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...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |