Oceanic internal wave amplitude retrieval from satellite images based on a data-driven transfer learning model

doi:10.1016/j.rse.2022.112940

CORC > 海洋研究所 > 中国科学院海洋研究所 > 海洋环流与波动重点实验室

	Oceanic internal wave amplitude retrieval from satellite images based on a data-driven transfer learning model
	Zhang, Xudong 7,8; Wang, Haoyu 7,8; Wang, Shuo 6; Liu, Yanliang 4,5; Yu, Weidong 2,3; Wang, Jing 1; Xu, Qing 1; Li, Xiaofeng 7,8
刊名	REMOTE SENSING OF ENVIRONMENT
	2022-04-01
卷号	272 页码:15
关键词	Internal wave Amplitude Transfer learning Remote sensing In-situ measurement Laboratory experiment
ISSN号	0034-4257
DOI	10.1016/j.rse.2022.112940
通讯作者	Li, Xiaofeng(lixf@qdio.ac.cn)
英文摘要	Internal waves (IW) are characterized by a large-amplitude, long-wave crest, and long-propagation distance. They are widespread in the global ocean. Amplitude is an essential IW parameter and is difficult to derive from the IW surface signatures in satellite images. A laboratory experiment and combined satellite/in-situ measurements were carried out to build two internal wave datasets (888 pairs of lab data and 121 pairs of synchronous in-situ data and satellite images). To efficiently use the lab data, we implemented a transfer learning model to retrieve IW amplitude from satellite images. The model is a purely data-driven model pre-trained with lab data and re-trained with satellite/in-situ data. A short connection was incorporated into the transfer learning framework to reduce information loss. Bias correction was adopted to improve the model performance. After the correction, the root mean square error (RMSE) of the estimated IW amplitude decreased from 12.09 m (17.84 m) to 9.59 m (11.59 m), the mean relative error decreased from 21% (27%) to 18% (16%), and the correlation coefficients improved from 0.81 (0.72) to 0.89 (0.90) on the test (training) dataset. For IWs with amplitude exceeding 100 m, the model can be expected to get an absolute error of 10 m. The mean relative error decreased with the increase in IW amplitudes. Comparisons with other algorithms demonstrate that the proposed model is efficient for IW studies. We applied the model to 156 satellite images containing IW signatures in the Andaman Sea, finding that large-amplitude IWs were mainly located at the water depth between 200 m and 1000 m on the continental slope. When considering one-pixel input errors for the peak-to-peak (PP) distance, the model shows large tolerance with the errors. Compared with the KdV equation-based method, the developed model was more accurate.
资助项目	CAS (Chinese Academy of Sciences) Program[Y9KY04101L] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB42000000] ; Key Project of Center for Ocean Mega-Science[COMS2019R02] ; National Natural Science Foundation for Young Scientists of China[41906157] ; National Natural Science Foundation of China[U2006211] ; National Natural Science Foundation of China[42090044] ; National Natural Science Foundation of China[41776183] ; Major scientific and technological innovation projects in Shandong Province[2019JZZY010102] ; UK Royal Society International Exchange Project[IES\R1\211036]
WOS研究方向	Environmental Sciences & Ecology ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	ELSEVIER SCIENCE INC
WOS记录号	WOS:000759731300003
内容类型	期刊论文
源URL	[http://ir.qdio.ac.cn/handle/337002/178140]
专题	海洋研究所_海洋环流与波动重点实验室
通讯作者	Li, Xiaofeng
作者单位	1.Ocean Univ China, Facult Informat Sci & Engn, Qingdao, Peoples R China 2.Sun Yat Sen Univ, Minist Educ, Key Lab Trop Atmosphere Ocean Syst, Guangzhou, Peoples R China 3.Sun Yat Sen Univ, Sch Atmospher Sci, Zhuhai, Peoples R China 4.Pilot Natl Lab Marine Sci & Technol Qingdao, Lab Reg Oceanog & Numer Modeling, Qingdao, Peoples R China 5.Minist Nat Resources, Inst Oceanog 1, Ctr Ocean & Climate Res, Qingdao, Peoples R China 6.Univ Birmingham, Sch Comp Sci, Birmingham, W Midlands, England 7.Chinese Acad Sci, Ctr Ocean Megasci, 7 Nanhai Rd, Qingdao 266071, Peoples R China 8.Chinese Acad Sci, Inst Oceanol, CAS Key Lab Ocean Circulat & Waves, 7 Nanhai Rd, Qingdao 266071, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Xudong,Wang, Haoyu,Wang, Shuo,et al. Oceanic internal wave amplitude retrieval from satellite images based on a data-driven transfer learning model[J]. REMOTE SENSING OF ENVIRONMENT,2022,272:15.
APA	Zhang, Xudong.,Wang, Haoyu.,Wang, Shuo.,Liu, Yanliang.,Yu, Weidong.,...&Li, Xiaofeng.(2022).Oceanic internal wave amplitude retrieval from satellite images based on a data-driven transfer learning model.REMOTE SENSING OF ENVIRONMENT,272,15.
MLA	Zhang, Xudong,et al."Oceanic internal wave amplitude retrieval from satellite images based on a data-driven transfer learning model".REMOTE SENSING OF ENVIRONMENT 272(2022):15.