Many countries have attempted to mitigate and manage issues related to harmful algal blooms (HABs) by monitoring and predicting their occurrence. The infrequency and duration of HABs occurrence pose the challenge of data imbalance when constructing machine learning models for their prediction. Furthermore, the appropriate selection of input variables is a significant issue because of the complexities between the input and output variables. Therefore, the objective of this study was to improve the predictive performance of HABs using feature selection and data resampling. Data resampling was used to address the imbalance in the minority class data. Two machine learning models were constructed to predict algal alert levels using 10 years of meteorological, hydrodynamic, and water quality data. The improvement in model accuracy due to changes in resampling methods was more noticeable than the improvement in model accuracy due to changes in feature selection methods. Models constructed using combinations of original and synthetic data across all resampling methods demonstrated higher prediction performance for the caution level (L-1) and warning level (L-2) than models constructed using the original data. In particular, the optimal artificial neural network and random forest models constructed using combinations of original and synthetic data showed significantly improved prediction accuracy for L-1 and L-2, representing the transition from normal to bloom formation states in the training and testing steps. The test results of the optimal RF model using the original data indicated prediction accuracies of 98.8% for L0, 50.0% for L1, and 50.0% for L2. In contrast, the optimal random forest model using the Synthetic Minority Oversampling Technique–Edited Nearest Neighbor (ENN) sampling method achieved accuracies of 85.0% for L0, 85.7% for L1, and 100% for L2. Therefore, applying synthetic data can address the imbalance in the observed data and improve the detection performance of machine learning models. Reliable predictions using improved models can support the design of management practices to mitigate HABs in reservoirs and ultimately ensure safe and clean water resources.

The HSPF model was modified to improve the growth-temperature formulation of phytoplankton and used to simulate Chl-a concentrations at the outlet of the Seom River watershed in Korea from 2025 to 2050 under four climate change scenarios: RCP 2.6, RCP 4.5, RCP 6.0, and RCP 8.5. The mean and median Chl-a concentrations increased by 5–10% and 23–29%, respectively, and the number of algal outbreak cases per year (defined as a day with Chl-a concentration ≥100 µg/L) decreased by 31–88% relative to the current values (2011–2015). Among the climate change scenarios, RCP 2.6 (stringent) showed the largest number of algal outbreak cases, mainly because of the largest yearly variability of precipitation and TP load. For each climate change scenario, three nutrient load reduction scenarios were in the HSPF simulation, and their efficiencies in reducing algal blooms were determined. Nonpoint source reduction in TP and TN from urban land, agricultural land, and grassland by 50% (S1) and controlling the effluent TP concentration of wastewater treatment plants (WWTPs) to 0.1 mg/L (S2) decreased algal outbreaks by 20–58% and 44–100%, respectively. The combination of effluent TP control of WWTPs during summer and S1 was the most effective management scenario; it could almost completely prevent algal outbreaks. This study demonstrates the cost effectiveness of using a season-based pollutant management strategy for controlling algal blooms.