Skip to main content

Research Repository

Advanced Search

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

Ling, Feng; Boyd, Doreen; Ge, Yong; Foody, Giles M.; Li, Xiaodong; Wang, Lihui; Zhang, Yihang; Shi, Lingfei; Shang, Cheng; Li, Xinyan; Du, Yun

Measuring River Wetted Width from Remotely Sensed Imagery at the Subpixel Scale with a Deep Convolutional Neural Network Thumbnail


Authors

Feng Ling

DOREEN BOYD doreen.boyd@nottingham.ac.uk
Professor of Earth Observation

Yong Ge

GILES FOODY giles.foody@nottingham.ac.uk
Professor of Geographical Information

Xiaodong Li

Lihui Wang

Yihang Zhang

Lingfei Shi

Cheng Shang

Xinyan Li

Yun Du



Abstract

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 sub‐pixel 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 super‐resolution mapping (SRM). In the SRM analysis, a deep convolutional neural network (CNN) 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 CNN based SRM model can effectively estimate sub‐pixel 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.

Citation

Ling, F., Boyd, D., Ge, Y., Foody, G. M., Li, X., Wang, L., …Du, Y. (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. https://doi.org/10.1029/2018wr024136

Journal Article Type Article
Acceptance Date Jun 6, 2019
Online Publication Date Jun 20, 2019
Publication Date Jul 10, 2019
Deposit Date Jun 25, 2019
Publicly Available Date Aug 16, 2019
Journal Water Resources Research
Print ISSN 0043-1397
Electronic ISSN 1944-7973
Publisher American Geophysical Union
Peer Reviewed Peer Reviewed
Volume 55
Issue 7
Pages 5631-5649
DOI https://doi.org/10.1029/2018wr024136
Keywords Water Science and Technology
Public URL https://nottingham-repository.worktribe.com/output/2227443
Publisher URL https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2018WR024136
Contract Date Jun 25, 2019

Files

Measuring River Wetted Width From Remotely Sensed Imagery at the Subpixel Scale With a Deep Convolutional Neural Network (3.5 Mb)
PDF





You might also like



Downloadable Citations