Articles | Volume 23, issue 11
https://doi.org/10.5194/hess-23-4621-2019
© Author(s) 2019. 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-23-4621-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
15 Nov 2019
Research article |
| 15 Nov 2019
| 15 Nov 2019
Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network
Matthew Moy de Vitry
CORRESPONDING AUTHOR
Department of Urban Water Management, Eawag – Swiss Federal Institute of Aquatic Science and Technology, 8600 Dübendorf, Switzerland
Institute of Environmental Engineering, ETH Zurich, 8093 Zürich, Switzerland
Simon Kramer
Institute of Environmental Engineering, ETH Zurich, 8093 Zürich, Switzerland
Jan Dirk Wegner
EcoVision Lab, Photogrammetry and Remote Sensing group, ETH Zurich,
8093 Zürich, Switzerland
João P. Leitão
Department of Urban Water Management, Eawag – Swiss Federal Institute of Aquatic Science and Technology, 8600 Dübendorf, Switzerland
Related authors
P. Chaudhary, S. D’Aronco, M. Moy de Vitry, J. P. Leitão, and J. D. Wegner
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2-W5, 5–12, https://doi.org/10.5194/isprs-annals-IV-2-W5-5-2019, https://doi.org/10.5194/isprs-annals-IV-2-W5-5-2019, 2019
Matthew Moy de Vitry, Simon Dicht, and João P. Leitão
Earth Syst. Sci. Data, 9, 657–666, https://doi.org/10.5194/essd-9-657-2017, https://doi.org/10.5194/essd-9-657-2017, 2017
Short summary
Short summary
Pluvial flash floods are a growing hazard in urban areas but the lack of appropriate data collection methods hinders the improvement of flood risk mapping and early warning systems. In the floodX project, 22 controlled urban flash floods were generated in a flood response training facility and monitored with state-of-the-art sensors complemented with standard surveillance cameras. The data can be used to explore vision-based monitoring concepts and flood model calibration strategies.
João P. Leitão, Matthew Moy de Vitry, Andreas Scheidegger, and Jörg Rieckermann
Hydrol. Earth Syst. Sci., 20, 1637–1653, https://doi.org/10.5194/hess-20-1637-2016, https://doi.org/10.5194/hess-20-1637-2016, 2016
Short summary
Short summary
Precise and detailed DEMs are essential to accurately predict overland flow in urban areas. In this this study we evaluated whether DEMs generated from UAV imagery are suitable for urban drainage overland flow modelling. Specifically, 14 UAV flights were conducted to assess the influence of four different flight parameters on the quality of generated DEMs. In addition, we compared the best quality UAV DEM to a conventional lidar-based DEM; the two DEMs are of comparable quality.
Tabea Cache, Milton Salvador Gomez, Tom Beucler, Jovan Blagojevic, João Paulo Leitao, and Nadav Peleg
Hydrol. Earth Syst. Sci., 28, 5443–5458, https://doi.org/10.5194/hess-28-5443-2024, https://doi.org/10.5194/hess-28-5443-2024, 2024
Short summary
Short summary
We introduce a new deep-learning model that addresses the limitations of existing urban flood models in handling varied terrains and rainfall events. Our model subdivides a city into small patches and presents a novel approach to incorporate broader terrain information. It accurately predicts high-resolution flood maps across diverse rainfall events and cities (on minute and meter scales) that haven’t been seen by the model, which offers valuable insights for urban flood mitigation strategies.
Nadav Peleg, Herminia Torelló-Sentelles, Grégoire Mariéthoz, Lionel Benoit, João P. Leitão, and Francesco Marra
Nat. Hazards Earth Syst. Sci., 23, 1233–1240, https://doi.org/10.5194/nhess-23-1233-2023, https://doi.org/10.5194/nhess-23-1233-2023, 2023
Short summary
Short summary
Floods in urban areas are one of the most common natural hazards. Due to climate change enhancing extreme rainfall and cities becoming larger and denser, the impacts of these events are expected to increase. A fast and reliable flood warning system should thus be implemented in flood-prone cities to warn the public of upcoming floods. The purpose of this brief communication is to discuss the potential implementation of low-cost acoustic rainfall sensors in short-term flood warning systems.
