Articles | Volume 25, issue 8
Hydrol. Earth Syst. Sci., 25, 4435–4453, 2021
https://doi.org/10.5194/hess-25-4435-2021
Hydrol. Earth Syst. Sci., 25, 4435–4453, 2021
https://doi.org/10.5194/hess-25-4435-2021

Research article 16 Aug 2021

Research article | 16 Aug 2021

Deep learning for automated river-level monitoring through river-camera images: an approach based on water segmentation and transfer learning

Remy Vandaele et al.

Related authors

Observation operators for assimilation of satellite observations in fluvial inundation forecasting
Elizabeth S. Cooper, Sarah L. Dance, Javier García-Pintado, Nancy K. Nichols, and Polly J. Smith
Hydrol. Earth Syst. Sci., 23, 2541–2559, https://doi.org/10.5194/hess-23-2541-2019,https://doi.org/10.5194/hess-23-2541-2019, 2019
Short summary
Technical note: Assessment of observation quality for data assimilation in flood models
Joanne A. Waller, Javier García-Pintado, David C. Mason, Sarah L. Dance, and Nancy K. Nichols
Hydrol. Earth Syst. Sci., 22, 3983–3992, https://doi.org/10.5194/hess-22-3983-2018,https://doi.org/10.5194/hess-22-3983-2018, 2018

Related subject area

Subject: Rivers and Lakes | Techniques and Approaches: Stochastic approaches
Do small and large floods have the same drivers of change? A regional attribution analysis in Europe
Miriam Bertola, Alberto Viglione, Sergiy Vorogushyn, David Lun, Bruno Merz, and Günter Blöschl
Hydrol. Earth Syst. Sci., 25, 1347–1364, https://doi.org/10.5194/hess-25-1347-2021,https://doi.org/10.5194/hess-25-1347-2021, 2021
Short summary
Flood trends in Europe: are changes in small and big floods different?
Miriam Bertola, Alberto Viglione, David Lun, Julia Hall, and Günter Blöschl
Hydrol. Earth Syst. Sci., 24, 1805–1822, https://doi.org/10.5194/hess-24-1805-2020,https://doi.org/10.5194/hess-24-1805-2020, 2020
Short summary
A large sample analysis of European rivers on seasonal river flow correlation and its physical drivers
Theano Iliopoulou, Cristina Aguilar, Berit Arheimer, María Bermúdez, Nejc Bezak, Andrea Ficchì, Demetris Koutsoyiannis, Juraj Parajka, María José Polo, Guillaume Thirel, and Alberto Montanari
Hydrol. Earth Syst. Sci., 23, 73–91, https://doi.org/10.5194/hess-23-73-2019,https://doi.org/10.5194/hess-23-73-2019, 2019
Short summary
Discharge hydrograph estimation at upstream-ungauged sections by coupling a Bayesian methodology and a 2-D GPU shallow water model
Alessia Ferrari, Marco D'Oria, Renato Vacondio, Alessandro Dal Palù, Paolo Mignosa, and Maria Giovanna Tanda
Hydrol. Earth Syst. Sci., 22, 5299–5316, https://doi.org/10.5194/hess-22-5299-2018,https://doi.org/10.5194/hess-22-5299-2018, 2018
Short summary
Large-scale hydrological model river storage and discharge correction using a satellite altimetry-based discharge product
Charlotte Marie Emery, Adrien Paris, Sylvain Biancamaria, Aaron Boone, Stéphane Calmant, Pierre-André Garambois, and Joecila Santos da Silva
Hydrol. Earth Syst. Sci., 22, 2135–2162, https://doi.org/10.5194/hess-22-2135-2018,https://doi.org/10.5194/hess-22-2135-2018, 2018
Short summary

Cited articles

Bargoti, S. and Underwood, J. P.: Image segmentation for fruit detection and yield estimation in apple orchards, J. Field Robot., 34, 1039–1060, https://doi.org/10.1002/rob.21699, 2017. a
Baruch, A.: An investigation into the role of crowdsourcing in generating information for flood risk management, PhD thesis, Loughborough University, Loughborough, 2018. a
Caesar, H., Uijlings, J., and Ferrari, V.: Coco-stuff: Thing and stuff classes in context, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1209–1218, https://doi.org/10.1109/CVPR.2018.00132, 2018. a, b
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A. L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs, IEEE T. Pattern Anal., 40, 834–848, https://doi.org/10.1109/TPAMI.2017.2699184, 2017. a, b, c
Civil Aviation Authority: Unmanned aircraft and drones, available at: https://www.caa.co.uk/Consumers/Unmanned-aircraft-and-drones/, last access: 16 November 2020. a
Download
Short summary
The acquisition of river-level data is a critical task for the understanding of flood events but is often complicated by the difficulty to install and maintain gauges able to provide such information. This study proposes applying deep learning techniques on river-camera images in order to automatically extract the corresponding water levels. This approach could allow for a new flexible way to observe flood events, especially at ungauged locations.