# load stations and match then to grid points # load station data from files with open(os.path.join(station_data_dir, 'station_infos'), 'r') as f: si_list = f.read().split('\n') si_list = filter(lambda x: len(x) > 0, map(string.strip, si_list)) # for each station id, load the station stations = [] for sinfo in si_list: code = sinfo.split(',')[0] mws = MesoWestStation(sinfo) for suffix in [ '_1', '_2', '_3', '_4', '_5', '_6', '_7' ]: mws.load_station_data(os.path.join(station_data_dir, '%s%s.xls' % (code, suffix))) stations.append(mws) print('Loaded %d stations.' % len(stations)) # check stations for nans stations = filter(MesoWestStation.data_ok, stations) print('Have %d stations with complete data.' % len(stations)) # check stations for zeros and for non-changing data stations = filter(check_zeros, stations) print('Have %d stations with non-zeros in data.' % len(stations)) # setup measurement variances print('Stats for stations that have passed the tests.') for st in stations:
def run_module(): # read in configuration file to execute run print("Reading configuration from [%s]" % sys.argv[1]) with open(sys.argv[1]) as f: cfg = eval(f.read()) # ensure output path exists if not os.path.isdir(cfg['output_dir']): os.mkdir(cfg['output_dir']) # configure diagnostics init_diagnostics(os.path.join(cfg['output_dir'], 'moisture_model_v1_diagnostics.txt')) # Error covariance matrix condition number in kriging diagnostics().configure_tag("skdm_cov_cond", False, True, True) # Assimilation parameters diagnostics().configure_tag("assim_K0", False, True, True) diagnostics().configure_tag("assim_K1", True, True, True) diagnostics().configure_tag("assim_data", False, False, True) diagnostics().configure_tag("obs_residual_var", True, True, True) diagnostics().configure_tag("fm10_model_residual_var", True, True, True) diagnostics().configure_tag("fm10_model_var", False, True, True) diagnostics().configure_tag("fm10_kriging_var", False, True, True) ### Load and preprocess WRF model data # load WRF data wrf_data = WRFModelData(cfg['input_file'], tz_name = 'US/Mountain') # read in spatial and temporal extent of WRF variables lat, lon = wrf_data.get_lats(), wrf_data.get_lons() tm = wrf_data.get_gmt_times() Nt = cfg['Nt'] if cfg['Nt'] is not None else len(tm) dom_shape = lat.shape # retrieve the rain variable rain = wrf_data['RAIN'] # moisture equilibria are now computed from averaged Q,P,T at beginning and end of period Ed, Ew = wrf_data.get_moisture_equilibria() ### Load observation data from the stations # load station data from files with open(os.path.join(cfg['station_data_dir'], cfg['station_list_file']), 'r') as f: si_list = f.read().split('\n') si_list = filter(lambda x: len(x) > 0, map(string.strip, si_list)) # for each station id, load the station stations = [] for sinfo in si_list: code = sinfo.split(',')[0] mws = MesoWestStation(sinfo, wrf_data) for suffix in [ '_1', '_2', '_3', '_4', '_5', '_6', '_7' ]: mws.load_station_data(os.path.join(cfg['station_data_dir'], '%s%s.xls' % (code, suffix))) stations.append(mws) print('Loaded %d stations.' % len(stations)) # check stations for nans stations = filter(MesoWestStation.data_ok, stations) print('Have %d stations with complete data.' % len(stations)) # set the measurement variance of the stations for s in stations: s.set_measurement_variance('fm10', cfg['fm10_meas_var']) # build the observation data obs_data_fm10 = build_observation_data(stations, 'fm10', wrf_data, tm) ### Initialize model and visualization # find maximum moisture overall to set up visualization maxE = 0.5 # construct initial conditions from timestep 1 (because Ed/Ew at zero are zero) E = 0.5 * (Ed[1,:,:] + Ew[1,:,:]) # set up parameters Q = np.eye(9) * cfg['Q'] P0 = np.eye(9) * cfg['P0'] dt = (tm[1] - tm[0]).seconds print("INFO: Computed timestep from WRF is is %g seconds." % dt) K = np.zeros_like(E) V = np.zeros_like(E) mV = np.zeros_like(E) predicted_field = np.zeros_like(E) mresV = np.zeros_like(E) Kf_fn = np.zeros_like(E) Vf_fn = np.zeros_like(E) mid = np.zeros_like(E) Kg = np.zeros((dom_shape[0], dom_shape[1], 9)) cV12 = np.zeros_like(E) # moisture state and observation residual variance estimators mod_re = OnlineVarianceEstimator(np.zeros_like(E), np.ones_like(E) * 0.05, 1) obs_re = OnlineVarianceEstimator(np.zeros((len(stations),)), np.ones(len(stations),) * 0.05, 1) # initialize the mean field model (default fit is 1.0 of equilibrium before new information comes in) mfm = MeanFieldModel(cfg['lock_gamma']) # construct model grid using standard fuel parameters Tk = np.array([1.0, 10.0, 100.0]) * 3600 models = np.zeros(dom_shape, dtype = np.object) models_na = np.zeros_like(models) for p in np.ndindex(dom_shape): models[p] = CellMoistureModel((lat[p], lon[p]), 3, E[p], Tk, P0 = P0) models_na[p] = CellMoistureModel((lat[p], lon[p]), 3, E[p], Tk, P0 = P0) m = None plt.figure(figsize = (12, 8)) ### Run model for each WRF timestep and assimilate data when available for t in range(1, Nt): model_time = tm[t] print("INFO: time: %s, step: %d" % (str(model_time), t)) # run the model update for p in np.ndindex(dom_shape): i, j = p models[p].advance_model(Ed[t-1, i, j], Ew[t-1, i, j], rain[t-1, i, j], dt, Q) models_na[p].advance_model(Ed[t-1, i, j], Ew[t-1, i, j], rain[t-1, i, j], dt, Q) # prepare visualization data f = np.zeros((dom_shape[0], dom_shape[1], 3)) f_na = np.zeros((dom_shape[0], dom_shape[1], 3)) for p in np.ndindex(dom_shape): f[p[0], p[1], :] = models[p].get_state()[:3] f_na[p[0], p[1], :] = models_na[p].get_state()[:3] P = models[p].get_state_covar() cV12[p] = P[0,1] mV[p] = P[1,1] mid[p] = models[p].get_model_ids()[1] diagnostics().push("fm10_model_var", (t, np.mean(mV))) # run Kriging on each observed fuel type Kf = [] Vf = [] fn = [] for obs_data, fuel_ndx in [ (obs_data_fm10, 1) ]: # run the kriging subsystem and the Kalman update only if we have observations if model_time in obs_data: # retrieve observations for current time obs_t = obs_data[model_time] # fit the current estimation of the moisture field to the data base_field = f[:,:,fuel_ndx] mfm.fit_to_data(base_field, obs_data[model_time]) # find differences (residuals) between observed measurements and nearest grid points # use this to update observation residual standard deviation obs_vals = np.array([o.get_value() for o in obs_data[model_time]]) mod_vals = np.array([base_field[o.get_nearest_grid_point()] for o in obs_data[model_time]]) mod_na_vals = np.array([f_na[:,:,fuel_ndx][o.get_nearest_grid_point()] for o in obs_data[model_time]]) obs_re.update_with(obs_vals - mod_vals) diagnostics().push("obs_residual_var", (t, np.mean(obs_re.get_variance()))) # predict the moisture field using observed fuel type predicted_field = mfm.predict_field(base_field) # update the model residual estimator and get current best estimate of variance mod_re.update_with(f[:,:,fuel_ndx] - predicted_field) mresV = mod_re.get_variance() diagnostics().push("fm10_model_residual_var", (t, np.mean(mresV))) # krige observations to grid points Kf_fn, Vf_fn = trend_surface_model_kriging(obs_data[model_time], wrf_data, predicted_field) krig_vals = np.array([Kf_fn[o.get_nearest_grid_point()] for o in obs_data[model_time]]) diagnostics().push("assim_data", (t, fuel_ndx, obs_vals, krig_vals, mod_vals, mod_na_vals)) plot_model_snapshot(cfg, tm, t, fuel_ndx, obs_vals, krig_vals, mod_vals, mod_na_vals) diagnostics().push("fm10_kriging_var", (t, np.mean(Vf_fn))) # append