Seven-day sea surface temperature prediction using a 3DConv-LSTM model
Due to the application demand, users have higher expectations for the accuracy and resolution of sea surface temperature (SST) products. Recent advances in deep learning show great advantages in exploiting massive ocean datasets, and provides opportunities for investigating regional SST predictions...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2022.905848/full |
| _version_ | 1828115881906929664 |
|---|---|
| author | Li Wei Lei Guan Lei Guan Lei Guan |
| author_facet | Li Wei Lei Guan Lei Guan Lei Guan |
| author_sort | Li Wei |
| collection | DOAJ |
| description | Due to the application demand, users have higher expectations for the accuracy and resolution of sea surface temperature (SST) products. Recent advances in deep learning show great advantages in exploiting massive ocean datasets, and provides opportunities for investigating regional SST predictions in an efficiency approach. However, for deep learning-based SST prediction to be adopted by users, the output must be accurate. This paper investigates the 7-day SST prediction over the China seas and their adjacent waters at a 0.05° spatial resolution. To improve the prediction’s accuracy, we designed a deep learning model combining the three-dimensional convolution and long short-term memory under multi-input multi-output strategy. The Operational SST and Sea Ice Analysis (OSTIA) SST anomaly was used as training data. To test the model prediction ability, we verified the predicted results with the Sub-seasonal to Seasonal (S2S) prediction data from 2015 to 2019. Validation of the predicted SSTs using the OSTIA test datasets show that the root-mean-square error increases from 0.27°C to 0.53°C during the 1- to 7-day lead time, with predictability decreases from southeast to northwest in the study area. Furthermore, the comparison of predicted SST and S2S data with Argo shows that our model is slightly more accurate, which can achieve -0.08°C bias, with a standard deviation of 0.35°C for a 1-day lead time and -0.07°C bias, with a standard deviation of 0.59°C for a 7-day lead time. The results indicate that the proposed deep learning model is accurate and can be applied in regional daily SST prediction. |
| first_indexed | 2024-04-11T12:48:36Z |
| format | Article |
| id | doaj.art-73909f30323248d09cfece58425d8857 |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-04-11T12:48:36Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-73909f30323248d09cfece58425d88572022-12-22T04:23:17ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452022-12-01910.3389/fmars.2022.905848905848Seven-day sea surface temperature prediction using a 3DConv-LSTM modelLi Wei0Lei Guan1Lei Guan2Lei Guan3Sanya Oceanographic Institution, Ocean University of China, Sanya, ChinaSanya Oceanographic Institution, Ocean University of China, Sanya, ChinaCollege of Marine Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao, ChinaLaboratory for Regional Oceanography and Numerical Modeling, Qingdao National Laboratory for Marine Science and Technology, Qingdao, ChinaDue to the application demand, users have higher expectations for the accuracy and resolution of sea surface temperature (SST) products. Recent advances in deep learning show great advantages in exploiting massive ocean datasets, and provides opportunities for investigating regional SST predictions in an efficiency approach. However, for deep learning-based SST prediction to be adopted by users, the output must be accurate. This paper investigates the 7-day SST prediction over the China seas and their adjacent waters at a 0.05° spatial resolution. To improve the prediction’s accuracy, we designed a deep learning model combining the three-dimensional convolution and long short-term memory under multi-input multi-output strategy. The Operational SST and Sea Ice Analysis (OSTIA) SST anomaly was used as training data. To test the model prediction ability, we verified the predicted results with the Sub-seasonal to Seasonal (S2S) prediction data from 2015 to 2019. Validation of the predicted SSTs using the OSTIA test datasets show that the root-mean-square error increases from 0.27°C to 0.53°C during the 1- to 7-day lead time, with predictability decreases from southeast to northwest in the study area. Furthermore, the comparison of predicted SST and S2S data with Argo shows that our model is slightly more accurate, which can achieve -0.08°C bias, with a standard deviation of 0.35°C for a 1-day lead time and -0.07°C bias, with a standard deviation of 0.59°C for a 7-day lead time. The results indicate that the proposed deep learning model is accurate and can be applied in regional daily SST prediction.https://www.frontiersin.org/articles/10.3389/fmars.2022.905848/fullLong short-term memoryoperational SST and sea ice analysis (OSTIA)sea surface temperature (SST)spatiotemporal predictionthree-dimensional convolution |
| spellingShingle | Li Wei Lei Guan Lei Guan Lei Guan Seven-day sea surface temperature prediction using a 3DConv-LSTM model Frontiers in Marine Science Long short-term memory operational SST and sea ice analysis (OSTIA) sea surface temperature (SST) spatiotemporal prediction three-dimensional convolution |
| title | Seven-day sea surface temperature prediction using a 3DConv-LSTM model |
| title_full | Seven-day sea surface temperature prediction using a 3DConv-LSTM model |
| title_fullStr | Seven-day sea surface temperature prediction using a 3DConv-LSTM model |
| title_full_unstemmed | Seven-day sea surface temperature prediction using a 3DConv-LSTM model |
| title_short | Seven-day sea surface temperature prediction using a 3DConv-LSTM model |
| title_sort | seven day sea surface temperature prediction using a 3dconv lstm model |
| topic | Long short-term memory operational SST and sea ice analysis (OSTIA) sea surface temperature (SST) spatiotemporal prediction three-dimensional convolution |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2022.905848/full |
| work_keys_str_mv | AT liwei sevendayseasurfacetemperaturepredictionusinga3dconvlstmmodel AT leiguan sevendayseasurfacetemperaturepredictionusinga3dconvlstmmodel AT leiguan sevendayseasurfacetemperaturepredictionusinga3dconvlstmmodel AT leiguan sevendayseasurfacetemperaturepredictionusinga3dconvlstmmodel |