Comprehensive Forecasting Model for Port Container Throughput Based on Hybrid Deep Neural Networks

DOI

10.2991/978-94-6463-514-0_35How to use a DOI?

Keywords

container throughput; sequence decomposition; neural networks; Guangzhou port

Abstract

Port container throughput holds considerable importance for port construction planning and operational decision-making management. The problem of container throughput forecasting essentially entails modeling a nonlinear dynamic system driven by multiple variables. To improve the predictive precision of container throughput and to process various types of complex, nonlinear data, the variational mode decomposition (VMD) algorithm is employed to perform feature decomposition on the container throughput series. A hybrid deep neural network based on CNN-GRU is then constructed to decipher the complex mapping relationships between the influencing factors and feature sequences, culminating in the development of a comprehensive VMD-CNN-GRU port container throughput forecasting model. Empirical analysis is conducted on the container throughput series from the Guangzhou port to test the predictive effectiveness of the proposed integrated model. Comparative experimental analysis with various models indicates that the proposed integrated model yields the best predictive results, confirming its effectiveness and accuracy. This model provides support for port container throughput forecasting tasks.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Qihao Tan
AU  - Hanyan Huang
PY  - 2024
DA  - 2024/09/28
TI  - Comprehensive Forecasting Model for Port Container Throughput Based on Hybrid Deep Neural Networks
BT  - Proceedings of the 2024 7th International Symposium on Traffic Transportation and Civil Architecture (ISTTCA 2024)
PB  - Atlantis Press
SP  - 332
EP  - 341
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-514-0_35
DO  - 10.2991/978-94-6463-514-0_35
ID  - Tan2024
ER  -