The need for advancing algal bloom forecasting using remote sensing and modeling: Progress and future directions

Abstract

Algal blooms are often major drivers of environmental and economic challenges. As these blooms increase in frequency and size, there is an increasing need for forecasting models to accurately predict their occurrence and progression. Such algal bloom forecast systems can provide early warnings to mitigate the harmful impacts on ecosystems and public health. This study presents an overview of the current progress for algal bloom forecasting (i.e., predicting the future occurrence, distribution, frequency, and intensity of algal blooms in water bodies) and emphasizes the need for research initiatives and future directions on this topic. Remote sensing, particularly ocean-color products, has emerged as a foundation for algal bloom monitoring and forecasting, providing critical spatial–temporal data to address the limitations of in situ measurements. Machine learning and deep learning models dominate recent developments, demonstrating their capabilities in capturing non-linear and complex dynamics and enhancing accuracy in forecasting. Forecast intervals used vary, ranging from daily forecasts to weeks, monthly, seasonal, and annual predictions. A relevant aspect of algal bloom forecasting is the input variables, and we identified the key inputs, including surface temperature, nitrogen and phosphorus concentrations, wind patterns, and previous/current bloom information. However, most studies are geographically concentrated in the Northern Hemisphere, specifically North America, Europe, and Asia, focusing on lakes and coastal waters, leaving tropical regions, rivers, reservoirs, and open oceans underexplored. Despite the advancement in this field, operational algal bloom forecasting systems are still scarce, particularly when compared to other environmental fields, such as meteorology and air quality forecasting. With new hyperspectral capabilities being developed, integrating these emerging technologies offers unprecedented opportunities to refine predictions, particularly for phytoplankton community composition and functional types. This study emphasizes the need to expand forecasting research to underrepresented regions and water body types, such as reservoirs and estuaries. Under current climate change scenarios, algal blooms may become more frequent and intense, and it is crucial to continuously develop and advance algal bloom research to support coastal and inland water management.