def read_daily_eta(var_id, level, year, month, days=None, concat_dim='TIME', xsub='[330:2:450]', ysub='[60:2:301]', verbose=True): """Return MERRA daily eta-level data for a single variable. Reads a single eta level of daily MERRA data from OpenDAP urls and concatenates into a DataArray for the selected days of the month. Parameters ---------- var_id : str Variable ID. Can be generic ID from the list below, in which case get_varname() is called to get the specific ID for MERRA. Or var_id can be the exact name as it appears in MERRA data files. Generic IDs: {'u', 'v', 'omega', 'hgt', 'T', 'q', 'ps', 'evap', 'precip'} level : int Eta level to extract (0-71). Level 71 is near-surface and level 0 is the top of atmosphere. year, month : int Numeric year and month (1-12). days : list of ints, optional Subset of days to read. If None, all days are included. concat_dim : str, optional Name of dimension for concatenation. xsub, ysub : str, optional Indices of longitude and latitude subsets to extract. verbose : bool, optional If True, print updates while processing files. Returns ------- data : xray.DataArray or xray.Dataset Daily data (3-hourly or hourly) for the month or a selected subset of days. """ varnm = get_varname(var_id) tsub = '[0:1:3]' zsub = '[%d:1:%d]' % (level, level) def datafile(year, mon, day, varnm, xsub, ysub, zsub, tsub): basedir = ('http://goldsmr3.sci.gsfc.nasa.gov:80/opendap/MERRA/' 'MAI6NVANA.5.2.0/') url = ('%s%d/%02d/MERRA100.prod.assim.inst6_3d_ana_Nv.%d%02d%02d.hdf' '?%s%s%s%s%s,XDim%s,YDim%s,Height%s,TIME%s') % (basedir, year, mon, year, mon, day, varnm, tsub, zsub, ysub, xsub, xsub, ysub, zsub, tsub) return url if days is None: days = range(1, atm.days_this_month(year, month) + 1) urls = [datafile(year, month, day, varnm, xsub, ysub, zsub, tsub) for day in atm.makelist(days)] var = atm.load_concat(urls, varnm, concat_dim, verbose=verbose) return var
url_dict[key] = merra.get_urls(year, month, version, nm) return url_dict # Initial setup vargroups = group_variables(varnms, version) calc_kw = {'latlon' : latlon, 'plevs' : plevs, 'dp_vars' : dp_vars, 'sector_lons' : sector_lons} nc_kw = { 'merra2' : {'format' : 'NETCDF4_classic', 'engine' : 'netcdf4'}, 'merra' : {'format' : None, 'engine' : None}}[version] # Read data and concatenate for year in years: dailyfiles = collections.defaultdict(list) for month in months: url_dict = get_url_dict(year, month, version, vargroups) days = range(1, atm.days_this_month(year, month) + 1) jdays = atm.season_days(atm.month_str(month), atm.isleap(year)) for day, jday in zip(days, jdays): files = read_groups(url_dict, vargroups, datadir, year, month, day, jday, calc_kw, nc_kw) for nm in files: dailyfiles[nm] += [files[nm]] # Consolidate daily files into yearly files and delete daily files for nm in dailyfiles: data = atm.load_concat(dailyfiles[nm], concat_dim='day') for varnm in data.data_vars: var = data[varnm] filenm = get_filename(var, version, datadir, year) var.name = var.attrs.get('varnm', varnm) print('Saving to ' + filenm) atm.save_nc(filenm, var)
