Articles | Volume 28, issue 17
https://doi.org/10.5194/hess-28-4085-2024
https://doi.org/10.5194/hess-28-4085-2024
Technical note
 | 
10 Sep 2024
Technical note |  | 10 Sep 2024

Technical note: Monitoring discharge of mountain streams by retrieving image features with deep learning

Chenqi Fang, Genyu Yuan, Ziying Zheng, Qirui Zhong, and Kai Duan

Related authors

Satellite-observed surging dynamics of North Kunchhang Glacier I in the Eastern Karakoram
Fanyu Zhao, Di Long, Chenqi Fang, Yiming Wang, and Xingwu Duan
EGUsphere, https://doi.org/10.5194/egusphere-2025-652,https://doi.org/10.5194/egusphere-2025-652, 2025
Short summary

Cited articles

Abdullah-Al-Wadud, M., Kabir, M. H., Dewan, M. A. A., and Chae, O.: A Dynamic Histogram Equalization for Image Contrast Enhancement, IEEE T. Consum. Electr., 53, 593–600, https://doi.org/10.1109/TCE.2007.381734, 2007. 
Ansari, S., Rennie, C., Jamieson, E., Seidou, O., and Clark, S.: RivQNet: Deep Learning Based River Discharge Estimation Using Close-Range Water Surface Imagery, Water Resour. Res., 59, e2021WR031841, https://doi.org/10.1029/2021WR031841, 2023. 
Aslam, J. A., Popa, R. A., and Rivest, R. L.: On estimating the size and confidence of a statistical audit, Proceedings of the USENIX Workshop on Accurate Electronic Voting Technology, Boston, MA, USA, 6–10 August 2007, 2007. 
Breiman, L.: Random Forests, Mach. Learn., 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001. 
Burges, C. J. C.: A Tutorial on Support Vector Machines for Pattern Recognition, Data Min. Knowl. Disc., 2, 121–167, https://doi.org/10.1023/A:1009715923555, 1998. 
Download
Short summary
Measuring discharge at steep, rocky mountain streams is challenging due to the difficulties in identifying cross-section characteristics and establishing stable stage–discharge relationships. We present a novel method using only a low-cost commercial camera and deep learning algorithms. Our study shows that deep convolutional neural networks can automatically recognize and retrieve complex stream features embedded in RGB images to achieve continuous discharge monitoring.
Share