def mark_lalo_anomoly(lat, lon):
"""mask pixels with abnormal values (0, etc.)
This is found on sentinelStack multiple swath lookup table file.
"""
# ignore pixels with zero value
zero_mask = np.multiply(lat != 0., lon != 0.)
# ignore anomaly non-zero values
# by get the most common data range (d_min, d_max) based on histogram
mask = np.array(zero_mask, np.bool_)
for data in [lat, lon]:
bin_value, bin_edge = np.histogram(data[mask], bins=10)
# if there is anomaly, histogram won't be evenly distributed
while np.max(bin_value) > np.sum(zero_mask) * 0.3:
# find the continous bins where the largest bin is --> normal data range
bin_value_thres = ut.median_abs_deviation_threshold(bin_value, cutoff=3)
bin_label = ndimage.label(bin_value > bin_value_thres)[0]
idx = np.where(bin_label == bin_label[np.argmax(bin_value)])[0]
# convert to min/max data value
bin_step = bin_edge[1] - bin_edge[0]
d_min = bin_edge[idx[0]] - bin_step / 2.
d_max = bin_edge[idx[-1]+1] + bin_step / 2.
mask *= np.multiply(data >= d_min, data <= d_max)
bin_value, bin_edge = np.histogram(data[mask], bins=10)
lat[mask == 0] = 90.
lon[mask == 0] = 0.
return lat, lon, mask
def mark_lat_lon_anomoly(lat, lon):
"""mask pixels with abnormal values (0, etc.)
This is found on sentinelStack multiple swath lookup table file.
"""
# ignore pixels with zero value
zero_mask = np.multiply(lat != 0., lon != 0.)
# ignore anomaly non-zero values
# by get the most common data range (d_min, d_max) based on histogram
mask = np.array(zero_mask, np.bool_)
for data in [lat, lon]:
bin_value, bin_edge = np.histogram(data[mask], bins=10)
# if there is anomaly, histogram won't be evenly distributed
while np.max(bin_value) > np.sum(zero_mask) * 0.3:
# find the continous bins where the largest bin is --> normal data range
bin_value_thres = ut.median_abs_deviation_threshold(
bin_value, cutoff=3)
bin_label = ndimage.label(bin_value > bin_value_thres)[0]
idx = np.where(
bin_label == bin_label[np.argmax(bin_value)])[0]
# convert to min/max data value
bin_step = bin_edge[1] - bin_edge[0]
d_min = bin_edge[idx[0]] - bin_step / 2.
d_max = bin_edge[idx[-1] + 1] + bin_step / 2.
mask *= np.multiply(data >= d_min, data <= d_max)
bin_value, bin_edge = np.histogram(data[mask], bins=10)
# set invalid pixels to fixed values
lat[mask == 0] = 90.
lon[mask == 0] = 0.
return lat, lon, mask