Predicting Harmful Algal Blooms Using Explainable Deep Learning Models: A Comparative Study

Harmful algal blooms (HABs) have emerged as a significant environmental challenge, impacting aquatic ecosystems, drinking water supply systems, and human health due to the combined effects of human activities and climate change. This study investigates the performance of deep learning models, particularly the Transformer model, as there are limited studies exploring its effectiveness in HAB prediction. The chlorophyll-a (Chl-a) concentration, a commonly used indicator of phytoplankton biomass and a proxy for HAB occurrences, is used as the target variable. We consider multiple influencing parameters—including physical, chemical, and biological water quality monitoring data from multiple stations located west of Lake Erie—and employ SHapley Additive exPlanations (SHAP) values as an explainable artificial intelligence (XAI) tool to identify key input features affecting HABs. Our findings highlight the superiority of deep learning models, especially the Transformer, in capturing the complex dynamics of water quality parameters and providing actionable insights for ecological management. The SHAP analysis identifies Particulate Organic Carbon, Particulate Organic Nitrogen, and total phosphorus as critical factors influencing HAB predictions. This study contributes to the development of advanced predictive models for HABs, aiding in early detection and proactive management strategies.