+lut

These files were created for SCOPE per pixel implementation within the TRUSTEE project (H2020, TRuStEE, MSCA-ITN-2016 No 721995) tutorials. Briefly, it creates a look up table (LUT) and compares two types of search within LUT - based on root mean squared error (RMSE) and gaussian process regression (GPR).

LUT input sampling within parameter borders adjusted in src/+lut/input_borders.csv

generate_lut_input(tab, n_spectra, outdir)

params = generate_lut_input(tab, n_spectra, outdir)

SCOPE run in time series mode with lut_in.csv data …

Training and testing of gaussian process regression (GPR)

train_gpr(lut_in_path, lut_out_path, var_name)

Preparation of data: flattening of tiff files to csv.

image2csv(im_path, outdir)

Preparation of validation data (random pixels from flattened image)

pick100(full_set_path, n_pixels)

SCOPE run in time series mode with validation.csv data …

Validation of methods

validate_gpr(gpr_path, val_in_path, val_out_path)
validate_rmse(lut_in_path, lut_out_path, val_in_path, val_out_path)

Usage of methods

use_gpr(gpr_path, full_set_path)
use_rmse(lut_in_path, lut_out_path, full_set_path, var_name)

Supporting functions

change_detection(rmse_im_path, gpr_im_path)
compress_geotiff(path_in, path_out)
csv2image_plane(val_in, res)

to read r, c from column name ind_r_c

check validity: all lut params in params

plot_1to1(meas, mod, what, out_path, var_name)
plot_image(im, what, out_path)
write_tiff(im, out_path)