Articles | Volume 28, issue 17
https://doi.org/10.5194/hess-28-4085-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-28-4085-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Technical note
| 
10 Sep 2024
Technical note |
| 10 Sep 2024
| 10 Sep 2024
Technical note: Monitoring discharge of mountain streams by retrieving image features with deep learning
Chenqi Fang
School of Civil Engineering, Sun Yat-sen University, Guangzhou, China
Genyu Yuan
School of Civil Engineering, Sun Yat-sen University, Guangzhou, China
Ziying Zheng
School of Civil Engineering, Sun Yat-sen University, Guangzhou, China
Qirui Zhong
School of Civil Engineering, Sun Yat-sen University, Guangzhou, China
Kai Duan
CORRESPONDING AUTHOR
School of Civil Engineering, Sun Yat-sen University, Guangzhou, China
Related authors
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
Short summary
The heterogeneous surge behaviors in Karakoram reveal critical knowledge gaps in the underlying mechanism, urging detailed investigations. We integrate multisource remote sensing (satellite altimetry, DEMs, optical/SAR imagery) to holistically characterize surge phases of a Karakoram glacier, quantifying flow velocity, surface elevation, terminus position, and lake level variations. This integrated approach underscores the value of multi-sensor synergies in deciphering complex surge mechanisms.
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
Short summary
The heterogeneous surge behaviors in Karakoram reveal critical knowledge gaps in the underlying mechanism, urging detailed investigations. We integrate multisource remote sensing (satellite altimetry, DEMs, optical/SAR imagery) to holistically characterize surge phases of a Karakoram glacier, quantifying flow velocity, surface elevation, terminus position, and lake level variations. This integrated approach underscores the value of multi-sensor synergies in deciphering complex surge mechanisms.
Hailong Wang, Kai Duan, Bingjun Liu, and Xiaohong Chen
Hydrol. Earth Syst. Sci., 25, 4741–4758, https://doi.org/10.5194/hess-25-4741-2021, https://doi.org/10.5194/hess-25-4741-2021, 2021
Short summary
Short summary
Using remote sensing and reanalysis data, we examined the relationships between vegetation development and water resource availability in a humid subtropical basin. We found overall increases in total water storage and surface greenness and vegetation production, and the changes were particularly profound in cropland-dominated regions. Correlation analysis implies water availability leads the variations in greenness and production, and irrigation may improve production during dry periods.
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.
Canziani, A., Paszke, A., and Culurciello, E.: An Analysis of Deep Neural Network Models for Practical Applications, arXiv [preprint], https://doi.org/10.48550/arXiv.1605.07678, 2016.
Carlisle, D., Grantham, T. E., Eng, K., and Wolock, D. M.: Biological relevance of streamflow metrics: Regional and national perspectives, Freshw. Sci., 36, 927–940, https://doi.org/10.1086/694913, 2017.
Chang, F., Hong, W., Zhang, T., Jing, J., and Liu, X.: Research on Wavelet Denoising for Pulse Signal Based on Improved Wavelet Thresholding, 2010 First International Conference on Pervasive Computing, Signal Processing and Applications, Harbin, China, 17–19 September 2010, 564–567, https://doi.org/10.1109/PCSPA.2010.142, 2010.
Chapman, K. W., Gilmore, T. E., Chapman, C. D., Mehrubeoglu, M., and Mittelstet, A. R.: Camera-based Water Stage and Discharge Prediction with Machine Learning, Hydrol. Earth Syst. Sci. Discuss. [preprint], https://doi.org/10.5194/hess-2020-575, 2020.
Cheng, H. D. and Shi, X. J.: A simple and effective histogram equalization approach to image enhancement, Digit. Signal Process., 14, 158–170, https://doi.org/10.1016/j.dsp.2003.07.002, 2004.
Clarke, R. T.: Uncertainty in the estimation of mean annual flood due to rating-curve indefinition, J. Hydrol., 222, 185–190, https://doi.org/10.1016/S0022-1694(99)00097-9, 1999.
Cortes, C. and Vapnik, V.: Support-vector networks, Mach. Learn., 20, 273–297, https://doi.org/10.1007/bf00994018, 1995.
Council, N. R.: Assessing the national streamflow information program, National Academies Press, 176 pp., https://doi.org/10.17226/10967, 2004.
Czuba, J. A., Foufoula-Georgiou, E., Gran, K. B., Belmont, P., and Wilcock, P. R.: Interplay between spatially explicit sediment sourcing, hierarchical river-network structure, and in-channel bed material sediment transport and storage dynamics, J. Geophys. Res.-Earth, 122, 1090–1120, https://doi.org/10.1002/2016jf003965, 2017.
