Real-time prediction of port water levels based on EMD-PSO-RBFNN

Addressing the spatial variability, temporal dynamics, and non-linearity characteristics of port water levels, a hybrid prediction scheme was proposed, which integrates empirical mode decomposition (EMD) with a radial basis function neural network (RBFNN), optimized using the particle swarm optimization (PSO) algorithm. First, through the application of EMD, the port water level time series was decomposed into sub-series characterized by lower non-linearity. Subsequently, PSO was applied to fine-tune the center and spread parameters of the RBFNN, thereby enhancing the model’s predictive performance. The optimized PSO-RBFNN model was employed to make predictions on the decomposed sub-series. Finally, reconstruction of the predicted sub-series yielded the final water level predictions. The feasibility and effectiveness of the proposed model were validated using measured port water level data. Results from simulations highlighted the model’s ability to deliver accurate predictions across various lead times. Furthermore, comparative analysis revealed that the proposed model outperforms alternative methods in port water level prediction. Therefore, the proposed model serves as a reliable, efficient, and real-time prediction tool, providing robust support for port operational safety.