PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific
Accurately predicting the spatio-temporal evolution trends and long-term dynamics of three-dimensional ocean temperature and salinity plays a crucial role in monitoring climate system changes and conducting fundamental oceanographic research. Numerical models are the most prevalent of the traditiona...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-11-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2024.1477710/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589550666383360 |
|---|---|
| author | Song Wu Senliang Bao Wei Dong Senzhang Wang Xiaojiang Zhang Chengcheng Shao Junxing Zhu Xiaoyong Li |
| author_facet | Song Wu Senliang Bao Wei Dong Senzhang Wang Xiaojiang Zhang Chengcheng Shao Junxing Zhu Xiaoyong Li |
| author_sort | Song Wu |
| collection | DOAJ |
| description | Accurately predicting the spatio-temporal evolution trends and long-term dynamics of three-dimensional ocean temperature and salinity plays a crucial role in monitoring climate system changes and conducting fundamental oceanographic research. Numerical models are the most prevalent of the traditional approaches, which are often too complex and lack of generality. Recently, with the rise of AI, many data-driven methods are proposed. However, most of them take no consideration of natural physical laws that may cause issues of physical inconsistency among different variables. In this paper, we proposed PGTransNet, a novel physics-guided transformer network for 3D Ocean temperature and salinity forecasting. This model is based on Vision Transformer, and to enhance the performance we have three aspects of improvements. Firstly, we design a loss function that deliveries the physical relationship among temperature, salinity and density by fusing the Thermodynamic Equation. Secondly, to capture global and long-term dependencies effectively, we add the Pacific Decadal Oscillation (PDO) and North Pacific Gyre Oscillation (NPGO) in the embedding layer. Thirdly, we adopted the Laplacian sparse positional encodings to alleviate the artifacts caused by high-norm tokens. The former two are the core components to leverage the physical information. Finally, to comprehensively evaluate PGTransnet, we conduct rich experiments in metrics RMSE, Anomoly Correlation Coefficients, Bias and physical consistency. Our proposal demonstrates higher prediction accuracy with fast convergence, and the metrics and visualizations show that our model is insensitive to hyperparameter tuning, ensuring better generalization and adherence to physical consistency. Moreover, as observed from the spatial distribution of the anomaly correlation coefficient, the model exhibits higher forecasting accuracy for coastal and marginal sea regions. |
| format | Article |
| id | doaj-art-885c5c8386874a3f9d91f17601290480 |
| institution | Kabale University |
| issn | 2296-7745 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-885c5c8386874a3f9d91f176012904802025-01-24T11:48:59ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452024-11-011110.3389/fmars.2024.14777101477710PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical PacificSong Wu0Senliang Bao1Wei Dong2Senzhang Wang3Xiaojiang Zhang4Chengcheng Shao5Junxing Zhu6Xiaoyong Li7College of Computer Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha, ChinaCollege of Computer Science and Technology, National University of Defense Technology, Changsha, ChinaSchool of Computer Science and Engineering, Central South University, Changsha, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha, ChinaAccurately predicting the spatio-temporal evolution trends and long-term dynamics of three-dimensional ocean temperature and salinity plays a crucial role in monitoring climate system changes and conducting fundamental oceanographic research. Numerical models are the most prevalent of the traditional approaches, which are often too complex and lack of generality. Recently, with the rise of AI, many data-driven methods are proposed. However, most of them take no consideration of natural physical laws that may cause issues of physical inconsistency among different variables. In this paper, we proposed PGTransNet, a novel physics-guided transformer network for 3D Ocean temperature and salinity forecasting. This model is based on Vision Transformer, and to enhance the performance we have three aspects of improvements. Firstly, we design a loss function that deliveries the physical relationship among temperature, salinity and density by fusing the Thermodynamic Equation. Secondly, to capture global and long-term dependencies effectively, we add the Pacific Decadal Oscillation (PDO) and North Pacific Gyre Oscillation (NPGO) in the embedding layer. Thirdly, we adopted the Laplacian sparse positional encodings to alleviate the artifacts caused by high-norm tokens. The former two are the core components to leverage the physical information. Finally, to comprehensively evaluate PGTransnet, we conduct rich experiments in metrics RMSE, Anomoly Correlation Coefficients, Bias and physical consistency. Our proposal demonstrates higher prediction accuracy with fast convergence, and the metrics and visualizations show that our model is insensitive to hyperparameter tuning, ensuring better generalization and adherence to physical consistency. Moreover, as observed from the spatial distribution of the anomaly correlation coefficient, the model exhibits higher forecasting accuracy for coastal and marginal sea regions.https://www.frontiersin.org/articles/10.3389/fmars.2024.1477710/fullphysics-guided machine learningspatio-temporal data analysisocean temperature predictionocean salinity predictionViT |
| spellingShingle | Song Wu Senliang Bao Wei Dong Senzhang Wang Xiaojiang Zhang Chengcheng Shao Junxing Zhu Xiaoyong Li PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific Frontiers in Marine Science physics-guided machine learning spatio-temporal data analysis ocean temperature prediction ocean salinity prediction ViT |
| title | PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific |
| title_full | PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific |
| title_fullStr | PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific |
| title_full_unstemmed | PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific |
| title_short | PGTransNet: a physics-guided transformer network for 3D ocean temperature and salinity predicting in tropical Pacific |
| title_sort | pgtransnet a physics guided transformer network for 3d ocean temperature and salinity predicting in tropical pacific |
| topic | physics-guided machine learning spatio-temporal data analysis ocean temperature prediction ocean salinity prediction ViT |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2024.1477710/full |
| work_keys_str_mv | AT songwu pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific AT senliangbao pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific AT weidong pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific AT senzhangwang pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific AT xiaojiangzhang pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific AT chengchengshao pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific AT junxingzhu pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific AT xiaoyongli pgtransnetaphysicsguidedtransformernetworkfor3doceantemperatureandsalinitypredictingintropicalpacific |