With the rapid development of China's maritime industry, accurate prediction of ship traffic flow is of great significance to improve the operational efficiency of ports. In this paper, we propose a combined model that combines the Seasonal Autoregressive Integrated Moving Average (SARIMA) model and Long Short-Term Memory (LSTM) fusing Multi-head Attention mechanism to improve the prediction accuracy of ship traffic flow. The example data summarizes the actual data from Guangzhou port production business system from 2014-2023. The study integrates the predictive capabilities of linear and nonlinear models while considering the influence of external economic factors on ship traffic flow, possessing better forecasting outcomes. Through comparison experiments with other three models, the combined deep learning model shows superior forecasting performance.
A Combined Deep Learning Method for Prediction of Ship Traffic Flow
23.05.2025
2814992 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Traffic flow prediction method based on deep learning
Europäisches Patentamt | 2024
|Regional ship traffic flow prediction method and system
Europäisches Patentamt | 2023
|Short-Term Traffic Flow Prediction: A Method of Combined Deep Learnings
DOAJ | 2021
|Urban traffic flow prediction method based on deep learning
Europäisches Patentamt | 2025
|Lightweight traffic flow prediction method based on deep learning
Europäisches Patentamt | 2024
|