Deep learning-based chlorophyll prediction: comparison with a dynamic model and applications to fish catch forecasting

Abstract

Anticipating marine ecosystem changes is critical for enabling communities to adapt to climate fluctuations and for predicting future climate by considering interactions between Earth's physical and biogeochemical fields. Earth System Models (ESMs) capture large-scale physical–biogeochemical coupling, but their biogeochemical prediction skill varies substantially across regions and lead times due to sparse observational records, structural uncertainties in biogeochemical models. Here, we develop a deep learning-based prediction system to forecast surface chlorophyll concentrations across all Large Marine Ecosystems (LMEs) at monthly to annual timescales with lead times up to two years. Trained on multi-decadal simulations from various climate models and a coupled physical–biogeochemical reanalysis from a data assimilative ESM run, the system demonstrates skillful chlorophyll predictions comparable to ESM-based dynamic forecasts. The prediction skill is associated with physical-biogeochemical coupling processes triggered by large-scale climate variability, consistent with the mechanisms previously identified in dynamical forecasts. Furthermore, predicted chlorophyll anomalies are significantly linked to interannual variability in fish catch in several LMEs, demonstrating the promise of data-driven biogeochemical forecasting to support adaptive, climate-informed marine resource management.