Harmful Algal Blooms (HABs) in Lake Erie cause significant economic losses. Conventional prediction methods using nutrient loading are inaccurate during extreme bloom years. This study demonstrates that a machine learning approach, incorporating observed nutrient loading and large-scale climate indices, improves HAB prediction in Lake Erie. Seasonal prediction can be completed by early June, enabling timely mitigation strategies.
Publisher
Communications Earth & Environment
Published On
Aug 31, 2022
Authors
Mukul Tewari, Chandra M. Kishtawal, Vincent W. Moriarty, Pallav Ray, Tarkeshwar Singh, Lei Zhang, Lloyd Treinish, Kushagra Tewari
Tags
Harmful Algal Blooms
Lake Erie
machine learning
climate indices
nutrient loading
economic losses
seasonal prediction
Related Publications
Explore these studies to deepen your understanding of the subject.