Nico Lang, Andrea Irniger, Agnieszka Rozniak, Roni Hunziker, Jan Dirk Wegner, and Konrad Schindler
Hydrol. Earth Syst. Sci., 25, 2567–2597, https://doi.org/10.5194/hess-25-2567-2021, https://doi.org/10.5194/hess-25-2567-2021, 2021
Short summary
Short summary
Grain size analysis is the key to understanding the sediment dynamics of river systems and is an important indicator for mitigating flood risk and preserving biodiversity in aquatic habitats. We propose GRAINet, a data-driven approach based on deep learning, to regress grain size distributions from georeferenced UAV images. This allows for a holistic analysis of entire gravel bars, resulting in robust grading curves and high-resolution maps of spatial grain size distribution at large scale.
R. Roscher, M. Volpi, C. Mallet, L. Drees, and J. D. Wegner
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-5-2020, 109–116, https://doi.org/10.5194/isprs-annals-V-5-2020-109-2020, https://doi.org/10.5194/isprs-annals-V-5-2020-109-2020, 2020
P. Chaudhary, S. D’Aronco, M. Moy de Vitry, J. P. Leitão, and J. D. Wegner
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2-W5, 5–12, https://doi.org/10.5194/isprs-annals-IV-2-W5-5-2019, https://doi.org/10.5194/isprs-annals-IV-2-W5-5-2019, 2019
C. Stucker, A. Richard, J. D. Wegner, and K. Schindler
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2, 263–270, https://doi.org/10.5194/isprs-annals-IV-2-263-2018, https://doi.org/10.5194/isprs-annals-IV-2-263-2018, 2018
Matthew Moy de Vitry, Simon Dicht, and João P. Leitão
Earth Syst. Sci. Data, 9, 657–666, https://doi.org/10.5194/essd-9-657-2017, https://doi.org/10.5194/essd-9-657-2017, 2017
Short summary
Short summary
Pluvial flash floods are a growing hazard in urban areas but the lack of appropriate data collection methods hinders the improvement of flood risk mapping and early warning systems. In the floodX project, 22 controlled urban flash floods were generated in a flood response training facility and monitored with state-of-the-art sensors complemented with standard surveillance cameras. The data can be used to explore vision-based monitoring concepts and flood model calibration strategies.
João P. Leitão, Matthew Moy de Vitry, Andreas Scheidegger, and Jörg Rieckermann
Hydrol. Earth Syst. Sci., 20, 1637–1653, https://doi.org/10.5194/hess-20-1637-2016, https://doi.org/10.5194/hess-20-1637-2016, 2016
Short summary
Short summary
Precise and detailed DEMs are essential to accurately predict overland flow in urban areas. In this this study we evaluated whether DEMs generated from UAV imagery are suitable for urban drainage overland flow modelling. Specifically, 14 UAV flights were conducted to assess the influence of four different flight parameters on the quality of generated DEMs. In addition, we compared the best quality UAV DEM to a conventional lidar-based DEM; the two DEMs are of comparable quality.
P. Tokarczyk, J. P. Leitao, J. Rieckermann, K. Schindler, and F. Blumensaat
Hydrol. Earth Syst. Sci., 19, 4215–4228, https://doi.org/10.5194/hess-19-4215-2015, https://doi.org/10.5194/hess-19-4215-2015, 2015
Short summary
Short summary
We investigate for the first time the possibility of deriving high-resolution imperviousness maps for urban areas from UAV imagery and using this information as input for urban drainage models. We show that imperviousness maps generated using UAV imagery processed with modern classification methods achieve accuracy comparable with standard, off-the-shelf aerial imagery. We conclude that UAV imagery represents a valuable alternative data source for urban drainage model applications.
Related subject area
Subject: Urban Hydrology | Techniques and Approaches: Instruments and observation techniques
A Bayesian updating framework for calibrating the hydrological parameters of road networks using taxi GPS data
Assessing specific differential phase (KDP)-based quantitative precipitation estimation for the record- breaking rainfall over Zhengzhou city on 20 July 2021
Sources and pathways of biocides and their transformation products in urban storm water infrastructure of a 2 ha urban district
Assessing different imaging velocimetry techniques to measure shallow runoff velocities during rain events using an urban drainage physical model
Using soil water isotopes to infer the influence of contrasting urban green space on ecohydrological partitioning
Reconstituting past flood events: the contribution of citizen science
Technical note: Laboratory modelling of urban flooding: strengths and challenges of distorted scale models
Weather radar rainfall data in urban hydrology
The potential of urban rainfall monitoring with crowdsourced automatic weather stations in Amsterdam
Gauge-adjusted rainfall estimates from commercial microwave links
Improving the precipitation accumulation analysis using lightning measurements and different integration periods
Local nutrient regimes determine site-specific environmental triggers of cyanobacterial and microcystin variability in urban lakes
Variability of drainage and solute leaching in heterogeneous urban vegetation environs
Technical note on measuring run-off dynamics from pavements using a new device: the weighable tipping bucket
Xiangfu Kong, Jiawen Yang, Ke Xu, Bo Dong, and Shan Jiang
Hydrol. Earth Syst. Sci., 27, 3803–3822, https://doi.org/10.5194/hess-27-3803-2023, https://doi.org/10.5194/hess-27-3803-2023, 2023
Short summary
Short summary
To solve the issue of sparsity of field-observed runoff data, we propose a methodology that leverages taxi GPS data to support hydrological parameter calibration for road networks. Novel to this study is that a new kind of data source, namely floating car data, is introduced to tackle the ungauged catchment problem, providing alternative flooding early warning supports for cities that have little runoff data but rich taxi data.
