Research on Optimal Selection of Runoff Prediction Models Based on Coupled Machine Learning Methods

Abstract

Runoff fluctuations under the influence of climate change and human activities present a significant challenge and valuable application in constructing high-accuracy runoff prediction models. This study aims to address this challenge by taking the Wanzhou station in the Three Gorges Reservoir area as a case study to optimize various prediction models. The study first selects artificial neural network (ANN) and support vector machine (SVM) as the base models. Then, it evaluates and selects from three time-series decomposition methods: Time-Varying Filter-based Empirical Mode Decomposition (TVF-EMD), Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and Variational Mode Decomposition (VMD). Subsequently, these decomposition methods are coupled with optimization algorithms, including Whale Optimization Algorithm (WOA), Grasshopper Optimization Algorithm (GOA), and Sparrow Search Algorithm (SSA), to construct various hybrid prediction models. The results indicate that: (1) Among the single prediction models, the Long Short-Term Memory (LSTM) model outperforms the Backpropagation Neural Network (BP) and SVM in terms of prediction accuracy; (2) The hybrid models show superior accuracy compared to the individual models, with the VMD-LSTM model outperforming the CEEMDAN-LSTM and TVF-EMD-LSTM models; (3) Among the coupled machine learning prediction models, the VMD-SSA-LSTM model achieves the highest accuracy. Employing a "decomposition-reconstruction" strategy combined with robust optimization algorithms enhances the performance of machine learning prediction models, thereby significantly improving the runoff prediction capabilities in watershed hydrological models.