to storage for kriged fields in this time instant Kf.append(Kf_fn) Vf.append(Vf_fn) fn.append(fuel_ndx) # if there were any observations, run the kalman update step if len(fn) > 0: Nobs = len(fn) # run the kalman update in each model independently # gather the standard deviations of the moisture fuel after the Kalman update for p in np.ndindex(dom_shape): O = np.zeros((Nobs,)) V = np.zeros((Nobs, Nobs)) # construct observations for this position for i in range(Nobs): O[i] = Kf[i][p] V[i,i] = Vf[i][p] # execute the Kalman update Kp = models[p].kalman_update(O, V, fn) Kg[p[0], p[1], :] = Kp[:, 0] # push new diagnostic outputs diagnostics().push("assim_K0", (t, np.mean(Kg[:,:,0]))) diagnostics().push("assim_K1", (t, np.mean(Kg[:,:,1]))) # prepare visualization data f = np.zeros((dom_shape[0], dom_shape[1], 3)) for p in np.ndindex(dom_shape): f[p[0], p[1], :] = models[p].get_state()[:3] plt.clf() plt.subplot(3,3,1) render_spatial_field_fast(m, lon, lat, f[:,:,0], '1-hr fuel') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3,3,2) render_spatial_field_fast(m, lon, lat, f[:,:,1], '10-hr fuel') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3,3,3) render_spatial_field_fast(m, lon, lat, f_na[:,:,1], '10hr fuel - no assim') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3,3,4) render_spatial_field_fast(m, lon, lat, Kg[:,:,0], 'Kalman gain for 1-hr fuel') plt.clim([0.0, 3.0]) plt.axis('off') plt.colorbar() plt.subplot(3,3,5) render_spatial_field_fast(m, lon, lat, Kg[:,:,1], 'Kalman gain for 10-hr fuel') plt.clim([0.0, 1.0]) plt.axis('off') plt.colorbar() plt.subplot(3,3,6) render_spatial_field_fast(m, lon, lat, Kf_fn, 'Kriging field') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3,3,7) render_spatial_field_fast(m, lon, lat, mid, 'Model ids') plt.clim([0.0, 5.0]) plt.axis('off') plt.colorbar() plt.subplot(3,3,8) render_spatial_field_fast(m, lon, lat, Vf_fn, 'Kriging variance') plt.clim([0.0, np.max(Vf_fn)]) plt.axis('off') plt.colorbar() plt.subplot(3,3,9) render_spatial_field_fast(m, lon, lat, mresV, 'Model res. variance') plt.clim([0.0, np.max(mresV)]) plt.axis('off') plt.colorbar() plt.savefig(os.path.join(cfg['output_dir'], 'moisture_model_t%03d.png' % t)) # store the diagnostics in a binary file diagnostics().dump_store(os.path.join(cfg['output_dir'], 'diagnostics.bin')) # make a plot of gammas plt.figure() plt.plot(diagnostics().pull('mfm_gamma'), 'bo-') plt.title('Mean field model - gamma') plt.savefig(os.path.join(cfg['output_dir'], 'plot_gamma.png')) plt.figure() plt.plot(diagnostics().pull('skdm_cov_cond')) plt.title('Condition number of covariance matrix') plt.savefig(os.path.join(cfg['output_dir'], 'plot_sigma_cond.png')) # make a plot for each substation plt.figure() D = diagnostics().pull("assim_data") for i in range(len(stations)): plt.clf() # get data for the i-th station t_i = [ o[0] for o in D] obs_i = [ o[2][i] for o in D] krig_i = [ o[3][i] for o in D] mod_i = [ o[4][i] for o in D] mod_na_i = [ o[5][i] for o in D] mx = max(max(obs_i), max(mod_i), max(krig_i), max(mod_i)) plt.plot(t_i, obs_i, 'ro') plt.plot(t_i, krig_i, 'bo-') plt.plot(t_i, mod_i, 'kx-', linewidth = 1.5) plt.plot(t_i, mod_na_i, 'mx-') plt.ylim([0.0, 1.1 * mx]) plt.legend(['Obs.', 'Kriged', 'Model', 'NoAssim']) plt.title('Station observations fit to model and kriging field') plt.savefig(os.path.join(cfg['output_dir'], 'station%02d.png' % (i+1))) plt.figure() plt.plot([d[0] for d in diagnostics().pull("assim_K1")], [d[1] for d in diagnostics().pull("assim_K1")], 'ro-') plt.title('Average Kalman gain') plt.savefig(os.path.join(cfg['output_dir'], 'plot_kalman_gain_10hr.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("assim_K0")], [d[1] for d in diagnostics().pull("assim_K0")], 'ro-') plt.title('Average Kalman gain') plt.savefig(os.path.join(cfg['output_dir'], 'plot_kalman_gain_1hr.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("fm10_model_var")], [d[1] for d in diagnostics().pull("fm10_model_var")], 'ro-') plt.title('Average fm10 model variance') plt.savefig(os.path.join(cfg['output_dir'], 'plot_fm10_model_variance.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("fm10_model_residual_var")], [d[1] for d in diagnostics().pull("fm10_model_residual_var")], 'ro-') plt.title('Average fm10 model residual variance') plt.savefig(os.path.join(cfg['output_dir'], 'plot_fm10_model_residual_variance.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("fm10_kriging_var")], [d[1] for d in diagnostics().pull("fm10_kriging_var")], 'ro-') plt.title('Kriging field variance') plt.savefig(os.path.join(cfg['output_dir'], 'plot_kriging_variance.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("obs_residual_var")], [d[1] for d in diagnostics().pull("obs_residual_var")], 'ro-') plt.title('Observation residual variance') plt.savefig(os.path.join(cfg['output_dir'], 'plot_observation_residual_variance.png')) plt.figure() plt.plot(diagnostics().pull("mfm_mape"), 'ro-', linewidth = 2) plt.title('Mean absolute prediction error of station data') plt.savefig(os.path.join(cfg['output_dir'], 'plot_station_mape.png'))
print("Loaded %d timestamps from WRF." % Nt) # load station data from files with open(cfg['station_list_file'], 'r') as f: si_list = f.read().split('\n') si_list = filter(lambda x: len(x) > 0 and x[0] != '#', map(string.strip, si_list)) # for each station id, load the station stations = [] for code in si_list: mws = MesoWestStation(code) mws.load_station_info(os.path.join(cfg["station_info_dir"], "%s.info" % code)) mws.register_to_grid(wrf_data) mws.load_station_data(os.path.join(cfg["station_obs_dir"], "%s.obs" % code)) stations.append(mws) print('Loaded %d stations.' % len(stations)) # construct basemap for rendering domain_rng = wrf_data.get_domain_extent() m = Basemap(llcrnrlon=domain_rng[0],llcrnrlat=domain_rng[1], urcrnrlon=domain_rng[2],urcrnrlat=domain_rng[3], projection = 'mill') # show the equilibrium field and render position of stations on top plt.figure(figsize = (12,9)) render_spatial_field(m, lon, lat, hgt[0,:,:], 'Station positions over topography') for s in stations: slon, slat = s.get_position()
def run_module(): # read in configuration file to execute run print("Reading configuration from [%s]" % sys.argv[1]) with open(sys.argv[1]) as f: cfg = eval(f.read()) # ensure output path exists if not os.path.isdir(cfg['output_dir']): os.mkdir(cfg['output_dir']) # configure diagnostics init_diagnostics( os.path.join(cfg['output_dir'], 'moisture_model_v1_diagnostics.txt')) # Trend surface model diagnostics diagnostics().configure_tag("kriging_cov_cond", True, True, True) diagnostics().configure_tag("s2_eta_hat", True, True, True) diagnostics().configure_tag("kriging_rmse", True, True, True) diagnostics().configure_tag("kriging_beta", True, True, True) diagnostics().configure_tag("kriging_iters", False, True, True) diagnostics().configure_tag("kriging_subzero_s2_estimates", False, True, True) diagnostics().configure_tag("fm10_kriging_var", True, True, True) diagnostics().configure_tag("f0_summary", True, True, True) diagnostics().configure_tag("f1_summary", True, True, True) diagnostics().configure_tag("f2_summary", True, True, True) diagnostics().configure_tag("f3_summary", True, True, True) # Assimilation parameters diagnostics().configure_tag("K0_summary", True, True, True) diagnostics().configure_tag("K1_summary", True, True, True) diagnostics().configure_tag("K2_summary", True, True, True) diagnostics().configure_tag("K3_summary", True, True, True) diagnostics().configure_tag("assim_info", False, False, True) # Model