Assessment of climate change impacts on hydropower potential in intermittent river basins using bootstrap aggregating machine learning method

ABSTRACT Devastating environmental effects of relying too much on fossil fuels include air pollution, acid rain and global warming. One renewable energy source that is crucial for slowing climate change is hydropower. However, climate change affects its potential and makes hydropower generation unpredictable. The bootstrap aggregating machine learning approach is being used in this study to evaluate the hydropower potential in intermittent river basins. The performance of the Bootstrap Aggregating (BA) model was benchmarked against Random Forest and Gradient Boosting algorithms, demonstrating superior predictive stability with an average absolute error of 5.46%. A regional model was developed using future precipitation data unique to the Antalya basin (2025–2055) under the RCP 4.5 intermediate emission scenario. The findings demonstrate that the approach effectively estimated power duration curves and cease-to-flow points, with only minor discrepancies between the modeled and observed data. Quantitative analysis using Area Under the Curve (AUC) revealed a downward shift in future energy potential, particularly impacting mid-range generation capacities. The influence of climate change on hydropower potential, emphasizing its role as a renewable energy source amidst growing water scarcity and energy demands. Future research may incorporate deep learning techniques to enhance these models.