Davids, J. C., Rutten, M. M., Pandey, A., Devkota, N., van Oyen, W. D., Prajapati, R., and van de Giesen, N.: Citizen science flow – an assessment of simple streamflow measurement methods, Hydrol. Earth Syst. Sci., 23, 1045–1065, https://doi.org/10.5194/hess-23-1045-2019, 2019.
Deweber, J. T., Tsang, Y. P., Krueger, D. M., Whittier, J. B., Wagner, T., Infante, D. M., and Whelan, G.: Importance of Understanding Landscape Biases in USGS Gage Locations: Implications and Solutions for Managers, Fisheries, 39, 155–163, https://doi.org/10.1080/03632415.2014.891503, 2014.
Finlayson, G. D., Hordley, S. D., and Drew, M. S.: Removing Shadows from Images, Computer Vision – ECCV 2002, 28–31 May 2002, 823–836, https://doi.org/10.1007/3-540-47979-1_55, 2002.
Fujita, I., Watanabe, H., and Tsubaki, R.: Development of a non-intrusive and efficient flow monitoring technique: The space-time image velocimetry (STIV), International Journal of River Basin Management, 5, 105–114, https://doi.org/10.1080/15715124.2007.9635310, 2007.
Fujita, I., Muste, M., and Kruger, A.: Large-scale particle image velocimetry for flow analysis in hydraulic engineering applications, J. Hydraul. Res., 36, 397–414, https://doi.org/10.1080/00221689809498626, 2010.
Gershon, R., Jepson, A. D., and Tsotsos, J. K.: Ambient illumination and the determination of material changes, J. Opt. Soc. Am. A, 3, 1700–1707, https://doi.org/10.1364/josaa.3.001700, 1986.
Gleason, C. J. and Smith, L. C.: Toward global mapping of river discharge using satellite images and at-many-stations hydraulic geometry, P. Natl. Acad. Sci. USA, 111, 4788–4791, https://doi.org/10.1073/pnas.1317606111, 2014.
Hanczar, B., Hua, J., Sima, C., Weinstein, J., Bittner, M., and Dougherty, E. R.: Small-sample precision of ROC-related estimates, Bioinformatics, 26, 822–830, https://doi.org/10.1093/bioinformatics/btq037, 2010.
Hannah, D. M., Demuth, S., van Lanen, H. A. J., Looser, U., Prudhomme, C., Rees, G., Stahl, K., and Tallaksen, L. M.: Large-scale river flow archives: importance, current status and future needs, Hydrol. Process., 25, 1191–1200, https://doi.org/10.1002/hyp.7794, 2011.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, 770–778, https://doi.org/10.1109/cvpr.2016.90, 2016.
Heaton, J.: Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning: The MIT Press, Genetic Program. Evol. M., 19, 305–307, https://doi.org/10.1007/s10710-017-9314-z, 2018.
Herzog, A., Stahl, K., Blauhut, V., and Weiler, M.: Measuring zero water level in stream reaches: A comparison of an image-based versus a conventional method, Hydrol. Process., 36, e14234, https://doi.org/10.1002/hyp.14658, 2022.
Jiang, P. T., Zhang, C. B., Hou, Q., Cheng, M. M., and Wei, Y.: LayerCAM: Exploring Hierarchical Class Activation Maps for Localization, IEEE T. Image Process., 30, 5875–5888, https://doi.org/10.1109/TIP.2021.3089943, 2021.
Karvonen, J.: Virtual radar ice buoys – a method for measuring fine-scale sea ice drift, The Cryosphere, 10, 29–42, https://doi.org/10.5194/tc-10-29-2016, 2016.
Kasuga, K., Hachiya, H., and Kinosita, T.: Quantitative Estimation of the Ultrasound Transmission Characteristics for River Flow Measurement during a Flood, Jpn. J. Appl. Phys., 42, 3212–3215, https://doi.org/10.1143/jjap.42.3212, 2003.
Keskar, N., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P.: On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima, arXiv [preprint], https://doi.org/10.48550/arXiv.1609.04836, 2016.
Kim, W., Roh, S.-H., Moon, Y., and Jung, S.: Evaluation of Rededge-M Camera for Water Color Observation after Image Preprocessing, Journal of the Korean Society of Surveying Geodesy Photogrammetry and Cartography, 37, 167–175, https://doi.org/10.7848/ksgpc.2019.37.3.167, 2019.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: ImageNet classification with deep convolutional neural networks, Commun. ACM, 60, 84–90, https://doi.org/10.1145/3065386, 2017.
Le Coz, J., Camenen, B., Peyrard, X., and Dramais, G.: Uncertainty in open-channel discharges measured with the velocity–area method, Flow Meas. Instrumentation, 26, 18-29, https://doi.org/10.1016/j.flowmeasinst.2012.05.001, 2012.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
Leduc, P., Ashmore, P., and Sjogren, D.: Technical note: Stage and water width measurement of a mountain stream using a simple time-lapse camera, Hydrol. Earth Syst. Sci., 22, 1–11, https://doi.org/10.5194/hess-22-1-2018, 2018.