forecast, analysis and non-assimilated model: state, covariance, errors diagnostics().configure_tag("fm10f_rmse", True, True, True) diagnostics().configure_tag("fm10na_rmse", True, True, True) # all simulation times and all assimilation times (subset) diagnostics().configure_tag("mta", False, True, True) diagnostics().configure_tag("mt", False, True, True) # observation values and their nearest grid points diagnostics().configure_tag("obs_vals", False, True, True) diagnostics().configure_tag("obs_ngp", False, True, True) # in test mode, we will emit observations at the target station # our predictions, the nearest grid point and the test station id diagnostics().configure_tag("test_obs", True, True, True) diagnostics().configure_tag("test_pred", True, True, True) diagnostics().configure_tag("test_ngp", True, True, True) diagnostics().configure_tag("test_station_id", True, True, True) ### Load and preprocess WRF model data # load WRF data wrf_data = WRFModelData(cfg['wrf_output'], ['T2', 'Q2', 'PSFC', 'RAINNC', 'RAINC', 'HGT']) wrf_data.slice_field('HGT') # read in spatial and temporal extent of WRF variables lat, lon = wrf_data.get_lats(), wrf_data.get_lons() hgt = wrf_data['HGT'] tm = wrf_data.get_gmt_times() Nt = cfg['Nt'] if cfg.has_key('Nt') and cfg['Nt'] is not None else len(tm) dom_shape = lat.shape print('INFO: domain size is %d x %d grid points.' % dom_shape) print('INFO: domain extent is lats (%g to %g) lons (%g to %g).' % (np.amin(lat), np.amax(lat), np.amin(lon), np.amax(lon))) # if writing is requested, open output file and set up dimensions if cfg['write_fields'] not in ['all', 'fmc_gc', 'none']: error('FATAL: write_fields must be one of all, fmc_gc or none.') if cfg['write_fields'] == 'none': cfg['write_fields'] = False out_file = None ncfmc_gc, ncfm10a, ncfm10aV, ncfm10f, cnfm10fV, ncfm10na = None, None, None, None, None, None nctsmV, ncKg = None, None if cfg['write_fields']: out_file = netCDF4.Dataset(cfg['output_dir'] + '/fields.nc', 'w') out_file.createDimension('Time', None) out_file.createDimension('fuel_moisture_classes_stag', 5) out_file.createDimension('south_north', dom_shape[0]) out_file.createDimension('west_east', dom_shape[1]) ncfmc_gc = out_file.createVariable( 'FMC_GC', 'f4', ('Time', 'fuel_moisture_classes_stag', 'south_north', 'west_east')) if cfg['write_fields'] == 'all': ncfm10a = out_file.createVariable( 'fm10a', 'f4', ('Time', 'south_north', 'west_east')) ncfm10aV = out_file.createVariable( 'fm10a_var', 'f4', ('Time', 'south_north', 'west_east')) ncfm10na = out_file.createVariable( 'fm10na', 'f4', ('Time', 'south_north', 'west_east')) ncfm10f = out_file.createVariable( 'fm10f', 'f4', ('Time', 'south_north', 'west_east')) ncfm10fV = out_file.createVariable( 'fm10f_var', 'f4', ('Time', 'south_north', 'west_east')) nctsmV = out_file.createVariable( 'tsm_var', 'f4', ('Time', 'south_north', 'west_east')) ncKg = out_file.createVariable( 'kalman_gain', 'f4', ('Time', 'south_north', 'west_east')) print('INFO: opened fields.nc for writing ALL output fields.') else: print('INFO: opened field.nc for writing FMC_GC only.') test_mode = (cfg['run_mode'] == 'test') tgt_station = None if cfg['run_mode'] == 'test': print('INFO: running in TEST mode! Will perform leave-one-out tesing.') tgt_station_id = cfg['target_station_id'] diagnostics().push('test_station_id', tgt_station_id) elif cfg['run_mode'] == 'production': print( 'INFO: running in PRODUCTION mode! Using all observation stations.' ) else: error('FATAL: invalid run mode! Must be "test" or "production".') # determine simulation times tm_start = parse_datetime( cfg['start_time']) if cfg['start_time'] is not None else tm[0] tm_end = parse_datetime( cfg['end_time']) if cfg['end_time'] is not None else tm[-1] # if the required start time or end time are outside the simulation domain, exit with an error if tm_start < tm[0] or tm_end > tm[-1]: print('FATAL: invalid time range, required [%s-%s], availble [%s-%s]' % (str(tm_start), str(tm_end), str(tm[0]), str(tm[-1]))) sys.exit(2) print('INFO: time limits are %s to %s\nINFO: simulation is from %s to %s' % (str(tm_start), str(tm_end), str(tm[0]), str(tm[-1]))) # retrieve dynamic covariates and remove mean at each time point for T2 and PSFC T2 = wrf_data['T2'] #T2 -= np.mean(np.mean(T2,axis=0),axis=0)[np.newaxis,np.newaxis,:] PSFC = wrf_data['PSFC'] #PSFC -= np.mean(np.mean(PSFC,axis=0),axis=0)[np.newaxis,np.newaxis,:] # numerical fix - if it rains at an intensity of less than 0.001 per hour, set rain to zero # also, use log(rain + 1) to prevent wild trend surface model predictions when stations see little rain # but elsewhere there is too much rain # without this, numerical errors in trend surface model may pop up rain = wrf_data['RAIN'] #rain[rain < 0.01] = 0.0 rain = np.log(rain + 1.0) # moisture equilibria are now computed from averaged Q,P,T at beginning and end of period Ed, Ew = wrf_data.get_moisture_equilibria() ### Load observation data from the stations # compute the diagonal distance between grid points grid_dist_km = great_circle_distance(lon[0, 0], lat[0, 0], lon[1, 1], lat[1, 1]) print('INFO: diagonal distance in grid is %g' % grid_dist_km) # load station data from files with open(cfg['station_list_file'], 'r') as f: si_list = f.read().split('\n') si_list = filter(lambda x: len(x) > 0 and x[0] != '#', map(string.strip, si_list)) # for each station id, load the station stations = [] for code in si_list: mws = MesoWestStation(code) mws.load_station_info( os.path.join(cfg["station_info_dir"], "%s.info" % code)) mws.register_to_grid(wrf_data) if mws.get_dist_to_grid() < grid_dist_km / 2.0: print( 'Station %s: lat %g lon %g nearest grid pt %s lat %g lon %g dist_to_grid %g' % (code, mws.lat, mws.lon, str(mws.grid_pt), lat[mws.grid_pt], lon[mws.grid_pt], mws.dist_grid_pt)) mws.load_station_data( os.path.join(cfg["station_data_dir"], "%s.obs" % code)) if test_mode and mws.get_id() == tgt_station_id: tgt_station = mws print( 'INFO: in test mode, targeting station %s (removed from data pool).' % tgt_station_id) diagnostics().push("test_ngp", mws.get_nearest_grid_point()) else: stations.append(mws) print('Loaded %d stations (discarded %d stations, too far from grid).' % (len(stations), len(si_list) - len(stations))) if test_mode and tgt_station is None: error( 'FATAL: in test mode, a station was removed that was not among accepted stations.' ) # build the observation data obs_data_fm10 = build_observation_data(stations, 'FM') # build target data if in test mode tgt_obs_fm10 = None test_ngp = None if test_mode: test_ngp = tgt_station.get_nearest_grid_point() tgt_obs_fm10 = build_observation_data([tgt_station], 'FM') ### Initialize model and visualization # construct initial conditions from timestep 0 E = 0.5 * (Ed[0, :, :] + Ew[0, :, :]) # set up parameters Nk = 4 # we simulate 4 types of fuel Q = np.diag(cfg['Q']) P0 = np.diag(cfg['P0']) Tk = np.array([1.0, 10.0, 100.0, 1000.0]) * 3600 dt = (tm[1] - tm[0]).seconds print("INFO: Computed timestep from WRF is is %g seconds." % dt) mresV = np.zeros_like(E) mid = np.zeros_like(E) Kg = np.zeros((dom_shape[0], dom_shape[1], len(Tk) + 2)) # preprocess all static covariates cov_ids = cfg['covariates'] Xd3 = len(cov_ids) + 1 X = np.zeros((dom_shape[0], dom_shape[1], Xd3)) Xr = np.zeros((dom_shape[0], dom_shape[1], Xd3)) static_covar_map = { "lon": lon - np.mean(lon), "lat": lat - np.mean(lat), "elevation": hgt - np.mean(hgt), "constant": np.ones(dom_shape) } dynamic_covar_map = {"temperature": T2, "pressure": PSFC, "rain": rain} for i in range(1, Xd3): cov_id = cov_ids[i - 1] if cov_id in static_covar_map: print('INFO: found static covariate %s' % cov_id) Xr[:, :, i] = static_covar_map[cov_id] elif cov_id in dynamic_covar_map: print('INFO: found dynamic covariate %s' % cov_id) else: print('FATAL: unknown covariate %s encountered' % cov_id) sys.exit(2) print("INFO: there are %d covariates (including model state)" % Xd3) # retrieve assimilation time window assim_time_win = cfg['assimilation_time_window'] print('GMM init: equilibrium (%g,%g,%g) and at 86,205 %g' % (np.amin(E), np.mean(E), np.amax(E), E[86, 205])) models = GridMoistureModel( E[:, :, np.newaxis][:, :, np.zeros((4, ), dtype=np.int)], Tk, P0) models_na = GridMoistureModel( E[:, :, np.newaxis][:, :, np.zeros((4, ), dtype=np.int)], Tk, P0) ### Run model for each WRF timestep and assimilate data when available t_start, t_end = 1, len(tm) - 1 while tm_start > tm[t_start]: t_start += 1 while tm_end < tm[t_end]: t_end -= 1 # the first FMC_GC value gets filled out with equilibria if cfg['write_fields']: for i in range(Nk): ncfmc_gc[0, i, :, :] = E print('INFO: running simulation from %s (%d) to %s (%d).' % (str(tm[t_start]), t_start, str(tm[t_end]), t_end)) for t in range(t_start, t_end + 1): model_time = tm[t] print("INFO: time: %s, step: %d" % (str(model_time), t)) diagnostics().push("mt", model_time) models_na.advance_model(Ed[t - 1, :, :], Ew[t - 1, :, :], rain[t - 1, :, :], dt, Q) models.advance_model(Ed[t - 1, :, :], Ew[t - 1, :, :], rain[t - 1, :, :], dt, Q) # extract fuel moisture contents [make a fresh copy every iteration!] f = models.get_state().copy() f_na = models_na.get_state().copy() # push 10-hr fuel state & variance of forecast if cfg['write_fields'] == 'all': ncfm10f[t, :, :] = models.get_state()[:, :, 1] ncfm10fV[t, :, :] = models.P[:, :, 1, 1] ncfm10na[t, :, :] = models_na.get_state()[:, :, 1] # examine the assimilated fields (if assimilation is activated) for i in range(4): diagnostics().push("f%d_summary" % i, (t, np.amin( f[:, :, i]), np.mean(f[:, :, i]), np.amax(f[:, :, i]))) if np.any(f[:, :, i] < 0.0): print( "WARN: in field %d there were %d negative moisture values !" % (i, np.count_nonzero(f[:, :, i] < 0.0))) ind = np.unravel_index(np.argmin(f[:, :, i]), f.shape[:2]) print(models.P[ind[0], ind[1], :, :]) print("Full model state at position %d,%d:" % (ind[0], ind[1])) print(models.m_ext[ind[0], ind[1], :]) if np.any(f[:, :, i] > 2.5): print( "WARN: in field %d there were %d moisture values above 2.5!" % (i, np.count_nonzero(f[:, :, i] > 2.5))) ind = np.unravel_index(np.argmax(f[:, :, i]), f.shape[:2]) print(models.P[ind[0], ind[1], :, :]) print("Full model state at position %d,%d:" % (ind[0], ind[1])) print(models.m_ext[ind[0], ind[1], :]) if cfg['assimilate']: # run Kriging on each observed fuel type Kfs, Vfs, fns = [], [], [] for obs_data, fuel_ndx in [(obs_data_fm10, 1)]: # run the kriging subsystem and the Kalman update only if have valid observations valid_times = [ z for z in obs_data.keys() if abs(total_seconds(z - model_time)) < assim_time_win / 2.0 ] print( 'INFO: there are %d valid times at model time %s for fuel index %d' % (len(valid_times), str(model_time), fuel_ndx)) if len(valid_times) > 0: # add model time as time when assimilation occurred diagnostics().push("mta", model_time) # retrieve observations for current time obs_valid_now = [] for z in valid_times: obs_valid_now.extend(obs_data[z]) print( 'INFO: model time %s, assimilating %d observations.' % (str(model_time), len(obs_valid_now))) # construct covariates for this time instant X[:, :, 0] = f[:, :, fuel_ndx] for i in range(1, Xd3): cov_id = cov_ids[i - 1] if cov_id in static_covar_map: X[:, :, i] = Xr[:, :, i] elif cov_id in dynamic_covar_map: F = dynamic_covar_map[cov_id] X[:, :, i] = F[t, :, :] else: error('FATAL: found unknown covariate %s' % cov_id) # find differences (residuals) between observed measurements and nearest grid points obs_vals = [o.get_value() for o in obs_valid_now] obs_ngp = [ o.get_nearest_grid_point() for o in obs_valid_now ] diagnostics().push("obs_vals", obs_vals) diagnostics().push("obs_ngp", obs_ngp) mod_vals = np.array( [f[i, j, fuel_ndx] for i, j in obs_ngp]) mod_na_vals = np.array( [f_na[i, j, fuel_ndx] for i, j in obs_ngp]) diagnostics().push("fm10f_rmse", np.mean((obs_vals - mod_vals)**2)**0.5) diagnostics().push( "fm10na_rmse", np.mean((obs_vals - mod_na_vals)**2)**0.5) # krige observations to grid points Kf_fn, Vf_fn = fit_tsm(obs_valid_now, X) if np.count_nonzero(Kf_fn > 2.5) > 0: rain_t = dynamic_covar_map['rain'][t, :, :] print( 'WARN: in TSM found %d values over 2.5, %d of those had rain, clamped to 2.5' % (np.count_nonzero(Kf_fn > 2.5), np.count_nonzero( np.logical_and(Kf_fn > 2.5, rain_t > 0.0)))) Kf_fn[Kf_fn > 2.5] = 2.5 if np.count_nonzero(Kf_fn < 0.0) > 0: print( 'WARN: in TSM found %d values under 0.0, clamped to 0.0' % np.count_nonzero(Kf_fn < 0.0)) Kf_fn[Kf_fn < 0.0] = 0.0 krig_vals = np.array([Kf_fn[ngp] for ngp in obs_ngp]) diagnostics().push("assim_info", (t, fuel_ndx, obs_vals, krig_vals, mod_vals, mod_na_vals)) diagnostics().push("fm10_kriging_var", (t, np.mean(Vf_fn))) if cfg['write_fields'] == 'all': nctsmV[t, :, :] = Vf_fn # append to storage for kriged fields in this time instant Kfs.append(Kf_fn) Vfs.append(Vf_fn) fns.append(fuel_ndx) # if there were any observations, run the kalman update step if len(fns) > 0: NobsClasses = len(fns) O = np.zeros((dom_shape[0], dom_shape[1], NobsClasses)) V = np.zeros( (dom_shape[0], dom_shape[1], NobsClasses, NobsClasses)) for i in range(NobsClasses): O[:, :, i] = Kfs[i] V[:, :, i, i] = Vfs[i] # execute the Kalman update if len(fns) == 1: models.kalman_update_single2(O, V, fns[0], Kg) else: models.kalman_update(O, V, fns, Kg) # push new diagnostic outputs if cfg['write_fields'] == 'all': ncKg[t, :, :] = Kg[:, :, 1] for i in range(4): diagnostics().push( "K%d_summary" % i, (t, np.amin(Kg[:, :, i]), np.mean( Kg[:, :, i]), np.amax(Kg[:, :, i]))) if np.any(models.get_state()[:, :, i] < 0.0): print( "WARN: in field %d there were %d negative moisture values !" % (i, np.count_nonzero( models.get_state()[:, :, i] < 0.0))) ind = np.unravel_index( np.argmin(models.get_state()[:, :, i]), models.get_state().shape[:2]) print(models.P[ind[0], ind[1], :, :]) print( "TSM input at given position: value %g variance %g" % (O[ind[0], ind[1]], V[ind[0], ind[1]])) print("Model state at given position:") print(models.m_ext[ind[0], ind[1], :]) # store post-assimilation (or forecast depending on whether observations were available) FM-10 state and variance if cfg['write_fields'] == 'all': ncfm10a[t, :, :] = models.get_state()[:, :, 1] ncfm10aV[t, :, :] = models.P[:, :, 1, 1] # we don't care if we assimilated or not, we always check our error on target station if in test mode if test_mode: valid_times = [ z for z in tgt_obs_fm10.keys() if abs(total_seconds(z - model_time)) < assim_time_win / 2.0 ] tgt_i, tgt_j = test_ngp diagnostics().push("test_pred", f[tgt_i, tgt_j, 1]) if len(valid_times) > 0: # this is our target observation [FIXME: this disregards multiple observations if multiple happen to be valid] tgt_obs = tgt_obs_fm10[valid_times[0]][0] obs = tgt_obs.get_value() diagnostics().push("test_obs", obs) else: diagnostics().push("test_obs", np.nan) # store data in wrf_file variable FMC_G if cfg['write_fields']: ncfmc_gc[t, :Nk, :, :] = np.transpose( models.get_state()[:, :, :Nk], axes=[2, 0, 1]) # store the diagnostics in a binary file when done diagnostics().dump_store(os.path.join(cfg['output_dir'], 'diagnostics.bin')) # close the netCDF file (relevant if we did write into FMC_GC) if out_file is not None: out_file.close()
