Chlorophyll-a is a key indicator of lake water quality and phytoplankton blooms, motivating the need for predictions of future chlorophyll-a concentrations for management. Advance notice of blooms could enable preemptive actions to mitigate water quality impacts, such as clogging of drinking water treatment plant filters or taste and odor concerns. Despite decades of research, however, accurate prediction of future lake chlorophyll-a remains difficult. Moreover, the application of various predictive modeling approaches across different datasets, waterbodies, and prediction windows makes model inter-comparison challenging and hampers identification of the most accurate modeling methods. To address these challenges, I am developing a suite of process-based and data-driven chlorophyll-a prediction models using data from the Virginia Reservoirs LTREB. My aim is to determine which models perform best at predicting chlorophyll-a over time and under different environmental conditions. In addition, many of the models are currently submitting to the Virginia Ecoforecast Reservoir Analysis (VERA) Forecasting Challenge!

Browse this project’s GitHub repository.