Global Chlorophyll-\textit{a} Retrieval algorithm from Sentinel 2 Using Residual Deep Learning and Novel Machine Learning Water Classification

TL;DR

This paper introduces a global water classification and chlorophyll-a retrieval algorithm using Sentinel-2 data, combining machine learning classifiers and residual CNN correction for accurate, scalable water quality assessment.

Contribution

It develops a novel integrated approach with a water classifier and residual CNN correction, achieving high accuracy in global chlorophyll-a estimation from satellite data.

Findings

Classifier outperforms negatives in chlorophyll-a retrieval

Residual CNN improves prediction accuracy significantly

Algorithm achieves R^2=0.79 and MAE=13.52 mg/m^3 on diverse water bodies

Abstract

We present the Global Water Classifier (GWC), a supervised, geospatially extensive Machine Learning (ML) classifier trained on Sen2Cor corrected Sentinel-2 surface reflectance data. Using nearly 100 globally distributed inland water bodies, GWC distinguishes water across Chlorophyll-a (Chla) levels from non-water spectra (clouds, sun glint, snow, ice, aquatic vegetation, land and sediments) and shows geographically stable performance. Building on this foundation model, we perform Chla retrieval based on a matchup Sentinel-2 reflectance data with the United States Geological Survey (USGS) AquaMatch in-situ dataset, covering diverse geographical and hydrological conditions. We train an XGBoost regressor on 13626 matchup points. The positive labeled scenes by the GWC consistently outperform the negatives and produce more accurate Chla retrieval values, which confirms the classifiers advantage in reducing various interferences. Next, residual analysis of the regression predictions revealed structured errors, motivating a residual CNN (RCNN) correction stage. We add a CNN residual stage trained on normalized residuals, which yield substantial improvement. Our algorithm was tested on 867 water bodies with over 2,000 predictions and Chla values up to 1000~mg$/m^{3}$, achieving $R^2$ = 0.79, MAE = 13.52~mg$/m^{3}$, and slope = 0.91, demonstrating robust, scalable, and globally transferable performance without additional tuning.