Haoran Li, Dmitri Moisseev, Yali Luo, Liping Liu, Zheng Ruan, Liman Cui, and Xinghua Bao
Hydrol. Earth Syst. Sci., 27, 1033–1046, https://doi.org/10.5194/hess-27-1033-2023, https://doi.org/10.5194/hess-27-1033-2023, 2023
Short summary
Short summary
A rainfall event that occurred at Zhengzhou on 20 July 2021 caused tremendous loss of life and property. This study compares different KDP estimation methods as well as the resulting QPE outcomes. The results show that the selection of the KDP estimation method has minimal impact on QPE, whereas the inadequate assumption of rain microphysics and unquantified vertical air motion may explain the underestimated 201.9 mm h−1 record.
Felicia Linke, Oliver Olsson, Frank Preusser, Klaus Kümmerer, Lena Schnarr, Marcus Bork, and Jens Lange
Hydrol. Earth Syst. Sci., 25, 4495–4512, https://doi.org/10.5194/hess-25-4495-2021, https://doi.org/10.5194/hess-25-4495-2021, 2021
Short summary
Short summary
We used a two-step approach with limited sampling effort in existing storm water infrastructure to illustrate the risk of biocide emission in a 2 ha urban area 13 years after construction had ended. First samples at a swale confirmed the overall relevance of biocide pollution. Then we identified sources where biocides were used for film protection and pathways where transformation products were formed. Our results suggest that biocide pollution is a also continuous risk in aging urban areas.
Juan Naves, Juan T. García, Jerónimo Puertas, and Jose Anta
Hydrol. Earth Syst. Sci., 25, 885–900, https://doi.org/10.5194/hess-25-885-2021, https://doi.org/10.5194/hess-25-885-2021, 2021
Short summary
Short summary
Surface water velocities are key in the calibration of physically based urban drainage models, but the shallow depths developed during non-extreme rainfall and the risks during floods limit the availability of this type of data. This study proves the potential of different imaging velocimetry techniques to measure water runoff velocities in urban catchments during rain events, highlighting the importance of considering rain properties to interpret and assess the results obtained.
Lena-Marie Kuhlemann, Doerthe Tetzlaff, Aaron Smith, Birgit Kleinschmit, and Chris Soulsby
Hydrol. Earth Syst. Sci., 25, 927–943, https://doi.org/10.5194/hess-25-927-2021, https://doi.org/10.5194/hess-25-927-2021, 2021
Short summary
Short summary
We studied water partitioning under urban grassland, shrub and trees during a warm and dry growing season in Berlin, Germany. Soil evaporation was highest under grass, but total green water fluxes and turnover time of soil water were greater under trees. Lowest evapotranspiration losses under shrub indicate potential higher drought resilience. Knowledge of water partitioning and requirements of urban green will be essential for better adaptive management of urban water and irrigation strategies.
Bocar Sy, Corine Frischknecht, Hy Dao, David Consuegra, and Gregory Giuliani
Hydrol. Earth Syst. Sci., 24, 61–74, https://doi.org/10.5194/hess-24-61-2020, https://doi.org/10.5194/hess-24-61-2020, 2020
Xuefang Li, Sébastien Erpicum, Martin Bruwier, Emmanuel Mignot, Pascal Finaud-Guyot, Pierre Archambeau, Michel Pirotton, and Benjamin Dewals
Hydrol. Earth Syst. Sci., 23, 1567–1580, https://doi.org/10.5194/hess-23-1567-2019, https://doi.org/10.5194/hess-23-1567-2019, 2019
Short summary
Short summary
With a growing urban flood risk worldwide, flood risk management tools need to be validated against reference data. Field and remote-sensing observations provide valuable data on inundation extent and depth but virtually no information on flow velocity. Laboratory scale models have the potential to deliver complementary data, provided that the model scaling is performed carefully. In this paper, we reanalyse existing laboratory data to discuss challenges related to the scaling of urban floods.
