Modeling Harmful Algal Blooms (HABs) in a changing climate is essential for achieving sustainable development goals, especially those concerning clean water and sanitation. However, a lack of consistent and adequate data on HABs presents a significant challenge. In this study, the sparse identification nonlinear dynamics (SINDy) technique was employed to model microcystin, an algal toxin, using dissolved oxygen as a water quality metric and evaporation as a meteorological parameter. SINDy, a novel technique combining sparse regression and machine learning, reconstructs the analytical representation of a dynamical system. In addition, a model-driven and web-based interactive tool was created to disseminate environmental education, raise public awareness about HAB events, and provide more effective solutions using what-if scenarios. This platform allows users to track HAB statuses in lakes and observe how specific parameters impact harmful algae formation. It also enables users to share images of HABs, providing a user-friendly way to monitor and understand the status of lakes affected by harmful algal blooms.
Related Articles
- Baydaroğlu, Ö., Yeşilköy, S., Dave, A., Linderman, M., & Demir, I. (2024). Modeling of Harmful Algal Bloom Dynamics and Integrated Web Framework for Inland Waters in Iowa.
DOI: https://doi.org/10.31223/X5S40X
Related Links
A snapshot of the web-based platform used for tracking Harmful Algal Blooms in Iowa lakes.
