A machine learning approach for early warning of cyanobacterial bloom outbreaks in a freshwater reservoir

Understanding the dynamics of harmful algal blooms is important to protect the aquatic ecosystem in regulated rivers and secure human health. In this study, artificial neural network (ANN) and support vector machine (SVM) models were used to predict algae alert levels for the early warning of blooms in a freshwater reservoir. Intensive water-quality, hydrodynamic, and meteorological data were used to train and validate both ANN and SVM models. The Latin-hypercube one-factor-at-a-time (LH-OAT) method and a pattern search algorithm were applied to perform sensitivity analyses for the input variables and to optimize the parameters of the models, respectively. The results indicated that the two models well reproduced the algae alert level based on the time-lag input and output data. In particular, the ANN model showed a better performance than the SVM model, displaying a higher performance value in both training and validation steps. Furthermore, a sampling frequency of 6- and 7-day were determined as efficient early-warning intervals for the freshwater reservoir. Therefore, this study presents an effective early-warning prediction method for algae alert level, which can improve the eutrophication management schemes for freshwater reservoirs.

Automated summary

Understanding harmful algal blooms is crucial for protecting aquatic ecosystems and human health. ANN and SVM models were used in this study to predict algae alert levels in a freshwater reservoir, with the ANN model outperforming the SVM model. A sampling frequency of 6-7 days was found to be effective for early warning intervals.