Convergence Research Seminar Series: Huichun (Judy) Zhang, PhD (CWRU)

Abstract:

The recent outbreaks of harmful algal blooms in the western Lake Erie Basin have drawn tremendous attention to bloom prediction for better control and management. Many weekly to annual bloom prediction models have been reported, but they only employ small datasets, have limited types of input features, build linear regression or probabilistic models, or require complex process-based computations. To address these limitations, we conducted an extensive literature review and compiled a large dataset encompassing the chlorophyll-a index as the output variable. By employing a novel combination of riverine and meteorological features as inputs, we constructed machine learning models to forecast short-term (10-d) bloom occurrences in Lake Erie. In addition, excess phosphorus (P) serves as a major catalyst for algal blooms in numerous lakes, including Lake Erie. Agricultural runoff, despite typically containing P concentrations lower than 0.5 mg/L, serves as a significant non-point source of P in many watersheds. Currently,…