def run_module(): # read in configuration file to execute run print("Reading configuration from [%s]" % sys.argv[1]) with open(sys.argv[1]) as f: cfg = eval(f.read()) # ensure output path exists if not os.path.isdir(cfg['output_dir']): os.mkdir(cfg['output_dir']) # configure diagnostics init_diagnostics(os.path.join(cfg['output_dir'], 'moisture_model_v1_diagnostics.txt')) # Trend surface model diagnostics diagnostics().configure_tag("kriging_cov_cond", True, True, True) diagnostics().configure_tag("s2_eta_hat", True, True, True) diagnostics().configure_tag("kriging_rmse", True, True, True) diagnostics().configure_tag("kriging_beta", True, True, True) diagnostics().configure_tag("kriging_iters", False, True, True) diagnostics().configure_tag("kriging_subzero_s2_estimates", False, True, True) diagnostics().configure_tag("fm10_kriging_var", True, True, True) diagnostics().configure_tag("f0_summary", True, True, True) diagnostics().configure_tag("f1_summary", True, True, True) diagnostics().configure_tag("f2_summary", True, True, True) diagnostics().configure_tag("f3_summary", True, True, True) # Assimilation parameters diagnostics().configure_tag("K0_summary", True, True, True) diagnostics().configure_tag("K1_summary", True, True, True) diagnostics().configure_tag("K2_summary", True, True, True) diagnostics().configure_tag("K3_summary", True, True, True) diagnostics().configure_tag("assim_info", False, False, True) # Model forecast, analysis and non-assimilated model: state, covariance, errors diagnostics().configure_tag("fm10f_rmse", True, True, True) diagnostics().configure_tag("fm10na_rmse", True, True, True) # all simulation times and all assimilation times (subset) diagnostics().configure_tag("mta", False, True, True) diagnostics().configure_tag("mt", False, True, True) # observation values and their nearest grid points diagnostics().configure_tag("obs_vals", False, True, True) diagnostics().configure_tag("obs_ngp", False, True, True) # in test mode, we will emit observations at the target station # our predictions, the nearest grid point and the test station id diagnostics().configure_tag("test_obs", True, True, True) diagnostics().configure_tag("test_pred", True, True, True) diagnostics().configure_tag("test_ngp", True, True, True) diagnostics().configure_tag("test_station_id", True, True, True) ### Load and preprocess WRF model data # load WRF data wrf_data = WRFModelData(cfg['wrf_output'], ['T2', 'Q2', 'PSFC', 'RAINNC', 'RAINC', 'HGT']) wrf_data.slice_field('HGT') # read in spatial and temporal extent of WRF variables lat, lon = wrf_data.get_lats(), wrf_data.get_lons() hgt = wrf_data['HGT'] tm = wrf_data.get_gmt_times() Nt = cfg['Nt'] if cfg.has_key('Nt') and cfg['Nt'] is not None else len(tm) dom_shape = lat.shape print('INFO: domain size is %d x %d grid points.' % dom_shape) print('INFO: domain extent is lats (%g to %g) lons (%g to %g).' % (np.amin(lat),np.amax(lat),np.amin(lon),np.amax(lon))) # if writing is requested, open output file and set up dimensions if cfg['write_fields'] not in [ 'all', 'fmc_gc', 'none']: error('FATAL: write_fields must be one of all, fmc_gc or none.') if cfg['write_fields'] == 'none': cfg['write_fields'] = False out_file = None ncfmc_gc, ncfm10a, ncfm10aV, ncfm10f, cnfm10fV, ncfm10na = None, None, None, None, None, None nctsmV, ncKg = None, None if cfg['write_fields']: out_file = netCDF4.Dataset(cfg['output_dir'] + '/fields.nc', 'w') out_file.createDimension('Time', None) out_file.createDimension('fuel_moisture_classes_stag', 5) out_file.createDimension('south_north', dom_shape[0]) out_file.createDimension('west_east', dom_shape[1]) ncfmc_gc = out_file.createVariable('FMC_GC', 'f4', ('Time', 'fuel_moisture_classes_stag', 'south_north', 'west_east')) if cfg['write_fields'] == 'all': ncfm10a = out_file.createVariable('fm10a', 'f4', ('Time', 'south_north', 'west_east')) ncfm10aV = out_file.createVariable('fm10a_var', 'f4', ('Time', 'south_north', 'west_east')) ncfm10na = out_file.createVariable('fm10na', 'f4', ('Time', 'south_north', 'west_east')) ncfm10f = out_file.createVariable('fm10f', 'f4', ('Time', 'south_north', 'west_east')) ncfm10fV = out_file.createVariable('fm10f_var', 'f4', ('Time', 'south_north', 'west_east')) nctsmV = out_file.createVariable('tsm_var', 'f4', ('Time', 'south_north', 'west_east')) ncKg = out_file.createVariable('kalman_gain', 'f4', ('Time', 'south_north', 'west_east')) print('INFO: opened fields.nc for writing ALL output fields.') else: print('INFO: opened field.nc for writing FMC_GC only.') test_mode = (cfg['run_mode'] == 'test') tgt_station = None if cfg['run_mode'] == 'test': print('INFO: running in TEST mode! Will perform leave-one-out tesing.') tgt_station_id = cfg['target_station_id'] diagnostics().push('test_station_id', tgt_station_id) elif cfg['run_mode'] == 'production': print('INFO: running in PRODUCTION mode! Using all observation stations.') else: error('FATAL: invalid run mode! Must be "test" or "production".') # determine simulation times tm_start = parse_datetime(cfg['start_time']) if cfg['start_time'] is not None else tm[0] tm_end = parse_datetime(cfg['end_time']) if cfg['end_time'] is not None else tm[-1] # if the required start time or end time are outside the simulation domain, exit with an error if tm_start < tm[0] or tm_end > tm[-1]: print('FATAL: invalid time range, required [%s-%s], availble [%s-%s]' % (str(tm_start), str(tm_end), str(tm[0]), str(tm[-1]))) sys.exit(2) print('INFO: time limits are %s to %s\nINFO: simulation is from %s to %s' % (str(tm_start), str(tm_end), str(tm[0]), str(tm[-1]))) # retrieve dynamic covariates and remove mean at each time point for T2 and PSFC T2 = wrf_data['T2'] #T2 -= np.mean(np.mean(T2,axis=0),axis=0)[np.newaxis,np.newaxis,:] PSFC = wrf_data['PSFC'] #PSFC -= np.mean(np.mean(PSFC,axis=0),axis=0)[np.newaxis,np.newaxis,:] # numerical fix - if it rains at an intensity of less than 0.001 per hour, set rain to zero # also, use log(rain + 1) to prevent wild trend surface model predictions when stations see little rain # but elsewhere there is too much rain # without this, numerical errors in trend surface model may pop up rain = wrf_data['RAIN'] #rain[rain < 0.01] = 0.0 rain = np.log(rain + 1.0) # moisture equilibria are now computed from averaged Q,P,T at beginning and end of period Ed, Ew = wrf_data.get_moisture_equilibria() ### Load observation data from the stations # compute the diagonal distance between grid points grid_dist_km = great_circle_distance(lon[0,0], lat[0,0], lon[1,1], lat[1,1]) print('INFO: diagonal distance in grid is %g' % grid_dist_km) # load station data from files with open(cfg['station_list_file'], 'r') as f: si_list = f.read().split('\n') si_list = filter(lambda x: len(x) > 0 and x[0] != '#', map(string.strip, si_list)) # for each station id, load the station stations = [] for code in si_list: mws = MesoWestStation(code) mws.load_station_info(os.path.join(cfg["station_info_dir"], "%s.info" % code)) mws.register_to_grid(wrf_data) if