BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in Ocean
Mesoscale eddies play a critical role in sea navigation and route planning, yet traditional prediction methods have often overlooked their spatial relationships, relying on indirect approaches to capture their distribution across extensive maps. To address this limitation, we present BiST-SA-LSTM, a...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/1/52 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588191176065024 |
|---|---|
| author | Yaoran Chen Zijian Zhao Yaojun Yang Xiaowei Li Yan Peng Hao Wu Xi Zhou Dan Zhang Hongyu Wei |
| author_facet | Yaoran Chen Zijian Zhao Yaojun Yang Xiaowei Li Yan Peng Hao Wu Xi Zhou Dan Zhang Hongyu Wei |
| author_sort | Yaoran Chen |
| collection | DOAJ |
| description | Mesoscale eddies play a critical role in sea navigation and route planning, yet traditional prediction methods have often overlooked their spatial relationships, relying on indirect approaches to capture their distribution across extensive maps. To address this limitation, we present BiST-SA-LSTM, an end-to-end prediction framework that combines Bidirectional Spatial Temporal LSTM and Self-Attention mechanisms. Utilizing data sourced from the South China Sea and its surrounding regions, which are renowned for their intricate maritime dynamics, our methodology outperforms similar models across a range of evaluation metrics and visual assessments. This is particularly evident in our ability to provide accurate long-term forecasts that extend for up to 10 days. Furthermore, integrating sea surface variables enhances forecasting accuracy, contributing to advancements in oceanic physics. |
| format | Article |
| id | doaj-art-40e0e6c4580d4350900f0e327ee359de |
| institution | Kabale University |
| issn | 2077-1312 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-40e0e6c4580d4350900f0e327ee359de2025-01-24T13:36:41ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-12-011315210.3390/jmse13010052BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in OceanYaoran Chen0Zijian Zhao1Yaojun Yang2Xiaowei Li3Yan Peng4Hao Wu5Xi Zhou6Dan Zhang7Hongyu Wei8Institute of Artificial Intelligence, Collaborative Innovation Center for the Marine Artificial Intelligence, Shanghai University, Shanghai 200444, ChinaInstitute of Artificial Intelligence, Collaborative Innovation Center for the Marine Artificial Intelligence, Shanghai University, Shanghai 200444, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai 200444, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaInstitute of Artificial Intelligence, Collaborative Innovation Center for the Marine Artificial Intelligence, Shanghai University, Shanghai 200444, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaShanghai Artificial Intelligence Laboratory, Shanghai 200032, ChinaInstitute of Artificial Intelligence, Collaborative Innovation Center for the Marine Artificial Intelligence, Shanghai University, Shanghai 200444, ChinaInstitute of Artificial Intelligence, Collaborative Innovation Center for the Marine Artificial Intelligence, Shanghai University, Shanghai 200444, ChinaMesoscale eddies play a critical role in sea navigation and route planning, yet traditional prediction methods have often overlooked their spatial relationships, relying on indirect approaches to capture their distribution across extensive maps. To address this limitation, we present BiST-SA-LSTM, an end-to-end prediction framework that combines Bidirectional Spatial Temporal LSTM and Self-Attention mechanisms. Utilizing data sourced from the South China Sea and its surrounding regions, which are renowned for their intricate maritime dynamics, our methodology outperforms similar models across a range of evaluation metrics and visual assessments. This is particularly evident in our ability to provide accurate long-term forecasts that extend for up to 10 days. Furthermore, integrating sea surface variables enhances forecasting accuracy, contributing to advancements in oceanic physics.https://www.mdpi.com/2077-1312/13/1/52mesoscale eddy distributionspatial temporal predictionBi-LSTMself-attentionmultivariable analysis |
| spellingShingle | Yaoran Chen Zijian Zhao Yaojun Yang Xiaowei Li Yan Peng Hao Wu Xi Zhou Dan Zhang Hongyu Wei BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in Ocean Journal of Marine Science and Engineering mesoscale eddy distribution spatial temporal prediction Bi-LSTM self-attention multivariable analysis |
| title | BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in Ocean |
| title_full | BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in Ocean |
| title_fullStr | BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in Ocean |
| title_full_unstemmed | BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in Ocean |
| title_short | BiST-SA-LSTM: A Deep Learning Framework for End-to-End Prediction of Mesoscale Eddy Distribution in Ocean |
| title_sort | bist sa lstm a deep learning framework for end to end prediction of mesoscale eddy distribution in ocean |
| topic | mesoscale eddy distribution spatial temporal prediction Bi-LSTM self-attention multivariable analysis |
| url | https://www.mdpi.com/2077-1312/13/1/52 |
| work_keys_str_mv | AT yaoranchen bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT zijianzhao bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT yaojunyang bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT xiaoweili bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT yanpeng bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT haowu bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT xizhou bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT danzhang bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean AT hongyuwei bistsalstmadeeplearningframeworkforendtoendpredictionofmesoscaleeddydistributioninocean |