IMPROVED DISSOLVED ORGANIC CARBON PREDICTION IN DIVERSE INLAND WATER BODIES: UTILIZING MACHINE LEARNING AND REMOTE SENSING

Abstract

The pool of dissolved organic carbon (DOC) is a pivotal influencer in the ecology and bio-geochemistry of inland water ecosystems, constituting a significant factor in the carbon budgets of terrestrial ecosystems. Employing a machine learning approach and leveraging a large curated dataset (AquaSat), this study delves into the importance of multiple spectral remote sensing data and spatio-temporal information in contributing to the variability of in situ DOC concentrations in inland water bodies. The research underscores the critical role of spatial and temporal information in enhancing the accuracy of DOC predictions, revealing a remarkable 200% increase in machine learning model performance when spatio-temporal information is incorporated. With a substantial coverage of inland water bodies in the dataset, the results offer valuable insights and findings for effective environmental monitoring and resource management.