Skip to main content

ORIGINAL RESEARCH article

Front. Mar. Sci.
Sec. Coastal Ocean Processes
Volume 12 - 2025 | doi: 10.3389/fmars.2025.1537696
This article is part of the Research Topic Innovative Approaches to Coastal Zone Monitoring and Geodata Management View all articles

Real-time Prediction of Port Water Levels Based on EMD-PSO-RBFNN

Provisionally accepted
Liju Wang Liju Wang 1Shenghao Liao Shenghao Liao 1*Sisi Wang Sisi Wang 1Jianchuan Yin Jianchuan Yin 2Ronghui Li Ronghui Li 2Jingyu Guan Jingyu Guan 1
  • 1 Naval Architecture And Shipping College, Guangdong Ocean University, Zhanjiang, Guangdong Province, China
  • 2 Guangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching, Guangdong Ocean University, Zhanjiang, Guangdong Province, China

The final, formatted version of the article will be published soon.

    Addressing the spatial variability, temporal dynamics, and nonlinearity characteristics of port water levels, a hybrid prediction scheme is 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 is decomposed into sub-series characterized by lower nonlinearity. Subsequently, PSO is applied to fine-tune the center and width parameters of the RBFNN, thereby enhancing the model's predictive performance. The optimized PSO-RBFNN model is employed to make predictions on the decomposed sub-series. Finally, reconstruction of the predicted sub-series yields the final water level predictions. The feasibility and effectiveness of the proposed model are validated using measured port water level data. Results from simulations highlight the model's ability to deliver accurate predictions across various lead times. Furthermore, comparative analysis reveals 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.

    Keywords: port water level prediction, Radial basis function neural network, Particle swarm optimization algorithmd, Empirical Mode Decomposition, Hybrid model

    Received: 01 Dec 2024; Accepted: 03 Jan 2025.

    Copyright: © 2025 Wang, Liao, Wang, Yin, Li and Guan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Shenghao Liao, Naval Architecture And Shipping College, Guangdong Ocean University, Zhanjiang, Guangdong Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.