Citation:

Gupta, A., Mohamed M. Hantush, AND R. Govindaraju. Sub-monthly time scale forecasting of harmful algal blooms intensity in Lake Erie using remote sensing and machine learning. SCIENCE OF THE TOTAL ENVIRONMENT. Elsevier BV, AMSTERDAM, Netherlands, 900:165781, (2023). https://doi.org/10.1016/j.scitotenv.2023.165781

Impact/Purpose:

This research presents a methodology and data-driven models to predict HABs cell-count and concentrations in Lake Erie using satellite imageries of Cyanobacteria. The Ensemble Average of three data-driven models can be used as a tool for research and HABs outbreak early warning and control system. 

Description:

Harmful algal blooms of cyanobacteria (CyanoHAB) have emerged as a serious environmental concern in large and small water bodies including many inland lakes. The growth dynamics of CyanoHAB can be chaotic at very short timescales but predictable at coarser timescales. In Lake Erie, cyanobacteria blooms occur in the spring-summer months, which, at annual timescale, are controlled by the total spring phosphorus (TP) load into the lake. This study aimed to forecast CyanoHAB cell count at sub-monthly (e.g., 10-day) timescales. Satellite-derived cyanobacterial index (CI) was used as a surrogate measure of CyanoHAB cell count. CI was related to the in-situ measured chlorophyll-a and phycocyanin concentrations and Microcystis biovolume in the lake. Using available data on environmental and lake hydrodynamics as predictor variables, four statistical models including LASSO (Least Absolute Shrinkage and Selection Operator), artificial neural network (ANN), random forest (RF), and an ensemble average of the three models (EA) were developed to forecast CI at 10-, 20- and 30-day lead times.

URLs/Downloads:

Record Details: