Measuring River Wetted Width From Remotely Sensed Imagery at the Subpixel Scale With a Deep Convolutional Neural Network

doi:10.1029/2018WR024136

	Measuring River Wetted Width From Remotely Sensed Imagery at the Subpixel Scale With a Deep Convolutional Neural Network
	Ling, Feng 2,3; Boyd, Doreen 1; Ge, Yong 4; Foody, Giles M.1; Li, Xiaodong 1,2; Wang, Lihui 2; Zhang, Yihang 2; Shi, Lingfei 2; Shang, Cheng 2; Li, Xinyan 2
刊名	WATER RESOURCES RESEARCH
	2019-07-01
卷号	55 期号:7 页码:5631-5649
ISSN号	0043-1397
DOI	10.1029/2018WR024136
通讯作者	Ling, Feng(lingf@whigg.ac.cn)
英文摘要	River wetted width (RWW) is an important variable in the study of river hydrological and biogeochemical processes. Presently, RWW is often measured from remotely sensed imagery, and the accuracy of RWW estimation is typically low when coarse spatial resolution imagery is used because river boundaries often run through pixels that represent a region that is a mixture of water and land. Thus, when conventional hard classification methods are used in the estimation of RWW, the mixed pixel problem can become a large source of error. To address this problem, this paper proposes a novel approach to measure RWW at the subpixel scale. Spectral unmixing is first applied to the imagery to obtain a water fraction image that indicates the proportional coverage of water in image pixels. A fine spatial resolution river map from which RWW may be estimated is then produced from the water fraction image by superresolution mapping (SRM). In the SRM analysis, a deep convolutional neural network is used to eliminate the negative effects of water fraction errors and reconstruct the geographical distribution of water. The proposed approach is assessed in two experiments, with the results demonstrating that the convolutional neural network-based SRM model can effectively estimate subpixel scale details of rivers and that the accuracy of RWW estimation is substantially higher than that obtained from the use of a conventional hard image classification. The improvement shows that the proposed method has great potential to derive more accurate RWW values from remotely sensed imagery.
资助项目	Strategic Priority Research Program of Chinese Academy of Sciences[XDA2003030201] ; National Science Fund for Distinguished Young Scholars of China[41725006] ; National Natural Science Foundation of China[51809250] ; Youth Innovation Promotion Association CAS[2017384]
WOS关键词	ESTIMATING DISCHARGE ; MIXTURE ANALYSIS ; CARBON-DIOXIDE ; LAND ; STREAMS ; WATERLINE ; MODEL
WOS研究方向	Environmental Sciences & Ecology ; Marine & Freshwater Biology ; Water Resources
语种	英语
出版者	AMER GEOPHYSICAL UNION
WOS记录号	WOS:000481444700026
资助机构	Strategic Priority Research Program of Chinese Academy of Sciences ; National Science Fund for Distinguished Young Scholars of China ; National Natural Science Foundation of China ; Youth Innovation Promotion Association CAS
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/69017]
专题	中国科学院地理科学与资源研究所
通讯作者	Ling, Feng
作者单位	1.Univ Nottingham, Sch Geog, Nottingham, England 2.Chinese Acad Sci, Inst Geodesy & Geophys, Key Lab Environm & Disaster Monitoring & Evaluat, Wuhan, Hubei, Peoples R China 3.Chinese Acad Sci, Sino Africa Joint Res Ctr, Wuhan, Hubei, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ling, Feng,Boyd, Doreen,Ge, Yong,et al. Measuring River Wetted Width From Remotely Sensed Imagery at the Subpixel Scale With a Deep Convolutional Neural Network[J]. WATER RESOURCES RESEARCH,2019,55(7):5631-5649.
APA	Ling, Feng.,Boyd, Doreen.,Ge, Yong.,Foody, Giles M..,Li, Xiaodong.,...&Du, Yun.(2019).Measuring River Wetted Width From Remotely Sensed Imagery at the Subpixel Scale With a Deep Convolutional Neural Network.WATER RESOURCES RESEARCH,55(7),5631-5649.
MLA	Ling, Feng,et al."Measuring River Wetted Width From Remotely Sensed Imagery at the Subpixel Scale With a Deep Convolutional Neural Network".WATER RESOURCES RESEARCH 55.7(2019):5631-5649.