Subsurface Temperature Estimation from Sea Surface Data Using Neural Network Models in the Western Pacific Ocean

doi:10.3390/math9080852

CORC > 海洋研究所 > 中国科学院海洋研究所

	Subsurface Temperature Estimation from Sea Surface Data Using Neural Network Models in the Western Pacific Ocean
	Wang, Haoyu 2,3; Song, Tingqiang 3; Zhu, Shanliang 1,2; Yang, Shuguo 1,2; Feng, Liqiang 4,5
刊名	MATHEMATICS
	2021-04-01
卷号	9 期号:8 页码:14
关键词	ocean subsurface temperature multisource sea surface data neural network model western Pacific Ocean
DOI	10.3390/math9080852
通讯作者	Zhu, Shanliang(zhushanliang@qust.edu.cn) ; Feng, Liqiang(Fenglq@qdio.ac.cn)
英文摘要	Estimating the ocean subsurface thermal structure (OSTS) based on multisource sea surface data in the western Pacific Ocean is of great significance for studying ocean dynamics and El Nino phenomenon, but it is challenging to accurately estimate the OSTS from sea surface parameters in the area. This paper proposed an improved neural network model to estimate the OSTS from 0-2000 m from multisource sea surface data including sea surface temperature (SST), sea surface salinity (SSS), sea surface height (SSH), and sea surface wind (SSW). In the model experiment, the rasterized monthly average data from 2005-2015 and 2016 were selected as the training and testing set, respectively. The results showed that the sea surface parameters selected in the paper had a positive effect on the estimation process, and the average RMSE value of the ocean subsurface temperature (OST) estimated by the proposed model was 0.55 degrees C. Moreover, there were pronounced seasonal variation signals in the upper layers (the upper 200 m), however, this signal gradually diminished with increasing depth. Compared with known estimation models such as the random forest (RF), the multiple linear regression (MLR), and the extreme gradient boosting (XGBoost), the proposed model outperformed these models under the data conditions of the paper. This research can provide an advanced artificial intelligence technique for estimating subsurface thermohaline structure in major sea areas.
资助项目	Open Fund of the Key Laboratory of Ocean Circulation and Waves, Chinese Academy of Sciences[KLOCW2003] ; Special Projects for Informatization of the Chinese Academy of Sciences[XXH13506-105]
WOS研究方向	Mathematics
语种	英语
出版者	MDPI
WOS记录号	WOS:000644540300001
内容类型	期刊论文
源URL	[http://ir.qdio.ac.cn/handle/337002/170877]
专题	中国科学院海洋研究所
通讯作者	Zhu, Shanliang; Feng, Liqiang
作者单位	1.Qingdao Univ Sci & Technol, Sch Math & Phys, Qingdao 266061, Peoples R China 2.Qingdao Univ Sci & Technol, Res Inst Math & Interdisciplinary Sci, Qingdao 266061, Peoples R China 3.Qingdao Univ Sci & Technol, Coll Informat Sci & Technol, Qingdao 266061, Peoples R China 4.Chinese Acad Sci, Inst Oceanol, Marine Sci Data Ctr, Qingdao 266071, Peoples R China 5.Chinese Acad Sci, Ctr Ocean Mega Sci, Qingdao 266071, Peoples R China
推荐引用方式 GB/T 7714	Wang, Haoyu,Song, Tingqiang,Zhu, Shanliang,et al. Subsurface Temperature Estimation from Sea Surface Data Using Neural Network Models in the Western Pacific Ocean[J]. MATHEMATICS,2021,9(8):14.
APA	Wang, Haoyu,Song, Tingqiang,Zhu, Shanliang,Yang, Shuguo,&Feng, Liqiang.(2021).Subsurface Temperature Estimation from Sea Surface Data Using Neural Network Models in the Western Pacific Ocean.MATHEMATICS,9(8),14.
MLA	Wang, Haoyu,et al."Subsurface Temperature Estimation from Sea Surface Data Using Neural Network Models in the Western Pacific Ocean".MATHEMATICS 9.8(2021):14.