Retrieval of Case 2 Water Quality Parameters with Machine Learning

TL;DR

This paper evaluates machine learning regression methods for estimating water quality parameters from Sentinel-3 OLCI data, focusing on highly absorbing waters with high CDOM levels, and compares their performance with existing neural network approaches.

Contribution

It introduces a comprehensive comparison of multiple machine learning regression techniques for water quality retrieval using the C2X dataset, including validation against independent data and existing neural network methods.

Findings

Random forest achieved the highest accuracy among tested methods.

Machine learning approaches outperformed the standard OLCI product in certain conditions.

The best model successfully estimated water quality parameters in a real scene.

Abstract

Water quality parameters are derived applying several machine learning regression methods on the Case2eXtreme dataset (C2X). The used data are based on Hydrolight in-water radiative transfer simulations at Sentinel-3 OLCI wavebands, and the application is done exclusively for absorbing waters with high concentrations of coloured dissolved organic matter (CDOM). The regression approaches are: regularized linear, random forest, Kernel ridge, Gaussian process and support vector regressors. The validation is made with and an independent simulation dataset. A comparison with the OLCI Neural Network Swarm (ONSS) is made as well. The best approached is applied to a sample scene and compared with the standard OLCI product delivered by EUMETSAT/ESA