Science Inventory

Forecasting freshwater cyanobacterial harmful algal blooms for Sentinel-3 satellite resolved U.S. lakes and reservoirs


Schaeffer, B., N. Reynolds, H. Ferriby, W. Salls, D. Smith, J. Johnston, AND M. Myer. Forecasting freshwater cyanobacterial harmful algal blooms for Sentinel-3 satellite resolved U.S. lakes and reservoirs. JOURNAL OF ENVIRONMENTAL MANAGEMENT. Elsevier Science Ltd, New York, NY, 349:119518, (2024).


Forecasting freshwater cyanobacteria is important for water quality management. Weekly cyanobacteria abundance data were obtained from Sentinel-3 satellite data. A Bayesian spatio-temporal model was applied to forecast World Health Organization alert level exceedance. Overall predication accuracy was 89% with 86% sensitivity and 90% specificity. Weekly forecasts were demonstrated for 2,192 larger U.S. lakes and reservoirs.The United Nations recommended that forecast systems for algal bloom events provide at least a 2 to 3 day advanced notice to enable proactive management response. In this study, the model provided 7-day advanced notice. The United Nations also recommends prioritizing models that work across different locations instead of individual systems to improve the effectiveness of these forecast systems, where satellite data could provide presence and absence data informing forecasts. This study applied a single hierarchical Bayesian spatio-temporal model approach that worked across 2,192 satellite resolved lakes. The model addressed basic information required by stakeholders, such as forecasts of the initiation, magnitude of the event defined here as exceeding the WHO Alert Level 2 threshold, and identification of potential priority areas where a cyanoHAB was mostly likely to occur. This model fills a critical gap of forecasting cyanoHAB occurrence, while more detailed mechanistic models may be developed, and directly supports the U.S. HABHRCA, WHO, and United Nations for advancing forecasts for cyanoHAB events in freshwater systems.


This forecasting approach may be useful for water managers and associated public health managers to predict near-term future high-risk cyanobacterial harmful algal blooms (cyanoHAB) occurrence. Freshwater cyanoHABs may grow to excessive concentrations and cause human, animal, and environmental health concerns in lakes and reservoirs. Knowledge of the timing and location of cyanoHAB events is important for water quality management of recreational and drinking water systems. No quantitative tool exists to forecast cyanoHABs across broad geographic scales and at regular intervals. Publicly available satellite monitoring has proven effective in detecting cyanobacteria biomass near-real time within the United States. Weekly cyanobacteria abundance was quantified from the Ocean and Land Colour Instrument (OLCI) onboard the Sentinel-3 satellite as the response variable. An Integrated Nested Laplace Approximation (INLA) hierarchical Bayesian spatiotemporal model was applied to forecast World Health Organization (WHO) recreation Alert Level 1 exceedance >12 μg L−1 chlorophyll-a with cyanobacteria dominance for 2192 satellite resolved lakes in the United States across nine climate zones. The INLA model was compared against support vector classifier and random forest machine learning models; and Dense Neural Network, Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Gneural Network (GNU) neural network models. Predictors were limited to data sources relevant to cyanobacterial growth, readily available on a weekly basis, and at the national scale for operational forecasting. Relevant predictors included water surface temperature, precipitation, and lake geomorphology. Overall, the INLA model outperformed the machine learning and neural network models with prediction accuracy of 90% with 88% sensitivity, 91% specificity, and 49% precision as demonstrated by training the model with data from 2017 through 2020 and independently assessing predictions with data from the 2021 calendar year. The probability of true positive responses was greater than false positive responses and the probability of true negative responses was less than false negative responses. This indicated the model correctly assigned lower probabilities of events when they didn't exceed the WHO Alert Level 1 threshold and assigned higher probabilities when events did exceed the threshold. The INLA model was robust to missing data and unbalanced sampling between waterbodies.

Record Details:

Product Published Date:01/01/2024
Record Last Revised:11/08/2023
OMB Category:Other
Record ID: 359438