Flow Field Analysis and Development of a Prediction Model Based on Deep Learning

The velocity of ocean currents significantly affects the trajectory prediction of ocean drifters and the safe navigation of intelligent vessels. Currently, most ocean current predictions focus on time-based forecasts at specific fixed points. In this study, deep learning based on the flow field pred...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingjie Yu, Xiufeng Zhang, Lucai Wang, Rui Tian, Xiaobin Qian, Dongdong Guo, Yanwei Liu
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/12/11/1929
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226539979866112
author Yingjie Yu
Xiufeng Zhang
Lucai Wang
Rui Tian
Xiaobin Qian
Dongdong Guo
Yanwei Liu
author_facet Yingjie Yu
Xiufeng Zhang
Lucai Wang
Rui Tian
Xiaobin Qian
Dongdong Guo
Yanwei Liu
author_sort Yingjie Yu
collection DOAJ
description The velocity of ocean currents significantly affects the trajectory prediction of ocean drifters and the safe navigation of intelligent vessels. Currently, most ocean current predictions focus on time-based forecasts at specific fixed points. In this study, deep learning based on the flow field prediction model (CNNs–MHA–BiLSTMs) is proposed, which predicts the changes in ocean currents by learning from historical flow fields. Unlike conventional models that focus on single-point current velocity data, the CNNs–MHA–BiLSTMs model focuses on the ocean surface current information within a specific area. The CNNs–MHA–BiLSTMs model integrates multiple convolutional neural networks (CNNs) in parallel, multi-head attention (MHA), and bidirectional long short-term memory networks (BiLSTMs). The model demonstrated exceptional modelling capabilities in handling spatiotemporal features. The proposed model was validated by comparing its predictions with those predicted by the MIKE21 flow model of the ocean area within proximity to Dalian Port (which used a commercial numerical model), as well as those predicted by other deep learning algorithms. The results showed that the model offers significant advantages and efficiency in simulating and predicting ocean surface currents. Moreover, the accuracy of regional flow field prediction improved with an increase in the number of sampling points used for training. The proposed CNNs–MHA–BiLSTMs model can provide theoretical support for maritime search and rescue, the control or path planning of Unmanned Surface Vehicles (USVs), as well as protecting offshore structures in the future.
format Article
id doaj-art-614894f81dfb4f7ea9604dd5250e7bb5
institution OA Journals
issn 2077-1312
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-614894f81dfb4f7ea9604dd5250e7bb52025-08-20T02:05:03ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-10-011211192910.3390/jmse12111929Flow Field Analysis and Development of a Prediction Model Based on Deep LearningYingjie Yu0Xiufeng Zhang1Lucai Wang2Rui Tian3Xiaobin Qian4Dongdong Guo5Yanwei Liu6Navigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation Department, Dalian Naval Academy, Dalian 116018, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaZhilong (Dalian) Marine Technology, Co., Ltd., Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaThe velocity of ocean currents significantly affects the trajectory prediction of ocean drifters and the safe navigation of intelligent vessels. Currently, most ocean current predictions focus on time-based forecasts at specific fixed points. In this study, deep learning based on the flow field prediction model (CNNs–MHA–BiLSTMs) is proposed, which predicts the changes in ocean currents by learning from historical flow fields. Unlike conventional models that focus on single-point current velocity data, the CNNs–MHA–BiLSTMs model focuses on the ocean surface current information within a specific area. The CNNs–MHA–BiLSTMs model integrates multiple convolutional neural networks (CNNs) in parallel, multi-head attention (MHA), and bidirectional long short-term memory networks (BiLSTMs). The model demonstrated exceptional modelling capabilities in handling spatiotemporal features. The proposed model was validated by comparing its predictions with those predicted by the MIKE21 flow model of the ocean area within proximity to Dalian Port (which used a commercial numerical model), as well as those predicted by other deep learning algorithms. The results showed that the model offers significant advantages and efficiency in simulating and predicting ocean surface currents. Moreover, the accuracy of regional flow field prediction improved with an increase in the number of sampling points used for training. The proposed CNNs–MHA–BiLSTMs model can provide theoretical support for maritime search and rescue, the control or path planning of Unmanned Surface Vehicles (USVs), as well as protecting offshore structures in the future.https://www.mdpi.com/2077-1312/12/11/1929ocean surface currentsocean current predictionflow field simulationneural networksspatiotemporal evolution
spellingShingle Yingjie Yu
Xiufeng Zhang
Lucai Wang
Rui Tian
Xiaobin Qian
Dongdong Guo
Yanwei Liu
Flow Field Analysis and Development of a Prediction Model Based on Deep Learning
Journal of Marine Science and Engineering
ocean surface currents
ocean current prediction
flow field simulation
neural networks
spatiotemporal evolution
title Flow Field Analysis and Development of a Prediction Model Based on Deep Learning
title_full Flow Field Analysis and Development of a Prediction Model Based on Deep Learning
title_fullStr Flow Field Analysis and Development of a Prediction Model Based on Deep Learning
title_full_unstemmed Flow Field Analysis and Development of a Prediction Model Based on Deep Learning
title_short Flow Field Analysis and Development of a Prediction Model Based on Deep Learning
title_sort flow field analysis and development of a prediction model based on deep learning
topic ocean surface currents
ocean current prediction
flow field simulation
neural networks
spatiotemporal evolution
url https://www.mdpi.com/2077-1312/12/11/1929
work_keys_str_mv AT yingjieyu flowfieldanalysisanddevelopmentofapredictionmodelbasedondeeplearning
AT xiufengzhang flowfieldanalysisanddevelopmentofapredictionmodelbasedondeeplearning
AT lucaiwang flowfieldanalysisanddevelopmentofapredictionmodelbasedondeeplearning
AT ruitian flowfieldanalysisanddevelopmentofapredictionmodelbasedondeeplearning
AT xiaobinqian flowfieldanalysisanddevelopmentofapredictionmodelbasedondeeplearning
AT dongdongguo flowfieldanalysisanddevelopmentofapredictionmodelbasedondeeplearning
AT yanweiliu flowfieldanalysisanddevelopmentofapredictionmodelbasedondeeplearning