Incorporating marine particulate carbon into machine learning for accurate estimation of coastal chlorophyll-a

Abstract

Accurate predictions of coastal ocean chlorophyll-a (Chl-a) concentrations are necessary for dynamic water quality monitoring, with eutrophication as a critical factor. Prior studies that used the driven-data method have typically overlooked the relationship between Chl-a and marine particulate carbon. To address this gap, marine particulate carbon was incorporated into machine learning (ML) and deep learning (DL) models to estimate Chl-a concentrations in the Yang Jiang coastal ocean of China. Incorporating particulate organic carbon (POC) and particulate inorganic carbon (PIC) as predictors can lead to successful Chl-a estimation. The Gaussian process regression (GPR) model significantly outperforming the DL model in terms of stability and robustness. A lower POC/Chl-a ratio was observed in coastal areas, in contrast to the higher ratios detected in the southern regions of the study area. This study highlights the efficacy of the GPR model for estimating Chl-a and the importance of considering POC in modeling Chl-a concentrations.