Søren Thorndahl, Thomas Einfalt, Patrick Willems, Jesper Ellerbæk Nielsen, Marie-Claire ten Veldhuis, Karsten Arnbjerg-Nielsen, Michael R. Rasmussen, and Peter Molnar
Hydrol. Earth Syst. Sci., 21, 1359–1380, https://doi.org/10.5194/hess-21-1359-2017, https://doi.org/10.5194/hess-21-1359-2017, 2017
Short summary
Short summary
This paper reviews how weather radar data can be used in urban hydrological applications. It focuses on three areas of research: (1) temporal and spatial resolution of rainfall data, (2) rainfall estimation, radar data adjustment and data quality, and (3) nowcasting of radar rainfall and real-time applications. Moreover, the paper provides examples of urban hydrological applications which can benefit from radar rainfall data in comparison to tradition rain gauge measurements of rainfall.
Lotte de Vos, Hidde Leijnse, Aart Overeem, and Remko Uijlenhoet
Hydrol. Earth Syst. Sci., 21, 765–777, https://doi.org/10.5194/hess-21-765-2017, https://doi.org/10.5194/hess-21-765-2017, 2017
Short summary
Short summary
Recent developments have made it possible to easily crowdsource meteorological measurements from automatic personal weather stations worldwide. This has offered free access to rainfall ground measurements at spatial and temporal resolutions far exceeding those of national operational sensor networks, especially in cities. This paper is the first step to make optimal use of this promising source of rainfall measurements and identify challenges for future implementation for urban applications.
Martin Fencl, Michal Dohnal, Jörg Rieckermann, and Vojtěch Bareš
Hydrol. Earth Syst. Sci., 21, 617–634, https://doi.org/10.5194/hess-21-617-2017, https://doi.org/10.5194/hess-21-617-2017, 2017
Short summary
Short summary
Commercial microwave links (CMLs) can provide rainfall observations with high space–time resolution. Unfortunately, CML rainfall estimates are often biased because we lack detailed information on the processes that attenuate the transmitted microwaves. We suggest removing the bias by continuously adjusting CMLs to cumulative data from rain gauges (RGs), which can be remote from the CMLs. Our approach practically eliminates the bias, which we demonstrate on unique data from several CMLs and RGs.
Erik Gregow, Antti Pessi, Antti Mäkelä, and Elena Saltikoff
Hydrol. Earth Syst. Sci., 21, 267–279, https://doi.org/10.5194/hess-21-267-2017, https://doi.org/10.5194/hess-21-267-2017, 2017
Short summary
Short summary
A new lightning data assimilation method has been implemented and validated within the Finnish Meteorological Institute – Local Analysis and Prediction System. Lightning data do improve the analysis when no radars are available, and even with radar data, lightning data have a positive impact on the results.
We also investigate the usage of different time integration intervals: 1, 6, 12, 24 h and 7 days, where the 1 h integration time length gives the best results.
S. C. Sinang, E. S. Reichwaldt, and A. Ghadouani
Hydrol. Earth Syst. Sci., 19, 2179–2195, https://doi.org/10.5194/hess-19-2179-2015, https://doi.org/10.5194/hess-19-2179-2015, 2015
H. Nouri, S. Beecham, A. M. Hassanli, and G. Ingleton
Hydrol. Earth Syst. Sci., 17, 4339–4347, https://doi.org/10.5194/hess-17-4339-2013, https://doi.org/10.5194/hess-17-4339-2013, 2013
T. Nehls, Y. Nam Rim, and G. Wessolek
Hydrol. Earth Syst. Sci., 15, 1379–1386, https://doi.org/10.5194/hess-15-1379-2011, https://doi.org/10.5194/hess-15-1379-2011, 2011
Cited articles
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M.,
Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R.,
Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden,
P., Wicke, M., Yu, Y., Zheng, X., Brain, G., Osdi, I., Barham, P., Chen, J.,
Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard,
M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner,
B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., and Zheng, X.:
TensorFlow: A System for Large-Scale
Machine Learning, Proc 12th USENIX Conf. Oper. Syst. Des. Implement., 2–4 November 2016, Savannah, GA, USA,
272–283, 2016.
Bhola, P. K., Nair, B. B., Leandro, J., Rao, S. N., and Disse, M.: Flood
inundation forecasts using validation data generated with the assistance of
computer vision, J. Hydroinform., 21, 240–256, https://doi.org/10.2166/hydro.2018.044, 2018.
