Improved seasonal prediction of harmful algal blooms in Lake Erie using large-scale climate indices

Abstract Harmful Algal Blooms lead to multi-billion-dollar losses in the United States due shellfish closures, fish mortalities, and reluctance consume seafood. Therefore, an improved early seasonal prediction of harmful algal blooms severity is important. Conventional methods for using nutrient loading as primary driver have been found be less accurate during extreme bloom years. Here we show that a machine learning approach observed loading, large-scale climate indices can improve Lake Erie. Moreover, completed by June, before expected peak activity from July October. This provide timely information policymakers adopting proper planning mitigation strategies such restrictions harvesting help monitoring toxins keep contaminated products off market.