viirs_l1b_l2.py

import numpy as np
import h5py
from util.util import get_grid_values, get_grid_values_all, is_night, is_day, compute_lwc_iwc
import glob
from aeolus.datasource import CLAVRx_VIIRS
from icing.moon_phase import *

keep_out_opd = ['/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/arm/2019/11/02/clavrx_VNP02IMG.A2019306.1912.001.2019307003236.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/arm/2019/04/13/clavrx_VNP02IMG.A2019103.1918.001.2019104005120.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/sioux_falls/2019/05/25/clavrx_VNP02IMG.A2019145.1936.001.2019146005424.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/sioux_falls/2019/11/01/clavrx_VNP02IMG.A2019305.1936.001.2019306005913.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/sioux_falls/2019/03/01/clavrx_VNP02IMG.A2019060.1930.001.2019061005942.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/table_mountain/2019/12/01/clavrx_VNP02IMG.A2019335.2012.001.2019336013827.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/table_mountain/2019/05/18/clavrx_VNP02IMG.A2019138.2006.001.2019139013059.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/fort_peck/2019/01/28/clavrx_VNP02IMG.A2019028.1930.001.2019029005408.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/fort_peck/2019/08/08/clavrx_VNP02IMG.A2019220.1930.001.2019221010714.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/madison/2019/10/13/clavrx_VNP02IMG.A2019286.1848.001.2019287001722.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/madison/2019/03/20/clavrx_VNP02IMG.A2019079.1830.001.2019079235918.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/madison/2019/12/26/clavrx_VNP02IMG.A2019360.1900.001.2019361001327.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/desert_rock/2019/02/05/clavrx_VNP02IMG.A2019036.2018.001.2019037030301.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/desert_rock/2019/03/30/clavrx_VNP02IMG.A2019089.2024.001.2019090015614.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/bondville_il/2019/11/03/clavrx_VNP02IMG.A2019307.1854.001.2019308001716.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/goodwin_creek/2019/04/15/clavrx_VNP02IMG.A2019105.1842.001.2019106001003.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/penn_state/2019/07/18/clavrx_VNP02IMG.A2019199.1742.001.2019199230925.uwssec.nc',
                '/ships19/cloud/scratch/cphillips/clavrx/run_viirs_superres/sites_super_l2/penn_state/2019/02/02/clavrx_VNP02IMG.A2019033.1754.001.2019034011318.uwssec.nc']

keep_out = keep_out_opd

# target_param = 'cloud_probability'
target_param = 'cld_opd_dcomp'

# group_name = ''
# group_name = 'super/'
group_name = 'orig/'
# l2_params = [group_name+'temp_11_0um_nom', group_name+'refl_0_65um_nom', group_name+target_param]
l2_params = [group_name+'temp_11_0um', group_name+'refl_0_65um', group_name+target_param]

# solzen_name = group_name + 'solar_zenith_angle'
solzen_name = group_name + 'solar_zenith'

label_params = l2_params
data_params = l2_params

param_idx = data_params.index(group_name + target_param)

# range = [0.0, 1.0]
cld_prob_norm_hist = [0.34458323, 0.03729378, 0.01817725, 0.01246574, 0.00991681, 0.00826515, 0.00785976, 0.00595133,
                      0.00567965, 0.00579926, 0.00642895, 0.00797761, 0.01218471, 0.51741677]

# range = [0.0, 160.0]
cld_opd_norm_hist = [7.31926378e-01, 9.52482193e-02, 4.62747706e-02, 3.15450036e-02, 1.98358694e-02, 1.33123841e-02,
                     1.03378429e-02, 7.95560979e-03, 5.77925319e-03, 4.82856215e-03, 3.31576300e-03, 2.86789405e-03,
                     2.50456177e-03, 1.79184632e-03, 1.51077739e-03, 1.29144749e-03, 9.20514553e-04, 7.47183923e-04,
                     6.50404531e-04, 1.73557144e-02]


def is_missing(p_idx, tile):
    keep = np.invert(np.isnan(tile[p_idx, ]))
    if np.sum(keep) / keep.size < 0.98:
        return True


def keep_tile(p_idx, tile):
    grd_k = tile[p_idx, ].copy()

    if target_param == 'cloud_probability':
        grd_k = process_cld_prob(grd_k)
    elif target_param == 'cld_opd_dcomp':
        grd_k = process_cld_opd(grd_k)

    if grd_k is not None:
        tile[p_idx, ] = grd_k
        return tile
    else:
        return None


def process_cld_prob(grd_k):
    keep = np.invert(np.isnan(grd_k))
    num_keep = np.sum(keep)
    keep_clr = np.where(keep, grd_k < 0.30, False)
    keep_cld = np.where(keep, grd_k > 0.70, False)
    frac_clr = np.sum(keep_clr)/num_keep
    frac_cld = np.sum(keep_cld)/num_keep
    if not (frac_clr >= 0.20 and frac_cld >= 0.20):
        return None
    grd_k = np.where(np.invert(keep), 0, grd_k)  # Convert NaN to 0
    return grd_k


