Research on water level prediction considering uncertainty quantification based on EMD-PSO-RBFNN hybrid model
With the rapid development of inland waterway transportation, the demand for reliability and accuracy in hydrological forecasting has been increasing. Inland water levels are affected by rainfall, upstream flood discharge, and seasonal factors, exhibiting highly nonlinear and non-stationary characteristics. Traditional deterministic prediction models can hardly meet the requirements of refined scheduling. This paper proposes a hybrid water level prediction model that integrates Empirical Mode Decomposition (EMD), Particle Swarm Optimization (PSO), and Radial Basis Function Neural Network (RBFNN), and innovatively introduces an uncertainty quantification mechanism based on the statistic. First, EMD is used to decompose the original complex water level signal into multiple Intrinsic Mode Functions (IMFs) to reduce data nonstationarity. Second, for each IMF component, the PSO algorithm is adopted to globally optimize the centers and spread constants of the RBF neural network, constructing high-precision base prediction models. Finally, the uncertainty coefficient is calculated. Using actual water level data from the Port of Guigang as the experimental object, the results show that the prediction accuracy of the hybrid model reaches R2=0.9415, and the α coefficient can effectively quantify the dynamic risk of prediction results. This study not only provides a high-precision technical approach for inland water level prediction, but its uncertainty quantification results also offer a scientific basis for the reliability evaluation and risk early warning of hydrological forecasting.