A deep learning method for bias correction of wind field in the South China Sea
To address the systematic bias in the Global Forecast System (GFS) wind field forecasts, we utilize deep learning techniques. The developed MU - Diffusion framework, based on a diffusion model and MultiUnet (a multitasking Unet model), establishes a nonlinear relationship between GFS and the fifth-g...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2024.1429057/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554575535898624 |
|---|---|
| author | Cong Pang Tao Song Tao Song Handan Sun Xin Li Danya Xu |
| author_facet | Cong Pang Tao Song Tao Song Handan Sun Xin Li Danya Xu |
| author_sort | Cong Pang |
| collection | DOAJ |
| description | To address the systematic bias in the Global Forecast System (GFS) wind field forecasts, we utilize deep learning techniques. The developed MU - Diffusion framework, based on a diffusion model and MultiUnet (a multitasking Unet model), establishes a nonlinear relationship between GFS and the fifth-generation EC atmospheric reanalysis (ERA5) data. Focusing on the South China Sea region, this method corrects both wind speed and direction simultaneously. Using 2022 GFS data, we achieved average enhancements of 42% in wind speed and 38.3% in wind direction compared to the initial GFS data. Tests in typhoon conditions also confirm the excellent performance of this architecture. |
| format | Article |
| id | doaj-art-a52f5f4add6c4acc845f1518bb554eb3 |
| institution | Kabale University |
| issn | 2296-7745 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-a52f5f4add6c4acc845f1518bb554eb32025-01-08T13:24:22ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-01-011110.3389/fmars.2024.14290571429057A deep learning method for bias correction of wind field in the South China SeaCong Pang0Tao Song1Tao Song2Handan Sun3Xin Li4Danya Xu5College of Computer Science and Technology, China University of Petroleum, Qingdao, Shandong, ChinaCollege of Computer Science and Technology, China University of Petroleum, Qingdao, Shandong, ChinaDepartment of Artificial Intelligence, Faculty of Computer Science, Polytechnical University of Madrid, Madrid, SpainCollege of Computer Science and Technology, China University of Petroleum, Qingdao, Shandong, ChinaCollege of Computer Science and Technology, China University of Petroleum, Qingdao, Shandong, ChinaGuangdong Laboratory of Marine Science and Engineering, Zhuhai, Guangdong, ChinaTo address the systematic bias in the Global Forecast System (GFS) wind field forecasts, we utilize deep learning techniques. The developed MU - Diffusion framework, based on a diffusion model and MultiUnet (a multitasking Unet model), establishes a nonlinear relationship between GFS and the fifth-generation EC atmospheric reanalysis (ERA5) data. Focusing on the South China Sea region, this method corrects both wind speed and direction simultaneously. Using 2022 GFS data, we achieved average enhancements of 42% in wind speed and 38.3% in wind direction compared to the initial GFS data. Tests in typhoon conditions also confirm the excellent performance of this architecture.https://www.frontiersin.org/articles/10.3389/fmars.2024.1429057/fulldeep learningmu-diffusionSouth China Seabias correctionwind fieldGFS |
| spellingShingle | Cong Pang Tao Song Tao Song Handan Sun Xin Li Danya Xu A deep learning method for bias correction of wind field in the South China Sea Frontiers in Marine Science deep learning mu-diffusion South China Sea bias correction wind field GFS |
| title | A deep learning method for bias correction of wind field in the South China Sea |
| title_full | A deep learning method for bias correction of wind field in the South China Sea |
| title_fullStr | A deep learning method for bias correction of wind field in the South China Sea |
| title_full_unstemmed | A deep learning method for bias correction of wind field in the South China Sea |
| title_short | A deep learning method for bias correction of wind field in the South China Sea |
| title_sort | deep learning method for bias correction of wind field in the south china sea |
| topic | deep learning mu-diffusion South China Sea bias correction wind field GFS |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2024.1429057/full |
| work_keys_str_mv | AT congpang adeeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT taosong adeeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT taosong adeeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT handansun adeeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT xinli adeeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT danyaxu adeeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT congpang deeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT taosong deeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT taosong deeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT handansun deeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT xinli deeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea AT danyaxu deeplearningmethodforbiascorrectionofwindfieldinthesouthchinasea |