MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature Prediction
Sea surface temperature (SST) is a crucial factor that affects global climate and marine activities. Predicting SST at different temporal scales benefits various applications, from short-term SST prediction for weather forecasting to long-term SST prediction for analyzing El Niño–Southern Oscillatio...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/10/2371 |
| _version_ | 1827666795869241344 |
|---|---|
| author | Siyun Hou Wengen Li Tianying Liu Shuigeng Zhou Jihong Guan Rufu Qin Zhenfeng Wang |
| author_facet | Siyun Hou Wengen Li Tianying Liu Shuigeng Zhou Jihong Guan Rufu Qin Zhenfeng Wang |
| author_sort | Siyun Hou |
| collection | DOAJ |
| description | Sea surface temperature (SST) is a crucial factor that affects global climate and marine activities. Predicting SST at different temporal scales benefits various applications, from short-term SST prediction for weather forecasting to long-term SST prediction for analyzing El Niño–Southern Oscillation (ENSO). However, existing approaches for SST prediction train separate models for different temporal scales, which is inefficient and cannot take advantage of the correlations among the temperatures of different scales to improve the prediction performance. In this work, we propose a unified spatio-temporal model termed the Multi-In and Multi-Out (MIMO) model to predict SST at different scales. MIMO is an encoder–decoder model, where the encoder learns spatio-temporal features from the SST data of multiple scales, and fuses the learned features with a Cross Scale Fusion (CSF) operation. The decoder utilizes the learned features from the encoder to adaptively predict the SST of different scales. To our best knowledge, this is the first work to predict SST at different temporal scales simultaneously with a single model. According to the experimental evaluation on the Optimum Interpolation SST (OISST) dataset, MIMO achieves the state-of-the-art prediction performance. |
| first_indexed | 2024-03-10T01:56:44Z |
| format | Article |
| id | doaj.art-4a7ee432892c4f608f613040488e5a18 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T01:56:44Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4a7ee432892c4f608f613040488e5a182023-11-23T12:55:06ZengMDPI AGRemote Sensing2072-42922022-05-011410237110.3390/rs14102371MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature PredictionSiyun Hou0Wengen Li1Tianying Liu2Shuigeng Zhou3Jihong Guan4Rufu Qin5Zhenfeng Wang6Department of Computer Science and Technology, Tongji University, Shanghai 200082, ChinaDepartment of Computer Science and Technology, Tongji University, Shanghai 200082, ChinaDepartment of Computer Science and Technology, Tongji University, Shanghai 200082, ChinaShanghai Key Lab of Intelligent Information Processing, Shanghai 200438, ChinaDepartment of Computer Science and Technology, Tongji University, Shanghai 200082, ChinaDepartment of Computer Science and Technology, Tongji University, Shanghai 200082, ChinaProject Management Office of China National Scientific Seafloor Observatory, Tongji University, Shanghai 200082, ChinaSea surface temperature (SST) is a crucial factor that affects global climate and marine activities. Predicting SST at different temporal scales benefits various applications, from short-term SST prediction for weather forecasting to long-term SST prediction for analyzing El Niño–Southern Oscillation (ENSO). However, existing approaches for SST prediction train separate models for different temporal scales, which is inefficient and cannot take advantage of the correlations among the temperatures of different scales to improve the prediction performance. In this work, we propose a unified spatio-temporal model termed the Multi-In and Multi-Out (MIMO) model to predict SST at different scales. MIMO is an encoder–decoder model, where the encoder learns spatio-temporal features from the SST data of multiple scales, and fuses the learned features with a Cross Scale Fusion (CSF) operation. The decoder utilizes the learned features from the encoder to adaptively predict the SST of different scales. To our best knowledge, this is the first work to predict SST at different temporal scales simultaneously with a single model. According to the experimental evaluation on the Optimum Interpolation SST (OISST) dataset, MIMO achieves the state-of-the-art prediction performance.https://www.mdpi.com/2072-4292/14/10/2371sea surface temperature (SST)multi-scale SST predictionspatio-temporal modeldata fusion |
| spellingShingle | Siyun Hou Wengen Li Tianying Liu Shuigeng Zhou Jihong Guan Rufu Qin Zhenfeng Wang MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature Prediction Remote Sensing sea surface temperature (SST) multi-scale SST prediction spatio-temporal model data fusion |
| title | MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature Prediction |
| title_full | MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature Prediction |
| title_fullStr | MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature Prediction |
| title_full_unstemmed | MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature Prediction |
| title_short | MIMO: A Unified Spatio-Temporal Model for Multi-Scale Sea Surface Temperature Prediction |
| title_sort | mimo a unified spatio temporal model for multi scale sea surface temperature prediction |
| topic | sea surface temperature (SST) multi-scale SST prediction spatio-temporal model data fusion |
| url | https://www.mdpi.com/2072-4292/14/10/2371 |
| work_keys_str_mv | AT siyunhou mimoaunifiedspatiotemporalmodelformultiscaleseasurfacetemperatureprediction AT wengenli mimoaunifiedspatiotemporalmodelformultiscaleseasurfacetemperatureprediction AT tianyingliu mimoaunifiedspatiotemporalmodelformultiscaleseasurfacetemperatureprediction AT shuigengzhou mimoaunifiedspatiotemporalmodelformultiscaleseasurfacetemperatureprediction AT jihongguan mimoaunifiedspatiotemporalmodelformultiscaleseasurfacetemperatureprediction AT rufuqin mimoaunifiedspatiotemporalmodelformultiscaleseasurfacetemperatureprediction AT zhenfengwang mimoaunifiedspatiotemporalmodelformultiscaleseasurfacetemperatureprediction |