def calc_fluxes(year, month, var_ids=['u', 'q', 'T', 'theta', 'theta_e', 'hgt'], concat_dim='TIME', scratchdir=None, keepscratch=False, verbose=True): """Return the monthly mean of MERRA daily fluxes. Reads MERRA daily data from OpenDAP urls, computes fluxes, and returns the monthly mean of the daily variable and its zonal and meridional fluxes. Parameters ---------- year, month : int Numeric year and month (1-12). var_ids : list of str, optional IDs of variables to include. concat_dim : str, optional Name of dimension for concatenation. scratchdir : str, optional Directory path to store temporary files while processing data. If omitted, the current working directory is used. keepscratch : bool, optional If True, scratch files are kept in scratchdir. Otherwise they are deleted. verbose : bool, optional If True, print updates while processing files. Returns ------- data : xray.Dataset Mean of daily data and the mean of the daily zonal fluxes (u * var) and meridional fluxes (v * var), for each variable in var_ids. """ nms = [get_varname(nm) for nm in atm.makelist(var_ids)] u_nm, v_nm = get_varname('u'), get_varname('v') nms.extend([u_nm, v_nm]) if 'theta' in nms: nms.append(get_varname('T')) if 'theta_e' in nms: nms.extend([get_varname('T'), get_varname('q')]) nms = set(nms) days = range(1, atm.days_this_month(year, month) + 1) def scratchfile(nm, k, year, month, day): filestr = '%s_level%d_%d%02d%02d.nc' % (nm, k, year, month, day) if scratchdir is not None: filestr = scratchdir + '/' + filestr return filestr # Read metadata from one file to get pressure-level array dataset = 'p_daily' url = url_list(dataset, return_dict=False)[0] with xray.open_dataset(url) as ds: pname = atm.get_coord(ds, 'plev', 'name') plev = atm.get_coord(ds, 'plev') # Pressure levels in Pa for theta/theta_e calcs p_units = atm.pres_units(ds[pname].units) pres = atm.pres_convert(plev, p_units, 'Pa') # Get daily data (raw and calculate extended variables) def get_data(nms, pres, year, month, day, concat_dim, subset_dict, verbose): # Lists of raw and extended variables ids = list(nms) ext = [] for var in ['theta', 'theta_e']: if var in ids: ext.append(var) ids.remove(var) # Read raw data and calculate extended variables data = read_daily(ids, year, month, day, concat_dim=concat_dim, subset_dict=subset_dict, verbose=verbose) if 'theta' in ext: print_if('Computing potential temperature', verbose) T = data[get_varname('T')] data['theta'] = atm.potential_temp(T, pres) if 'theta_e' in ext: print_if('Computing equivalent potential temperature', verbose) T = data[get_varname('T')] q = data[get_varname('q')] data['theta_e'] = atm.equiv_potential_temp(T, pres, q) return data # Iterate over vertical levels for k, p in enumerate(plev): subset_dict = {pname : (p, p)} print_if('Pressure-level %.1f' % p, verbose) files = [] for day in days: # Read data for this level and day ds = get_data(nms, pres[k], year, month, day, concat_dim, subset_dict, verbose) # Compute fluxes print_if('Computing fluxes', verbose) u = ds[get_varname('u')] v = ds[get_varname('v')] for nm in var_ids: var = ds[get_varname(nm)] varname, attrs, _, _ = atm.meta(var) u_var = u * var v_var = v * var u_var.name = get_varname(u_nm) + '*' + var.name units = var.attrs['units'] + ' * ' + u.attrs['units'] u_var.attrs['units'] = units v_var.name = get_varname(v_nm) + '*' + var.name v_var.attrs['units'] = units ds[u_var.name] = u_var ds[v_var.name] = v_var # Save to temporary scratch file filenm = scratchfile('fluxes', k, year, month, day) files.append(filenm) print_if('Saving to scratch file ' + filenm, verbose) ds.to_netcdf(filenm) # Concatenate daily scratch files ds = atm.load_concat(files) if not keepscratch: for f in files: os.remove(f) # Compute monthly means print_if('Computing monthly means', verbose) if k == 0: data = ds.mean(dim=concat_dim) else: data = xray.concat([data, ds.mean(dim=concat_dim)], dim=pname) for var in data.data_vars: data[var].attrs = ds[var].attrs return data