_index()
df['elapsed_minutes'] = (df.time.values - ref_date) / np.timedelta64(
60, 's')
df['salinity'] = 0 * df.flow_cms
df['temperature'] = 20 + 0 * df.flow_cms
if all_flows_unit:
df['flow_cms'] = 1.0 + 0 * df.flow_cms
else:
df['flow_cms'] = flow_scale * df.flow_cms
for quantity, suffix in [('dischargebnd', '_flow'),
('salinitybnd', '_salt'),
('temperaturebnd', '_temp')]:
lines = [
'QUANTITY=%s' % quantity,
'FILENAME=%s%s.pli' % (src_name, suffix), 'FILETYPE=9',
'METHOD=3', 'OPERAND=O', ""
]
with open(old_bc_fn, 'at') as fp:
fp.write("\n".join(lines))
# read the pli back to know how to name the per-node timeseries
feats = dio.read_pli(
os.path.join(run_base_dir, "%s%s.pli" % (src_name, suffix)))
feat = feats[0] # just one polyline in the file
if len(feat) == 3:
node_names = feat[2]
else:
node_names = [""] * len(feat[1])
for node_idx, node_name in enumerate(node_names):
# if no node names are known, create the default name of <feature name>_0001
if not node_name:
node_name = "%s%s_%04d" % (src_name, suffix, 1 + node_idx)
tim_fn = os.path.join(run_base_dir, node_name + ".tim")
columns = ['elapsed_minutes']
if quantity == 'dischargebnd':
columns.append('flow_cms')
elif quantity == 'salinitybnd':
columns.append('salinity')
elif quantity == 'temperaturebnd':
columns.append('temperature')
df.to_csv(tim_fn,
sep=' ',
index=False,
header=False,
columns=columns)
adjusted_features = dio.read_pli(adjusted_pli_fn)
# Add the freshwater flows - could come from erddap, but use github submodule
# for better control on version
# create a pair of bc and pli files, each including all the sources.
# exact placement will
# be done by hand in the GUI
full_flows_ds = xr.open_dataset(
os.path.join(freshwater_dir, 'outputs', 'sfbay_freshwater.nc'))
# period of the full dataset which will be include for this run
sel = (full_flows_ds.time > run_start - 5 * DAY) & (full_flows_ds.time <
run_stop + 5 * DAY)
flows_ds = full_flows_ds.isel(time=sel)
nudge_by_gage(flows_ds, '11169025', station='SCLARAVCc', decorr_days=20)
nudge_by_gage(flows_ds, '11180700', station='UALAMEDA', decorr_days=20)
if 1: # Special handling for Mowry Slough
mowry_feat = None
src_name = "MOWRY"
for adj_feat in adjusted_features:
if adj_feat[0] == src_name:
mowry_feat = adj_feat
# Write copies for flow, salinity and temperatures
for suffix in ['_flow', '_salt', '_temp']:
# function to add suffix
feat_suffix = dio.add_suffix_to_feature(mowry_feat, suffix)
pli_fn = os.path.join(run_base_dir,
"%s%s.pli" % (src_name, suffix))
dio.write_pli(pli_fn, [feat_suffix])
dredge_grid.dredge_boundary(grid, mowry_feat[1], dredge_depth)
for stni in range(len(flows_ds.station)):
stn_ds = flows_ds.isel(station=stni)
src_name = stn_ds.station.item(
) # kind of a pain to get scalar values back out...
# At least through the GUI, pli files must have more than one node.
# Don't get too big for our britches, just stick a second node 50m east
# if the incoming data is a point, but check for manually set locations
# in adjusted_features
if 1: #-- Write a PLI file
feat = (src_name,
np.array([[stn_ds.utm_x, stn_ds.utm_y],
[stn_ds.utm_x + 50.0, stn_ds.utm_y]]))
# Scan adjusted features for a match to use instead
for adj_feat in adjusted_features:
if adj_feat[0] == src_name:
feat = adj_feat
break
# Write copies for flow, salinity and temperatures
for suffix in ['_flow', '_salt', '_temp']:
# function to add suffix
feat_suffix = dio.add_suffix_to_feature(feat, suffix)
pli_fn = os.path.join(run_base_dir,
"%s%s.pli" % (src_name, suffix))
dio.write_pli(pli_fn, [feat_suffix])
dredge_grid.dredge_boundary(grid, feat[1], dredge_depth)
if 1: #-- Write the time series and stanza in FlowFM_bnd.ext
if src_name == "EBAYS" and mowry_feat is not None:
write_flow_data(stn_ds, src_name)
# EBAYS watershed is something like 13000 acres.
# don't worry about scaling back EBAYS, but add in some extra
# here for MOWRY
write_flow_data(stn_ds, "MOWRY", flow_scale=12.8 / 13000)
else:
write_flow_data(stn_ds, src_name)
full_flows_ds.close()
def add_sfbay_freshwater(mdu,
flow_locations_shp,
grid,
dredge_depth,
time_offset=None):
"""
Add freshwater flows from a combination of gaged and ungaged
watersheds, with simple scaling between them.
This is the approach that was used for SUNTANS runs, was replaced
by BAHM for sfbay_dfm_v2, but is useful for periods outside
existing BAHM runs.
flow_locations_shp: A shapefile with linestring giving each input
location,
fields:
gages: A '|' separate listed of USGS gage numbers from which flow data
will be pulled.
area_sq_mi: watershed area for this flow. This area is compared to the
area in USGS inventory, in order to establish a scaling factor.
amplify: an additional adjustment to scaling factor.
grid: UnstructuredGrid to add the flows to. Depths in this grid may be
"dredged" down to dredge_depth in order to keep inflow locations wet.
time_offset: pull freshwater flows from this timedelta off from the
specified. I.e. if your run is really 2016, but you want 2015 flows,
specify np.timedelta64(-365,'D').
Flows are given 0 salinity and 20degC temperature.
"""
ref_date, run_start, run_stop = mdu.time_range()
if time_offset is not None:
run_start = run_start + time_offset
run_stop = run_stop + time_offset
ref_date = ref_date + time_offset
else:
time_offset = np.timedelta64(0)
flow_features = wkb2shp.shp2geom(flow_locations_shp)
# create a pair of bc and pli files, each including all the sources.
# First need the observations --
# get a list of all the gages that are referenced:
all_gages = np.unique(
np.concatenate([gages.split('|') for gages in flow_features['gages']]))
usgs_gage_cache = os.path.join(local_config.cache_path, 'usgs',
'streamflow')
flows_ds = usgs_nwis.nwis_dataset_collection(
all_gages,
start_date=run_start - 5 * DAY,
end_date=run_stop + 5 * DAY,
products=[60], # streamflow
days_per_request='M', # monthly chunks
frequency='daily', # time resolution of the data
cache_dir=usgs_gage_cache)
usgs_inventory = wkb2shp.shp2geom(usgs_inventory_shp_fn)
station_to_area = dict([("%d" % site, area) for site, area in zip(
usgs_inventory['site_no'], usgs_inventory['drain_area'])])
unique_names = {}
for feat_i, feat in enumerate(flow_features):
gages = feat['gages'].split('|')
sub_flows = flows_ds.sel(site=gages)
featA = feat['area_sq_mi']
gage_areas = np.array(
[float(station_to_area[g] or 'nan') for g in gages])
# assume the variable name here, and that dims are [site,time],
# and units start as cfs.
# Weighted average of reference gages based on watershed area, and
# data availability
# total flow from all reference gages
site_axis = 0
ref_cms = np.nansum(sub_flows['stream_flow_mean_daily'].values,
axis=site_axis) * FT3_to_M3
# area represented by reference gages at each time step
ref_area = np.sum(
np.isfinite(sub_flows['stream_flow_mean_daily'].values) *
gage_areas[:, None],
axis=site_axis)
# avoid division by zero for steps missing all flows
feat_cms = featA * ref_cms
feat_cms[ref_area > 0] /= ref_area[ref_area > 0]
feat_cms[ref_area == 0.0] = np.nan
stn_ds = xr.Dataset()
stn_ds['time'] = flows_ds.time
missing = np.isnan(feat_cms)
if np.all(missing):
raise Exception(
"Composite from gages %s has no data for period %s - %s" %
(gages, stn_ds.time.values[0], stn_ds.time.values[-1]))
if np.any(missing):
logging.warning(
"Composite from gages %s has missing data in period %s - %s" %
(gages, stn_ds.time.values[0], stn_ds.time.values[-1]))
# Best guess is period average
feat_cms[missing] = np.mean(feat_cms[~missing])
stn_ds['flow_cms'] = ('time', ), feat_cms
# sanitize and trim the feature name
src_name = feat['name'].replace(' ', '_').replace(',', '_')[:13]
if src_name in unique_names:
serial = 1
while True:
test_name = "%s_%dser" % (src_name, serial)
if test_name not in unique_names:
break
serial += 1
logging.warning("Source name %s duplicate - will use %s" %
(src_name, test_name))
src_name = test_name
unique_names[src_name] = src_name
if 1: #-- Write a PLI file
pli_feat = (src_name, np.array(feat['geom']))
# Write copies for flow, salinity and temperatures
for suffix in ['_flow', '_salt', '_temp']:
if suffix == '_temp' and not mdu[
'physics', 'Temperature']: # present and not 0.
continue
if suffix == '_salt' and not mdu['physics', 'Salinity']:
continue
# function to add suffix
pli_feat_with_suffix = dio.add_suffix_to_feature(
pli_feat, suffix)
pli_fn = os.path.join(mdu.base_path,
"%s%s.pli" % (src_name, suffix))
dio.write_pli(pli_fn, [pli_feat_with_suffix])
dredge_grid.dredge_boundary(grid, pli_feat[1], dredge_depth)
if 1: #-- Write the time series and stanza in FlowFM_bnd.ext
write_QST_data(mdu, stn_ds, src_name, time_offset=-time_offset)