12-prediction-inputs.py

This script queries STAC on the Planetary Computer to download and process image chips from the entire Sentinel 2 catalogue for every ANA and ITV monitoring site. These images chips will be used subsequently to generate time-series model predictions for each site. This script must be run separately for ANA and ITV sites.

usage: 12-prediction-inputs.py [-h] [--data-src {itv,ana,usgs,usgsi}]
                               [--cloud-thr CLOUD_THR]
                               [--buffer-distance BUFFER_DISTANCE]
                               [--write-chips] [--mask-method1 {lulc,scl}]
                               [--mask-method2 {mndwi,ndvi,""}]
                               [--start-date START_DATE] [--end-date END_DATE]

Named Arguments

--data-src

Possible choices: itv, ana, usgs, usgsi

For which data source should this script run?

--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

--write-chips

Write image chips to blob storage? Should be set to true unless troubleshooting.

Default: False

--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”

--start-date

The earliest date for which to generate prediction inputs

Default: “2015-01-01”

--end-date

The latest date for which to generate prediction inputs

Default: “2021-12-31”