Shanghai Port Container Throughput Prediction Based on EEMD-WOA-LSTM

Given the important role of container throughput prediction in port management and development, this paper proposes a combined prediction model based on EEMD-WOA-LSTM. The model first uses the Ensemble Empirical Mode Decomposition (EEMD) technique to decompose monthly container throughput data into multiple intrinsic mode functions (IMF) and trend residuals with different characteristics. Then, it utilizes a Long Short-Term Memory (LSTM) network optimized by Whale Optimization Algorithm (WOA) to predict each component. Finally, the predictions of all components are integrated to obtain the final forecast value. Empirical results show that the proposed combined prediction model significantly outperforms traditional models in terms of prediction accuracy and stability, demonstrating good application prospects. This model can provide scientific evidence and decision support for relevant port authorities and shipping enterprises.