Li, W., Liao, Q., and Ran, Q.: Stereo-imaging LSPIV (SI-LSPIV) for 3D water surface reconstruction and discharge measurement in mountain river flows, J. Hydrol., 578, 124099, https://doi.org/10.1016/j.jhydrol.2019.124099, 2019.
Matykiewicz, P. and Pestian, J.: Effect of small sample size on text categorization with support vector machines, BioNLP: Proceedings of the 2012 Workshop on Biomedical Natural Language Processing, Montreal, Canada, 8 June 2012, 193–201, 2012.
McMillan, H., Freer, J., Pappenberger, F., Krueger, T., and Clark, M.: Impacts of uncertain river flow data on rainfall-runoff model calibration and discharge predictions, Hydrol. Process., 24, 1270–1284, https://doi.org/10.1002/hyp.7587, 2010.
Noto, S., Tauro, F., Petroselli, A., Apollonio, C., Botter, G., and Grimaldi, S.: Low-cost stage-camera system for continuous water-level monitoring in ephemeral streams, Hydrolog. Sci. J., 67, 1439–1448, https://doi.org/10.1080/02626667.2022.2079415, 2022.
Panda, B., Herbach, J., Basu, S., and Bayardo, R.: PLANET: Massively parallel learning of tree ensembles with MapReduce, Proc. VLDB Endow., 2, 1426–1437, https://doi.org/10.14778/1687553.1687569, 2009.
Royem, A. A., Mui, C. K., Fuka, D. R., and Walter, M. T.: Technical Note: Proposing a Low-Tech, Affordable, Accurate Stream Stage Monitoring System, T. ASABE, 55, 2237–2242, https://doi.org/10.13031/2013.42512, 2012.
Sauvola, J. and Pietikäinen, M.: Adaptive document image binarization, Pattern Recogn., 33, 225–236, https://doi.org/10.1016/s0031-3203(99)00055-2, 2000.
Shi, W., Jiang, F., Liu, S., and Zhao, D.: Image Compressed Sensing using Convolutional Neural Network, IEEE T. Image Process., 29, 375–388, https://doi.org/10.1109/TIP.2019.2928136, 2019.
Tauro, F., Grimaldi, S., and Porfiri, M.: Unraveling flow patterns through nonlinear manifold learning, PLoS One, 9, e91131, https://doi.org/10.1371/journal.pone.0091131, 2014.
Tauro, F., Piscopia, R., and Grimaldi, S.: Streamflow Observations From Cameras: Large-Scale Particle Image Velocimetry or Particle Tracking Velocimetry?, Water Resour. Res., 53, 10374–10394, https://doi.org/10.1002/2017wr020848, 2017.
Tauro, F., Tosi, F., Mattoccia, S., Toth, E., Piscopia, R., and Grimaldi, S.: Optical Tracking Velocimetry (OTV): Leveraging Optical Flow and Trajectory-Based Filtering for Surface Streamflow Observations, Remote Sensing, 10, 2010, https://doi.org/10.3390/rs10122010, 2018.
Tin Kam, H.: Random decision forests, Proceedings of 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada, 14–16 August 1995, 271, 278–282 https://doi.org/10.1109/ICDAR.1995.598994, 1995.
Tsubaki, R.: On the Texture Angle Detection Used in Space-Time Image Velocimetry (STIV), Water Resour. Res., 53, 10908–10914, https://doi.org/10.1002/2017wr021913, 2017.
Wang, R., Chaudhari, P., and Davatzikos, C.: Bias in machine learning models can be significantly mitigated by careful training: Evidence from neuroimaging studies, P. Natl. Acad. Sci. USA, 120, e2211613120, https://doi.org/10.1073/pnas.2211613120, 2023.
Yorke, T. H. and Oberg, K. A.: Measuring river velocity and discharge with acoustic Doppler profilers, Flow Meas. Instrum., 13, 191–195, https://doi.org/10.1016/s0955-5986(02)00051-1, 2002.
Young, D. S., Hart, J. K., and Martinez, K.: Image analysis techniques to estimate river discharge using time-lapse cameras in remote locations, Comput. Geosci., 76, 1–10, https://doi.org/10.1016/j.cageo.2014.11.008, 2015.
Zhang, D.: Fundamentals of Image Data Mining, Analysis, Features, Classification and Retrieval, Springer, 7, 35–44, https://doi.org/10.1007/978-3-030-17989-2, 2019.
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.
Measuring discharge at steep, rocky mountain streams is challenging due to the difficulties in...
