A hybrid variational mode decomposition and sparrow search algorithm-based least square support vector machine model for monthly runoff forecasting

Abstract Monthly runoff forecasting has always been a key problem in water resources management. As data-driven method, the least square support vector machine (LSSVM) method investigated by numerous studies forecasting. However, selecting appropriate parameters for LSSVM is to obtaining satisfactory model performance. In this study, we propose hybrid monthly forecasting, VMD-SSA-LSSVM short, which combines variational mode decomposition (VMD) with and of are optimized sparrow search algorithm (SSA). Firstly, VMD utilized decompose original time series data into several subsequences. Secondly, employed simulate each subsequence, SSA. Finally, simulated results subsequence accumulated as final results. The validity proposed was verified two reservoirs located China. Four frequently-used statistical indexes, namely Nash efficiency coefficient, root mean squared error, correlation coefficient absolute percentage error were used evaluate demonstrate superiority over compared models terms all indicating that it beneficial enhancing forecast accuracy.