Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian Process
The accurate prediction of sea surface temperature (SST) is essential for studying marine phenomena, understanding climate dynamics, and forecasting environmental changes. However, developing a general SST prediction model is challenging due to significant regional variations and the impacts of dive...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/5/1373 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850222696182317056 |
|---|---|
| author | Zhenglin Li Qingxiong Zhu Dan Zhang Hao Wu Yan Peng |
| author_facet | Zhenglin Li Qingxiong Zhu Dan Zhang Hao Wu Yan Peng |
| author_sort | Zhenglin Li |
| collection | DOAJ |
| description | The accurate prediction of sea surface temperature (SST) is essential for studying marine phenomena, understanding climate dynamics, and forecasting environmental changes. However, developing a general SST prediction model is challenging due to significant regional variations and the impacts of diverse climate phenomena. To improve the performance of SST predictions, we propose a hybrid framework that effectively models the spatial and temporal dependencies of SST data with a Gaussian process-enhanced Long Short-Term Memory network. The LSTM module adaptively captures both long and short-term temporal trends in SST variation, while the Gaussian process incorporates the spatial dependency of neighboring data to further refine the predictions. Furthermore, our proposed framework estimates the uncertainty associated with SST predictions, providing crucial information for practical applications. Comprehensive experiments are conducted on the OISST dataset, with a focus on the Bohai Sea and the South China Sea. The results of our framework outperform state-of-the-art methods, validating its superiority in SST prediction. |
| format | Article |
| id | doaj-art-61390eb3c8cb40d8b39ccda00ae4ee6b |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-61390eb3c8cb40d8b39ccda00ae4ee6b2025-08-20T02:06:15ZengMDPI AGSensors1424-82202025-02-01255137310.3390/s25051373Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian ProcessZhenglin Li0Qingxiong Zhu1Dan Zhang2Hao Wu3Yan Peng4School of Future Technology, Shanghai University, Shanghai 200444, ChinaInstitute of Artificial Intelligence, Shanghai University, Shanghai 200444, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaSchool of Future Technology, Shanghai University, Shanghai 200444, ChinaThe accurate prediction of sea surface temperature (SST) is essential for studying marine phenomena, understanding climate dynamics, and forecasting environmental changes. However, developing a general SST prediction model is challenging due to significant regional variations and the impacts of diverse climate phenomena. To improve the performance of SST predictions, we propose a hybrid framework that effectively models the spatial and temporal dependencies of SST data with a Gaussian process-enhanced Long Short-Term Memory network. The LSTM module adaptively captures both long and short-term temporal trends in SST variation, while the Gaussian process incorporates the spatial dependency of neighboring data to further refine the predictions. Furthermore, our proposed framework estimates the uncertainty associated with SST predictions, providing crucial information for practical applications. Comprehensive experiments are conducted on the OISST dataset, with a focus on the Bohai Sea and the South China Sea. The results of our framework outperform state-of-the-art methods, validating its superiority in SST prediction.https://www.mdpi.com/1424-8220/25/5/1373sea surface temperatureprobabilistic forecastingspatiotemporal correlationGaussian Process Regression |
| spellingShingle | Zhenglin Li Qingxiong Zhu Dan Zhang Hao Wu Yan Peng Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian Process Sensors sea surface temperature probabilistic forecasting spatiotemporal correlation Gaussian Process Regression |
| title | Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian Process |
| title_full | Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian Process |
| title_fullStr | Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian Process |
| title_full_unstemmed | Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian Process |
| title_short | Sea Surface Temperature Prediction Enhanced by Exploring Spatiotemporal Correlation Based on LSTM and Gaussian Process |
| title_sort | sea surface temperature prediction enhanced by exploring spatiotemporal correlation based on lstm and gaussian process |
| topic | sea surface temperature probabilistic forecasting spatiotemporal correlation Gaussian Process Regression |
| url | https://www.mdpi.com/1424-8220/25/5/1373 |
| work_keys_str_mv | AT zhenglinli seasurfacetemperaturepredictionenhancedbyexploringspatiotemporalcorrelationbasedonlstmandgaussianprocess AT qingxiongzhu seasurfacetemperaturepredictionenhancedbyexploringspatiotemporalcorrelationbasedonlstmandgaussianprocess AT danzhang seasurfacetemperaturepredictionenhancedbyexploringspatiotemporalcorrelationbasedonlstmandgaussianprocess AT haowu seasurfacetemperaturepredictionenhancedbyexploringspatiotemporalcorrelationbasedonlstmandgaussianprocess AT yanpeng seasurfacetemperaturepredictionenhancedbyexploringspatiotemporalcorrelationbasedonlstmandgaussianprocess |