mws.get_dist_to_grid() < grid_dist_km / 2.0: print('Station %s: lat %g lon %g nearest grid pt %s lat %g lon %g dist_to_grid %g' % (code, mws.lat, mws.lon, str(mws.grid_pt), lat[mws.grid_pt], lon[mws.grid_pt], mws.dist_grid_pt)) mws.load_station_data(os.path.join(cfg["station_data_dir"], "%s.obs" % code)) if test_mode and mws.get_id() == tgt_station_id: tgt_station = mws print('INFO: in test mode, targeting station %s (removed from data pool).' % tgt_station_id) diagnostics().push("test_ngp", mws.get_nearest_grid_point()) else: stations.append(mws) print('Loaded %d stations (discarded %d stations, too far from grid).' % (len(stations), len(si_list) - len(stations))) if test_mode and tgt_station is None: error('FATAL: in test mode, a station was removed that was not among accepted stations.') # build the observation data obs_data_fm10 = build_observation_data(stations, 'FM') # build target data if in test mode tgt_obs_fm10 = None test_ngp = None if test_mode: test_ngp = tgt_station.get_nearest_grid_point() tgt_obs_fm10 = build_observation_data([tgt_station], 'FM') ### Initialize model and visualization # construct initial conditions from timestep 0 E = 0.5 * (Ed[0,:,:] + Ew[0,:,:]) # set up parameters Nk = 4 # we simulate 4 types of fuel Q = np.diag(cfg['Q']) P0 = np.diag(cfg['P0']) Tk = np.array([1.0, 10.0, 100.0, 1000.0]) * 3600 dt = (tm[1] - tm[0]).seconds print("INFO: Computed timestep from WRF is is %g seconds." % dt) mresV = np.zeros_like(E) mid = np.zeros_like(E) Kg = np.zeros((dom_shape[0], dom_shape[1], len(Tk)+2)) # preprocess all static covariates cov_ids = cfg['covariates'] Xd3 = len(cov_ids) + 1 X = np.zeros((dom_shape[0], dom_shape[1], Xd3)) Xr = np.zeros((dom_shape[0], dom_shape[1], Xd3)) static_covar_map = { "lon" : lon - np.mean(lon), "lat" : lat - np.mean(lat), "elevation" : hgt - np.mean(hgt), "constant" : np.ones(dom_shape) } dynamic_covar_map = { "temperature" : T2, "pressure" : PSFC, "rain" : rain } for i in range(1, Xd3): cov_id = cov_ids[i-1] if cov_id in static_covar_map: print('INFO: found static covariate %s' % cov_id) Xr[:, :, i] = static_covar_map[cov_id] elif cov_id in dynamic_covar_map: print('INFO: found dynamic covariate %s' % cov_id) else: print('FATAL: unknown covariate %s encountered' % cov_id) sys.exit(2) print("INFO: there are %d covariates (including model state)" % Xd3) # retrieve assimilation time window assim_time_win = cfg['assimilation_time_window'] print('GMM init: equilibrium (%g,%g,%g) and at 86,205 %g' % (np.amin(E),np.mean(E),np.amax(E),E[86,205])) models = GridMoistureModel(E[:,:,np.newaxis][:,:,np.zeros((4,),dtype=np.int)], Tk, P0) models_na = GridMoistureModel(E[:,:,np.newaxis][:,:,np.zeros((4,),dtype=np.int)], Tk, P0) ### Run model for each WRF timestep and assimilate data when available t_start, t_end = 1, len(tm)-1 while tm_start > tm[t_start]: t_start+=1 while tm_end < tm[t_end]: t_end-=1 # the first FMC_GC value gets filled out with equilibria if cfg['write_fields']: for i in range(Nk): ncfmc_gc[0, i, :, :] = E print('INFO: running simulation from %s (%d) to %s (%d).' % (str(tm[t_start]), t_start, str(tm[t_end]), t_end)) for t in range(t_start, t_end+1): model_time = tm[t] print("INFO: time: %s, step: %d" % (str(model_time), t)) diagnostics().push("mt", model_time) models_na.advance_model(Ed[t-1,:,:], Ew[t-1,:,:], rain[t-1,:,:], dt, Q) models.advance_model(Ed[t-1,:,:], Ew[t-1,:,:], rain[t-1,:,:], dt, Q) # extract fuel moisture contents [make a fresh copy every iteration!] f = models.get_state().copy() f_na = models_na.get_state().copy() # push 10-hr fuel state & variance of forecast if cfg['write_fields'] == 'all': ncfm10f[t,:,:] = models.get_state()[:,:,1] ncfm10fV[t,:,:] = models.P[:,:,1,1] ncfm10na[t,:,:] = models_na.get_state()[:,:,1] # examine the assimilated fields (if assimilation is activated) for i in range(4): diagnostics().push("f%d_summary" % i, (t, np.amin(f[:,:,i]), np.mean(f[:,:,i]), np.amax(f[:,:,i]))) if np.any(f[:,:,i] < 0.0): print("WARN: in field %d there were %d negative moisture values !" % (i, np.count_nonzero(f[:,:,i] < 0.0))) ind = np.unravel_index(np.argmin(f[:,:,i]), f.shape[:2]) print(models.P[ind[0],ind[1],:,:]) print("Full model state at position %d,%d:" % (ind[0],ind[1])) print(models.m_ext[ind[0],ind[1],:]) if np.any(f[:,:,i] > 2.5): print("WARN: in field %d there were %d moisture values above 2.5!" % (i, np.count_nonzero(f[:,:,i] > 2.5))) ind = np.unravel_index(np.argmax(f[:,:,i]), f.shape[:2]) print(models.P[ind[0],ind[1],:,:]) print("Full model state at position %d,%d:" % (ind[0],ind[1])) print(models.m_ext[ind[0],ind[1],:]) if cfg['assimilate']: # run Kriging on each observed fuel type Kfs, Vfs, fns = [], [], [] for obs_data, fuel_ndx in [ (obs_data_fm10, 1) ]: # run the kriging subsystem and the Kalman update only if have valid observations valid_times = [z for z in obs_data.keys() if abs(total_seconds(z - model_time)) < assim_time_win/2.0] print('INFO: there are %d valid times at model time %s for fuel index %d' % (len(valid_times), str(model_time), fuel_ndx)) if len(valid_times) > 0: # add model time as time when assimilation occurred diagnostics().push("mta", model_time) # retrieve observations for current time obs_valid_now = [] for z in valid_times: obs_valid_now.extend(obs_data[z]) print('INFO: model time %s, assimilating %d observations.' % (str(model_time), len(obs_valid_now))) # construct covariates for this time instant X[:,:,0] = f[:,:,fuel_ndx] for i in range(1, Xd3): cov_id = cov_ids[i-1] if cov_id in static_covar_map: X[:, :, i] = Xr[:, :, i] elif cov_id in dynamic_covar_map: F = dynamic_covar_map[cov_id] X[:, :, i] = F[t, :, :] else: error('FATAL: found unknown covariate %s' % cov_id) # find differences (residuals) between observed measurements and nearest grid points obs_vals = [o.get_value() for o in obs_valid_now] obs_ngp = [o.get_nearest_grid_point() for o in obs_valid_now] diagnostics().push("obs_vals", obs_vals) diagnostics().push("obs_ngp", obs_ngp) mod_vals = np.array([f[i,j,fuel_ndx] for i,j in obs_ngp]) mod_na_vals = np.array([f_na[i,j,fuel_ndx] for i,j in obs_ngp]) diagnostics().push("fm10f_rmse", np.mean((obs_vals - mod_vals)**2)**0.5) diagnostics().push("fm10na_rmse", np.mean((obs_vals - mod_na_vals)**2)**0.5) # krige observations to grid points Kf_fn, Vf_fn = fit_tsm(obs_valid_now, X) if np.count_nonzero(Kf_fn > 2.5) > 0: rain_t = dynamic_covar_map['rain'][t,:,:] print('WARN: in TSM found %d values over 2.5, %d of those had rain, clamped to 2.5' % (np.count_nonzero(Kf_fn > 2.5), np.count_nonzero(np.logical_and(Kf_fn > 2.5, rain_t > 0.0)))) Kf_fn[Kf_fn > 2.5] = 2.5 if np.count_nonzero(Kf_fn < 0.0) > 0: print('WARN: in TSM found %d values under 0.0, clamped to 0.0' % np.count_nonzero(Kf_fn < 0.0)) Kf_fn[Kf_fn < 0.0] = 0.0 krig_vals = np.array([Kf_fn[ngp] for ngp in obs_ngp]) diagnostics().push("assim_info", (t, fuel_ndx, obs_vals, krig_vals, mod_vals, mod_na_vals)) diagnostics().push("fm10_kriging_var", (t, np.mean(Vf_fn))) if cfg['write_fields'] == 'all': nctsmV[t,:,:] = Vf_fn # append to storage for kriged fields in this time instant Kfs.append(Kf_fn) Vfs.append(Vf_fn) fns.append(fuel_ndx) # if there were any observations, run the kalman update step if len(fns) > 0: NobsClasses = len(fns) O = np.zeros((dom_shape[0], dom_shape[1], NobsClasses)) V = np.zeros((dom_shape[0], dom_shape[1], NobsClasses, NobsClasses)) for i in range(NobsClasses): O[:,:,i] = Kfs[i] V[:,:,i,i] = Vfs[i] # execute the Kalman update if len(fns) == 1: models.kalman_update_single2(O, V, fns[0], Kg) else: models.kalman_update(O, V, fns, Kg) # push new diagnostic outputs if cfg['write_fields'] == 'all': ncKg[t,:,:] = Kg[:,:,1] for i in range(4): diagnostics().push("K%d_summary" % i, (t, np.amin(Kg[:,:,i]), np.mean(Kg[:,:,i]), np.amax(Kg[:,:,i]))) if np.any(models.get_state()[:,:,i] < 0.0): print("WARN: in field %d there were %d negative moisture values !" % (i, np.count_nonzero(models.get_state()[:,:,i] < 0.0))) ind = np.unravel_index(np.argmin(models.get_state()[:,:,i]), models.get_state().shape[:2]) print(models.P[ind[0],ind[1],:,:]) print("TSM input at given position: value %g variance %g" % (O[ind[0],ind[1]], V[ind[0],ind[1]])) print("Model state at given position:") print(models.m_ext[ind[0],ind[1],:]) # store post-assimilation (or forecast depending on whether observations were available) FM-10 state and variance if cfg['write_fields'] == 'all': ncfm10a[t,:,:] = models.get_state()[:,:,1] ncfm10aV[t,:,:] = models.P[:,:,1,1] # we don't care if we assimilated or not, we always check our error on target station if in test mode if test_mode: valid_times = [z for z in tgt_obs_fm10.keys() if abs(total_seconds(z - model_time)) < assim_time_win/2.0] tgt_i, tgt_j = test_ngp diagnostics().push("test_pred", f[tgt_i, tgt_j,1]) if len(valid_times) > 0: # this is our target observation [FIXME: this disregards multiple observations if multiple happen to be valid] tgt_obs = tgt_obs_fm10[valid_times[0]][0] obs = tgt_obs.get_value() diagnostics().push("test_obs", obs) else: diagnostics().push("test_obs", np.nan) # store data in wrf_file variable FMC_G if cfg['write_fields']: ncfmc_gc[t,:Nk,:,:] = np.transpose(models.get_state()[:,:,:Nk],axes=[2,0,1]) # store the diagnostics in a binary file when done diagnostics().dump_store(os.path.join(cfg['output_dir'], 'diagnostics.bin')) # close the netCDF file (relevant if we did write into FMC_GC) if out_file is not None: out_file.close()
def run_module(): # read in configuration file to execute run print("Reading configuration from [%s]" % sys.argv[1]) with open(sys.argv[1]) as f: cfg = eval(f.read()) # ensure output path exists if not os.path.isdir(cfg['output_dir']): os.mkdir(cfg['output_dir']) # configure diagnostics init_diagnostics( os.path.join(cfg['output_dir'], 'moisture_model_v1_diagnostics.txt')) # Error covariance matrix condition number in kriging diagnostics().configure_tag("skdm_cov_cond", False, True, True) # Assimilation parameters diagnostics().configure_tag("assim_K0", False, True, True) diagnostics().configure_tag("assim_K1", True, True, True) diagnostics().configure_tag("assim_data", False, False, True) diagnostics().configure_tag("fm10_model_var", False, True, True) diagnostics().configure_tag("fm10_kriging_var", False, True, True) ### Load and preprocess WRF model data # load WRF data wrf_data = WRFModelData(cfg['input_file'], tz_name='US/Mountain') # read in spatial and temporal extent of WRF variables lat, lon = wrf_data.get_lats(), wrf_data.get_lons() tm = wrf_data.get_gmt_times() Nt = cfg['Nt'] if cfg.has_key('Nt') and cfg['Nt'] is not None else len(tm) dom_shape = lat.shape # retrieve the rain variable rain = wrf_data['RAIN'] # moisture equilibria are now computed from averaged Q,P,T at beginning and end of period Ed, Ew = wrf_data.get_moisture_equilibria() ### Load observation data from the stations # load station data from files with open(os.path.join(cfg['station_data_dir'], cfg['station_list_file']), 'r') as f: si_list = f.read().split('\n') si_list = filter(lambda x: len(x) > 0 and x[0] != '#', map(string.strip, si_list)) # for each station id, load the station stations = [] for code in si_list: mws = MesoWestStation(code) mws.load_station_info( os.path.join(cfg["station_data_dir"], "%s.info" % code)) mws.register_to_grid(wrf_data) mws.load_station_data( os.path.join(cfg["station_data_dir"], "%s.obs" % code)) stations.append(mws) print('Loaded %d stations.' % len(stations)) # check stations for nans stations = filter(MesoWestStation.data_ok, stations) print('Have %d stations with complete data.' % len(stations)) # build the observation data # obs_data_fm10 = build_observation_data(stations, 'FM') obs_data_fm10 = {} ### Initialize model and visualization # find maximum moisture overall to set up visualization maxE = 0.5 # construct initial conditions from timestep 1 (because Ed/Ew at zero are zero) E = 0.5 * (Ed[1, :, :] + Ew[1, :, :]) # set up parameters Q = np.eye(9) * cfg['Q'] P0 = np.eye(9) * cfg['P0'] dt = (tm[1] - tm[0]).seconds print("INFO: Computed timestep from WRF is is %g seconds." % dt) K = np.zeros_like(E) V = np.zeros_like(E) mV = np.zeros_like(E) predicted_field = np.zeros_like(E) mresV = np.zeros_like(E) Kf_fn = np.zeros_like(E) Vf_fn = np.zeros_like(E) mid = np.zeros_like(E) Kg = np.zeros((dom_shape[0], dom_shape[1], 9)) cV12 = np.zeros_like(E) # initialize the mean field model (default fit is 1.0 of equilibrium before new information comes in) mfm = MeanFieldModel(cfg['lock_gamma']) # construct model grid using standard fuel parameters Tk = np.array([1.0, 10.0, 100.0]) * 3600 models = np.zeros(dom_shape, dtype=np.object) models_na = np.zeros_like(models) for p in np.ndindex(dom_shape): models[p] = CellMoistureModel((lat[p], lon[p]), 3, E[p], Tk, P0=P0) models_na[p] = CellMoistureModel((lat[p], lon[p]), 3, E[p], Tk, P0=P0) m = None plt.figure(figsize=(12, 8)) ### Run model for each WRF timestep and assimilate data when available for t in range(1, Nt): model_time = tm[t] print("INFO: time: %s, step: %d" % (str(model_time), t)) # run the model update for p in np.ndindex(dom_shape): i, j = p models[p].advance_model(Ed[t - 1, i, j], Ew[t - 1, i, j], rain[t - 1, i, j], dt, Q) models_na[p].advance_model(Ed[t - 1, i, j], Ew[t - 1, i, j], rain[t - 1, i, j], dt, Q) # prepare visualization data f = np.zeros((dom_shape[0], dom_shape[1], 3)) f_na = np.zeros((dom_shape[0], dom_shape[1], 3)) for p in np.ndindex(dom_shape): f[p[0], p[1], :] = models[p].get_state()[:3] f_na[p[0], p[1], :] = models_na[p].get_state()[:3] P = models[p].get_state_covar() cV12[p] = P[0, 1] mV[p] = P[1, 1] mid[p] = models[p].get_model_ids()[1] diagnostics().push("fm10_model_var", (t, np.mean(mV))) # run Kriging on each observed fuel type Kf = [] Vf = [] fn = [] for obs_data, fuel_ndx in [(obs_data_fm10, 1)]: # run the kriging subsystem and the Kalman update only if we have observations if model_time in obs_data: # retrieve observations for current time obs_t = obs_data[model_time] # fit the current estimation of the moisture field to the data base_field = f[:, :, fuel_ndx] mfm.fit_to_data(base_field, obs_data[model_time]) # find differences (residuals) between observed measurements and nearest grid points # use this to update observation residual standard deviation obs_vals = np.array( [o.get_value() for o in obs_data[model_time]]) mod_vals = np.array([ base_field[o.get_nearest_grid_point()] for o in obs_data[model_time] ]) mod_na_vals = np.array([ f_na[:, :, fuel_ndx][o.get_nearest_grid_point()] for o in obs_data[model_time] ]) # predict the moisture field using observed fuel type predicted_field = mfm.predict_field(base_field) # krige observations to grid points Kf_fn, Vf_fn = trend_surface_model_kriging( obs_data[model_time], wrf_data, predicted_field) krig_vals = np.array([ Kf_fn[o.get_nearest_grid_point()] for