A cloud-native Alternative Correction (AC) for Landsat-8/9 Collection 2 surface reflectance over inland waters
Abstract
This repository contains the source code for the Alternative Correction (AC) method, a cloud-native solution designed to mitigate Dark Plume Over Water (DPOW) artifacts in Landsat-8/9 Collection 2 Surface Reflectance products. The method is implemented in Python using the Google Earth Engine (GEE) API. It employs a random forest regression approach, trained on spatiotemporally aggregated high-quality water pixels, to reconstruct reliable surface reflectance from Top-of-Atmosphere (TOA) observations without relying on external atmospheric data.
Fields of Study & Subjects
Satellite Image Processing and Photogrammetry
Calibration and Measurement Techniques
Remote Sensing in Agriculture
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 January 2026