A Ship Trajectory Prediction Method Based on an Optuna–BILSTM Model
Open Access
- 27 April 2024
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 14 (9) , 3719
Abstract
In the field of maritime traffic management, overcoming the challenges of low prediction accuracy and computational inefficiency in ship trajectory prediction is crucial for collision avoidance. This paper presents an advanced solution using a deep bidirectional long- and short-term memory network (BILSTM) and the Optuna hyperparameter automatic optimized framework. Utilizing automatic identification system (AIS) data to analyze ship navigation patterns, the study applies Optuna to fine-tune the hyperparameters of the BILSTM network to improve prediction accuracy and efficiency. The developed Optuna–BILSTM model shows a remarkable 7% increase in prediction accuracy over traditional back propagation (BP) neural networks and standard BILSTM models. These results not only improve ship navigation and safety but also have significant implications for the development of autonomous ship collision avoidance systems, marking a significant step toward safer and more efficient maritime traffic management.Keywords
Funding Information
- Ningbo International Science and Technology Cooperation Project: Theoretical and Technological Research on Cooperative Traffic Control of Port-Collector-Supply Highway (2023H020, 52272334)
- National Natural Science Foundation of China (NNSF) Top Project: Traffic State Estimation and Control Methods for Port-Collector-Supply Roads in Project Networked Vehicle Environment (2023H020, 52272334)
This publication has 24 references indexed in Scilit:
- IS-STGCNN: An Improved Social spatial-temporal graph convolutional neural network for ship trajectory predictionOcean Engineering, 2022
- Towards a probabilistic model for estimation of grounding accidents in fluctuating backwater zone of the Three Gorges ReservoirReliability Engineering & System Safety, 2021
- Ship trajectory uncertainty prediction based on a Gaussian Process modelOcean Engineering, 2019
- Inland Ship Trajectory Restoration by Recurrent Neural NetworkJournal of Navigation, 2019
- Optimal air route flight conflict resolution based on receding horizon controlAerospace Science and Technology, 2016
- Real-time vessel behavior predictionEvolving Systems, 2015
- Comprehensive Analysis of Automatic Identification System (AIS) Data in Regard to Vessel Movement PredictionJournal of Navigation, 2014
- Machine learning for vessel trajectories using compression, alignments and domain knowledgeExpert Systems with Applications, 2012
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Learning representations by back-propagating errorsNature, 1986