o in obs_data[model_time] ]) diagnostics().push( "assim_data", (t, fuel_ndx, obs_vals, krig_vals, mod_vals, mod_na_vals)) plot_model_snapshot(cfg, tm, t, fuel_ndx, obs_vals, krig_vals, mod_vals, mod_na_vals) diagnostics().push("fm10_kriging_var", (t, np.mean(Vf_fn))) # append to storage for kriged fields in this time instant Kf.append(Kf_fn) Vf.append(Vf_fn) fn.append(fuel_ndx) # if there were any observations, run the kalman update step if len(fn) > 0: Nobs = len(fn) # run the kalman update in each model independently # gather the standard deviations of the moisture fuel after the Kalman update for p in np.ndindex(dom_shape): O = np.zeros((Nobs, )) V = np.zeros((Nobs, Nobs)) # construct observations for this position for i in range(Nobs): O[i] = Kf[i][p] V[i, i] = Vf[i][p] # execute the Kalman update Kp = models[p].kalman_update(O, V, fn) Kg[p[0], p[1], :] = Kp[:, 0] # push new diagnostic outputs diagnostics().push("assim_K0", (t, np.mean(Kg[:, :, 0]))) diagnostics().push("assim_K1", (t, np.mean(Kg[:, :, 1]))) # prepare visualization data f = np.zeros((dom_shape[0], dom_shape[1], 3)) for p in np.ndindex(dom_shape): f[p[0], p[1], :] = models[p].get_state()[:3] plt.clf() plt.subplot(3, 3, 1) render_spatial_field_fast(m, lon, lat, f[:, :, 0], '1-hr fuel') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3, 3, 2) render_spatial_field_fast(m, lon, lat, f[:, :, 1], '10-hr fuel') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3, 3, 3) render_spatial_field_fast(m, lon, lat, f_na[:, :, 1], '10hr fuel - no assim') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3, 3, 4) render_spatial_field_fast(m, lon, lat, Kg[:, :, 0], 'Kalman gain for 1-hr fuel') plt.clim([0.0, 3.0]) plt.axis('off') plt.colorbar() plt.subplot(3, 3, 5) render_spatial_field_fast(m, lon, lat, Kg[:, :, 1], 'Kalman gain for 10-hr fuel') plt.clim([0.0, 1.0]) plt.axis('off') plt.colorbar() plt.subplot(3, 3, 6) render_spatial_field_fast(m, lon, lat, Kf_fn, 'Kriging field') plt.clim([0.0, maxE]) plt.axis('off') plt.colorbar() plt.subplot(3, 3, 7) render_spatial_field_fast(m, lon, lat, mid, 'Model ids') plt.clim([0.0, 5.0]) plt.axis('off') plt.colorbar() plt.subplot(3, 3, 8) render_spatial_field_fast(m, lon, lat, Vf_fn, 'Kriging variance') plt.clim([0.0, np.max(Vf_fn)]) plt.axis('off') plt.colorbar() # plt.subplot(3,3,9) # render_spatial_field_fast(m, lon, lat, mresV, 'Model variance') # plt.clim([0.0, np.max(mresV)]) # plt.axis('off') # plt.colorbar() plt.savefig( os.path.join(cfg['output_dir'], 'moisture_model_t%03d.png' % t)) # store the diagnostics in a binary file diagnostics().dump_store(os.path.join(cfg['output_dir'], 'diagnostics.bin')) # make a plot of gammas plt.figure() plt.plot(diagnostics().pull('mfm_gamma'), 'bo-') plt.title('Mean field model - gamma') plt.savefig(os.path.join(cfg['output_dir'], 'plot_gamma.png')) plt.figure() plt.plot(diagnostics().pull('skdm_cov_cond')) plt.title('Condition number of covariance matrix') plt.savefig(os.path.join(cfg['output_dir'], 'plot_sigma_cond.png')) # make a plot for each substation plt.figure() D = diagnostics().pull("assim_data") for i in range(len(stations)): plt.clf() # get data for the i-th station t_i = [o[0] for o in D] obs_i = [o[2][i] for o in D] krig_i = [o[3][i] for o in D] mod_i = [o[4][i] for o in D] mod_na_i = [o[5][i] for o in D] mx = max(max(obs_i), max(mod_i), max(krig_i), max(mod_i)) plt.plot(t_i, obs_i, 'ro') plt.plot(t_i, krig_i, 'bo-') plt.plot(t_i, mod_i, 'kx-', linewidth=1.5) plt.plot(t_i, mod_na_i, 'mx-') plt.ylim([0.0, 1.1 * mx]) plt.legend(['Obs.', 'Kriged', 'Model', 'NoAssim']) plt.title('Station observations fit to model and kriging field') plt.savefig( os.path.join(cfg['output_dir'], 'station%02d.png' % (i + 1))) plt.figure() plt.plot([d[0] for d in diagnostics().pull("assim_K1")], [d[1] for d in diagnostics().pull("assim_K1")], 'ro-') plt.title('Average Kalman gain') plt.savefig(os.path.join(cfg['output_dir'], 'plot_kalman_gain_10hr.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("assim_K0")], [d[1] for d in diagnostics().pull("assim_K0")], 'ro-') plt.title('Average Kalman gain') plt.savefig(os.path.join(cfg['output_dir'], 'plot_kalman_gain_1hr.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("fm10_model_var")], [d[1] for d in diagnostics().pull("fm10_model_var")], 'ro-') plt.title('Average fm10 model variance') plt.savefig(os.path.join(cfg['output_dir'], 'plot_fm10_model_variance.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("fm10_model_residual_var")], [d[1] for d in diagnostics().pull("fm10_model_residual_var")], 'ro-') plt.title('Average fm10 model residual variance') plt.savefig( os.path.join(cfg['output_dir'], 'plot_fm10_model_residual_variance.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("fm10_kriging_var")], [d[1] for d in diagnostics().pull("fm10_kriging_var")], 'ro-') plt.title('Kriging field variance') plt.savefig(os.path.join(cfg['output_dir'], 'plot_kriging_variance.png')) plt.figure() plt.plot([d[0] for d in diagnostics().pull("obs_residual_var")], [d[1] for d in diagnostics().pull("obs_residual_var")], 'ro-') plt.title('Observation residual variance') plt.savefig( os.path.join(cfg['output_dir'], 'plot_observation_residual_variance.png')) plt.figure() plt.plot(diagnostics().pull("mfm_mape"), 'ro-', linewidth=2) plt.title('Mean absolute prediction error of station data') plt.savefig(os.path.join(cfg['output_dir'], 'plot_station_mape.png'))
# load station data from files with open(cfg['station_list_file'], 'r') as f: si_list = f.read().split('\n') si_list = filter(lambda x: len(x) > 0 and x[0] != '#', map(string.strip, si_list)) # for each station id, load the station stations = [] for code in si_list: mws = MesoWestStation(code) mws.load_station_info( os.path.join(cfg["station_info_dir"], "%s.info" % code)) mws.register_to_grid(wrf_data) mws.load_station_data( os.path.join(cfg["station_obs_dir"], "%s.obs" % code)) stations.append(mws) print('Loaded %d stations.' % len(stations)) # construct basemap for rendering domain_rng = wrf_data.get_domain_extent() m = Basemap(llcrnrlon=domain_rng[0], llcrnrlat=domain_rng[1], urcrnrlon=domain_rng[2], urcrnrlat=domain_rng[3], projection='mill') # show the equilibrium field and render position of stations on top plt.figure(figsize=(12, 9)) render_spatial_field(m, lon, lat, hgt[0, :, :],
wrf_data = WRFModelData(os.path.join(station_data_dir, wrf_data_file), fields = ['T2', 'Q2', 'PSFC', fm_var_name, 'FMC_EQUI'], tz_name = 'GMT') lon, lat, tm = wrf_data.get_lons(), wrf_data.get_lats(), wrf_data.get_times() efms, wrf_equi = wrf_data[fm_var_name], wrf_data['FMC_EQUI'] T2 = wrf_data['T2'] print('Loaded %d times from WRF output (%s - %s).' % (len(tm), str(tm[0]), str(tm[-1]))) # for each station id, load the station stations = [] for sinfo in si_list: code = sinfo.split(',')[0] mws = MesoWestStation(sinfo, wrf_data) for suffix in [ '_1', '_2', '_3', '_4', '_5', '_6', '_7' ]: mws.load_station_data(os.path.join(station_data_dir, '%s%s.xls' % (code, suffix))) stations.append(mws) print('Loaded %d stations.' % len(stations)) # check stations for nans stations = filter(MesoWestStation.data_ok, stations) print('Have %d stations with complete data.' % len(stations)) # setup measurement variances for st in stations: st.set_measurement_variance('fm10', 0.2) st.set_measurement_variance('air_temp', 0.5) st.set_measurement_variance('rh', 10) # compute the mean of the equilibria