| Prediction of seasonal sea surface temperature based on temperature and salinity of subsurface ocean using machine learning | |
Wei, Sentao1; Wang, CH(王澄海)1,2  ; Zhang, FM(张飞民)1; Yang, K(杨凯)1 | |
| 2024-02-06 | |
| Online publication date | 2024-02 |
| Source Publication | INTERNATIONAL JOURNAL OF CLIMATOLOGY Impact Factor & Quartile Of Published Year The Latest Impact Factor & Quartile |
| ISSN | 0899-8418 |
| EISSN | 1097-0088 |
| page numbers | 13 |
| Abstract | The sea surface temperature (SST) is not only a crucial external factor in the evolution of the atmosphere, but also a primary factor and premonition signal used in climate prediction. It is challenging to obtain a precise SST for generating accurate initial and boundary conditions in numerical models. This study employs a machine learning approach, that is, a convolutional neural network (CNN) algorithm, to predict SST on a seasonal scale. In particular, the subsurface ocean temperature (OT) and ocean salinity (OS) at depths of 5.02, 15.08, 25.16, 35.28, 45.45 and 76.55 m were used as training factors in developing a CNN prediction model. The results indicate that subsurface OT and OS can persist for 6 months or longer, with a maximum persistence of up to 12 months. Using the CNN prediction model, the SST can be reliably predicted 6 months in advance in most cases. The predicted SST has a mean bias of approximately 0-0.8 K on the globe. The bias is small (below 0.5 K) in the open ocean. The root mean square errors (RMSEs) of hindcasting for Interdecadal Pacific Oscillation, North Atlantic Oscillation (NAO) and Atlantic Multidecadal Oscillation indices are all less than 1.0 K. Specifically, the RMSE for El Nino prediction is less than 0.5 K. This study provides a viable method for establishing initial and boundary conditions for climate prediction. It is challenging to obtain a precise sea surface temperature (SST) for generating accurate initial and boundary conditions in numerical models. This study employs a machine learning approach, which is a convolutional neural network algorithm, to predict SST on a seasonal scale. image |
| Keyword | convolution neural network El Nino persistence of ocean temperature and ocean salinity sea surface temperature |
| Publisher | WILEY |
| DOI | 10.1002/joc.8384 |
| Indexed By | SCIE ; EI |
| Language | 英语 |
| WOS Research Area | Meteorology & Atmospheric Sciences |
| WOS Subject | Meteorology & Atmospheric Sciences |
| WOS ID | WOS:001156567800001 |
| EI Accession Number | 20240715532747 |
| EI Keywords | Surface temperature |
| EI Classification Number | 443.1 Atmospheric Properties ; 444.1 Surface Water ; 471.1 Oceanography, General ; 481.3 Geophysics ; 641.1 Thermodynamics ; 716.1 Information Theory and Signal Processing ; 723.4 Artificial Intelligence ; 922.2 Mathematical Statistics |
| Original Document Type | Article ; Early Access |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | https://ir.lzu.edu.cn/handle/262010/583618 |
| Collection | 大气科学学院 |
| Corresponding Author | Wang, Chenghai |
| Affiliation | 1.Lanzhou Univ, Coll Atmospher Sci, Res & Dev Ctr Earth Syst Model RDCM, Key Lab Climate Resource Dev & Disaster Prevent Ga, Lanzhou, Peoples R China; 2.Lanzhou Univ, Coll Atmospher Sci, Lanzhou 730000, Gansu, Peoples R China |
| First Author Affilication | College of Atmospheric Sciences |
| Corresponding Author Affilication | College of Atmospheric Sciences |
| First Signature Affilication | College of Atmospheric Sciences |
| Recommended Citation GB/T 7714 | Wei, Sentao,Wang, Chenghai,Zhang, Feimin,et al. Prediction of seasonal sea surface temperature based on temperature and salinity of subsurface ocean using machine learning[J]. INTERNATIONAL JOURNAL OF CLIMATOLOGY,2024. |
| APA | Wei, Sentao,Wang, Chenghai,Zhang, Feimin,&Yang, Kai.(2024).Prediction of seasonal sea surface temperature based on temperature and salinity of subsurface ocean using machine learning.INTERNATIONAL JOURNAL OF CLIMATOLOGY. |
| MLA | Wei, Sentao,et al."Prediction of seasonal sea surface temperature based on temperature and salinity of subsurface ocean using machine learning".INTERNATIONAL JOURNAL OF CLIMATOLOGY (2024). |
| Files in This Item: | There are no files associated with this item. | ||||