def process_cld_opd(grd_k):
    keep = np.invert(np.isnan(grd_k))
    num_keep = np.sum(keep)
    keep_cld = np.where(keep, (0.1 < grd_k), False)
    frac_cld = np.sum(keep_cld)/num_keep
    if not (0.50 < frac_cld < 0.85):
        return None
    grd_k = np.where(np.invert(keep), 0, grd_k)  # Convert NaN to 0
    return grd_k


def run_all(directory, out_directory, day_night='ANY', start=10):
    cnt = start
    total_num_train_samples = 0
    total_num_valid_samples = 0
    total_num_not_missing = 0
    num_keep_x_tiles = 14
    tile_width = 64

    # pattern = 'clavrx_VNP02MOD*.highres.nc.level2.nc'
    pattern = 'clavrx_*.nc'
    path = directory + '**' + '/' + pattern

    all_files = glob.glob(path, recursive=True)
    data_files = [f for f in all_files if f not in keep_out]

    data_valid_tiles = []
    data_train_tiles = []
    f_cnt = 0

    num_files = len(data_files)

    print('Start, number of files: ', num_files)

    for idx, data_f in enumerate(data_files):
        # if idx % 4 == 0:  # if we want to skip some files
        if True:
            try:
                data_h5f = h5py.File(data_f, 'r')
            except:
                print('cant open file: ', data_f)
                continue

            try:
                num_not_missing = run(data_h5f, data_params, data_train_tiles, data_valid_tiles, num_keep_x_tiles=num_keep_x_tiles, tile_width=tile_width, kernel_size=11, day_night=day_night)
            except Exception as e:
                print(e)
                data_h5f.close()
                continue
            print(data_f)
            f_cnt += 1
            data_h5f.close()

            total_num_not_missing += num_not_missing

            if len(data_train_tiles) == 0 and len(data_valid_tiles) == 0:
                continue

            if (f_cnt % 20) == 0:
                num_valid_samples = 0
                if len(data_valid_tiles) > 0:
                    data_valid = np.stack(data_valid_tiles)
                    np.save(out_directory + 'data_valid_' + str(cnt), data_valid)
                    num_valid_samples = data_valid.shape[0]

                num_train_samples = 0
                if len(data_train_tiles) > 0:
                    data_train = np.stack(data_train_tiles)
                    np.save(out_directory+'data_train_' + str(cnt), data_train)
                    num_train_samples = data_train.shape[0]

                data_valid_tiles = []
                data_train_tiles = []

                print('  num_train_samples, num_valid_samples, progress % : ', num_train_samples, num_valid_samples, int((f_cnt/num_files)*100))
                total_num_train_samples += num_train_samples
                total_num_valid_samples += num_valid_samples
                print('total_num_train_samples, total_num_valid_samples, total_num_not_missing: ',
                      total_num_train_samples, total_num_valid_samples, total_num_not_missing)
                print('---------------------------------------------------------')

                cnt += 1

    # Write out leftover, if any. Maybe make this better someday
    num_valid_samples = 0
    if len(data_valid_tiles) > 0:
        data_valid = np.stack(data_valid_tiles)
        np.save(out_directory + 'data_valid_' + str(cnt), data_valid)
        num_valid_samples = data_valid.shape[0]

    num_train_samples = 0
    if len(data_train_tiles) > 0:
        data_train = np.stack(data_train_tiles)
        np.save(out_directory + 'data_train_' + str(cnt), data_train)
        num_train_samples = data_train.shape[0]

    print('  num_train_samples, num_valid_samples, progress % : ', num_train_samples, num_valid_samples,
          int((f_cnt / num_files) * 100))
    total_num_train_samples += num_train_samples
    total_num_valid_samples += num_valid_samples
    print('total_num_train_samples, total_num_valid_samples, total_num_not_missing: ',
          total_num_train_samples, total_num_valid_samples, total_num_not_missing)
    print('---------------------------------------------------------')

    print('*** Done, total_num_train_samples, total_num_valid_samples: ', total_num_train_samples, total_num_valid_samples)


#  tile_width: Must be even!
#  kernel_size: Must be odd!
def run(data_h5f, param_s, train_tiles, valid_tiles, num_keep_x_tiles=8, tile_width=64, kernel_size=9, day_night='ANY'):

    border = int((kernel_size - 1)/2)

    param_name = param_s[0]

    num_lines = data_h5f[param_name].shape[0]
    num_pixels = data_h5f[param_name].shape[1]  # Must be even

    if day_night != 'ANY':
        solzen = get_grid_values(data_h5f, solzen_name, 0, 0, None, num_lines, num_pixels)

    grd_s = []
    for param in param_s:
        try:
            grd = get_grid_values(data_h5f, param, 0, 0, None, num_lines, num_pixels)
            grd_s.append(grd)
        except Exception as e:
            print(e)
            return
    data = np.stack(grd_s)

    tile_width += 2 * border

    i_skip = tile_width
    j_skip = tile_width
    i_start = int(num_pixels / 2) - int((num_keep_x_tiles * tile_width) / 2)
    j_start = 0

    num_y_tiles = int(num_lines / tile_width) - 1

    tiles = []
    num_not_missing = 0

    for j in range(num_y_tiles):
        j_a = j_start + j * j_skip
        j_b = j_a + tile_width

        for i in range(num_keep_x_tiles):
            i_a = i_start + i * i_skip
            i_b = i_a + tile_width

            if day_night == 'DAY' and not is_day(solzen[j_a:j_b, i_a:i_b]):
                continue
            elif day_night == 'NIGHT' and is_day(solzen[j_a:j_b, i_a:i_b]):
                continue

            nda = data[:, j_a:j_b, i_a:i_b]
            if is_missing(param_idx, nda):
                continue
            num_not_missing += 1

            nda = keep_tile(param_idx, nda)
            if nda is not None:
                tiles.append(nda)

    num_tiles = len(tiles)
    num_valid = int(num_tiles * 0.10)
    num_train = num_tiles - num_valid

    for k in range(num_train):
        train_tiles.append(tiles[k])
    for k in range(num_valid):
        valid_tiles.append(tiles[num_train + k])

    return num_not_missing


def scan(directory):

    data_src = CLAVRx_VIIRS(directory)
    files = data_src.flist

    for idx, file in enumerate(files):
        h5f = h5py.File(file, 'r')
        ts = data_src.ftimes[idx][0]
        try:
            solzen = get_grid_values_all(h5f, 'solar_zenith_angle')
        except Exception as e:
            # print(e)
            h5f.close()
            continue

        # if is_day(solzen) and moon_phase(ts):
        if is_night(solzen) and moon_phase(ts):
            print(file)
        h5f.close()


def scan_for_location(txt_file, lon_range=[111.0, 130.0], lat_range=[14.0, 32.0]):
    with open(txt_file) as file:
        for idx, fpath in enumerate(file):
            fpath = fpath.strip()
            h5f = h5py.File(fpath, 'r')
            try:
                lon_s = get_grid_values_all(h5f, 'longitude', stride=4)
                lat_s = get_grid_values_all(h5f, 'latitude', stride=4)
                c_lon, c_lat = lon_s[406, 400], lat_s[406, 400]
                if (lon_range[0] < c_lon < lon_range[1]) and (lat_range[0] < c_lat < lat_range[1]):
                    print(fpath)

            except Exception as e:
                # print(e)
                h5f.close()
                continue


def test_nlcomp(file):
    h5f = h5py.File(file, 'r')

    cld_phs = get_grid_values_all(h5f, 'cloud_phase', scale_factor_name=None, range_name=None)
    keep_0 = np.invert(np.isnan(cld_phs))

    reff = get_grid_values_all(h5f, 'cld_reff_nlcomp')
    keep_1 = np.invert(np.isnan(reff))

    opd = get_grid_values_all(h5f, 'cld_opd_nlcomp')
    keep_2 = np.invert(np.isnan(opd))

    cld_dz = get_grid_values_all(h5f, 'cld_geo_thick')
    keep_3 = np.logical_and(np.invert(np.isnan(cld_dz)), cld_dz > 5.0)

    keep = keep_0 & keep_1 & keep_2 & keep_3

    cld_phs = cld_phs[keep]
    reff = reff[keep]
    opd = opd[keep]
    cld_dz = cld_dz[keep]

    lwc_c, iwc_c = compute_lwc_iwc(cld_phs, reff, opd, cld_dz)

    return lwc_c, iwc_c


# def run_mean_std(directory):
#
#     data_dct = {name: [] for name in mod_res_params}
#     mean_dct = {name: 0 for name in mod_res_params}
#     std_dct = {name: 0 for name in mod_res_params}
#
#     for p in os.scandir(directory):
#         if not p.is_dir():
#             continue
#         mod_files = glob.glob(directory+p.name+'/'+'VNP02MOD*.uwssec.nc')
#
#         for idx, mfile in enumerate(mod_files):
#             if idx % 8 == 0:
#                 h5f = h5py.File(mfile, 'r')
#                 for param in mod_res_params:
#                     name = 'observation_data/'+param
#                     gvals = get_grid_values_all(h5f, name, range_name=None, stride=10)
#                     data_dct[param].append(gvals.flatten())
#                 print(mfile)
#                 h5f.close()
#
#     for param in mod_res_params:
#         data = data_dct[param]
#         data = np.concatenate(data)
#
#         mean_dct[param] = np.nanmean(data)
#         std_dct[param] = np.nanstd(data)