Assistant Professor FAMU-FSU College of Engineering
The global increase in harmful algal blooms (HABs) has led to a greater prevalence of toxic algal species and a wider geographical impact. Climate change, particularly fluctuations in water temperature and precipitation, is anticipated to influence coastal HAB dynamics. Because higher water temperatures will favor the growth and reproduction of many HAB species, and changes in precipitation and runoff will alter nutrient loads that may stimulate algal growth. Biscayne Bay, downstream of Miami-Dade County, is already showing signs of water quality deterioration and HAB occurrence due to anthropogenic influences from rapid urbanization and the potential threat of climate change. In this context, we developed a data-driven model to predict HABs for the susceptible Biscayne Bay area, integrating diverse climatic factors such as water and air temperatures, relative humidity, and precipitation. First, we established a data-driven framework for HAB prediction by integrating water quality, climate, and land use data. Then, by leveraging the Random Forest algorithm, we downscaled the extensive Global Circulation Model (GCM) to obtain future climatic data across various scenarios. Finally, we applied the downscaled climate data into the predictive framework and assessed the results of future HABs. Our findings indicate that, under the influence of climate change, HABs in Biscayne Bay are likely to increase to varying degrees. This approach not only predict HAB occurrences under evolving climate scenarios but also fortifies resilience against HAB-related challenges. Such insights are critical in safeguarding coastal ecosystems and human health and promoting sustainable development.
