08-partition-data.py

This script develops the partitions used to train and evaluate fluvius models. A first-phase partition divides the sites into either a training or a test set. Sites in the test set are never seen by the model during training, including the hyperparameter grid search used to identify the top-performing model. Sites that appear in the training set are further partitioned into train and validation sets over k-folds. Several parameters involved in the partition are hard-coded.

usage: 08-partition-data.py [-h] [--day-tolerance DAY_TOLERANCE]
                            [--cloud-thr CLOUD_THR]
                            [--buffer-distance BUFFER_DISTANCE]
                            [--mask-method1 {lulc,scl}]
                            [--mask-method2 {mndwi,ndvi,""}]
                            [--n-folds N_FOLDS] [--seed SEED]

Named Arguments

--day-tolerance

Days of search around sample date for a matching Sentinel 2 image.

Default: 8

--cloud-thr

Percent of cloud cover acceptable in the Sentinel tile corresponding to the sample. If this threshold is surpassed, no Sentinel image chip will be collected for the sample.

Default: 80

--buffer-distance

Square search radius (in meters) to use for reflectance data aggregation. This determines the size of the image chip that will be extracted and processed.

Default: 500

--mask-method1

Possible choices: lulc, scl

Which data to use for masking (removing) non-water in order to calculate aggreated reflectance values for only water pixels? Choose (“scl”) to water pixels as identified based on the Scene Classification Layer that accompanies the Snetinel tile, or (“lulc”) to use Impact Observatory’s Land-Use/Land-Cover layer to identify water, and the Scene Classification Layer to remove clouds. Using “lulc” is strongly recommended.

Default: “lulc”

--mask-method2

Possible choices: mndwi, ndvi, “”

Which additional normalized index to use, if any, to update the mask to remove errors of ommission (pixels classified as water that shouldn’t be) prior to calculated aggregated reflectance? If “ndvi”, then only pixels with an NDVI value less than 0.25 will be retained. If “mndwi” (recommended) then only pixels with an MNDWI value greater than 0 will be retained. Of “”, then no secondary mask is used.

Default: “mndwi”

--n-folds

The number of folds to create for the training / validation set when fitting models using k-fold cross-validation.

Default: 5

--seed

The seed (an integer) used to initialize the pseudorandom number generator for use in partitioning data.

Default: 123