Blanchard, E.: Hurricane Harvey Flooding in Houston, available at: https://www.youtube.com/watch?v=__IBuu06URY (last access: 8 October 2018), 2017.
Chaudhary, P.: Floodwater-estimation through semantic image interpretation,
Technical University Munich, Munich, Germany, 2018.
Chaudhary, P., Aronco, S. D., Moy de Vitry, M., Leitao, J. P., and Wegner, J.
D.: Flood-Water Level Estimation from Social Media Images, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W5, 5–12, 2019.
Chollet, F., and others: Keras Documentation, available at:
https://keras.io (last access: 11 November 2019), 2015.
Cityofchaska: Athletic Park Flood, available at:
https://www.youtube.com/watch?v=7cnXTgpcnSo (last access: 8 October 2018),
2010.
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B.: The Cityscapes Dataset, in: CVPR Workshop on The Future of Datasets in Vision, 7–12 June 2015, Boston, USA, 2015.
El Kadi Abderrezzak, K., Paquier, A., and Mignot, E.: Modelling flash flood
propagation in urban areas using a two-dimensional numerical model,
Nat. Hazards, 50, 433–460, 2009.
Fukushima, K.: Neocognitron: A self-organizing neural network model for a
mechanism of pattern recognition unaffected by shift in position, Biol.
Cybern., 36, 193–202, https://doi.org/10.1007/BF00344251, 1980.
Gaitan, S., van de Giesen, N. C., and ten Veldhuis, J. A. E. E.: Can urban
pluvial flooding be predicted by open spatial data and weather data?,
Environ. Modell. Softw., 85, 156–171, https://doi.org/10.1016/j.envsoft.2016.08.007,
2016.
Goold, B., Van Den Hoven, J., Lim, L., Seck, M., Squires, P., and Töpfer,
E.: Citizens, Cities and Video Surveillance, European Forum for Urban Security, Paris, France, 2010.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image
Recognition, in: 2016 IEEE Conference on Computer Vision and Pattern
Recognition (CVPR),
26 June–1 July 2016, Las Vegas, USA, 770–778, 2016.
He, K., Gkioxari, G., Dollar, P., Girshick, R., Dollár, P., and Girshick,
R.: Mask R-CNN, in: Proceedings of the IEEE International Conference on
Computer Vision, 22–29 October 2017,
Venice, Italy, 2017.
Heller, N., Dean, J., and Papanikolopoulos, N.: Imperfect Segmentation
Labels: How Much Do They Matter?, in: Intravascular Imaging and Computer
Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert
Label Synthesis, Springer International Publishing, 112–120, available at: https://link.springer.com/chapter/10.1007/978-3-030-01364-6_13 (last access: 14 November 2019), 2018.
Hunter, N. M., Bates, P. D., Neelz, S., Pender, G., Villanueva, I., Wright,
N. G., Liang, D., Falconer, R. A., Lin, B., Waller, S., Crossley, A. J., and
Mason, D. C.: Benchmarking 2D hydraulic models for urban flooding, Proc.
Inst. Civ. Eng.-Water Manag., 161, 13–30,
https://doi.org/10.1680/wama.2008.161.1.13, 2008.
Hurricanetrack: Brays Bayou Flooding Time Lapse and Real-Time Archive,
available at:
https://www.youtube.com/watch?v=y6jByqVX7PE (last access: 8 October 2018),
2015.
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep Network
Training by Reducing Internal Covariate Shift, arXiv1502.03167, available at: http://arxiv.org/abs/1502.03167 (last access: 13 November 2019), 2015.
Jiang, J., Liu, J., Qin, C.-Z. Z., and Wang, D.: Extraction of Urban
Waterlogging Depth from Video Images Using Transfer Learning, Water, 10, 1485,
https://doi.org/10.3390/w10101485, 2018.
Jiang, J., Liu, J., Cheng, C., Huang, J., and Xue, A.: Automatic Estimation
of Urban Waterlogging Depths from Video Images Based on Ubiquitous Reference
Objects, Remote Sens., 11, 587, https://doi.org/10.3390/rs11050587, 2019.
Jiang, Y., Zevenbergen, C., and Ma, Y.: Urban pluvial flooding and stormwater
management: A contemporary review of China's challenges and “sponge
cities” strategy, Environ. Sci. Policy, 80, 132–143,
https://doi.org/10.1016/j.envsci.2017.11.016, 2018.
Kim, B., Sanders, B. F., Han, K., Kim, Y., and Famiglietti, J. S.:
Calibration of Stormwater management model using flood extent data, Proc.
Inst. Civ. Eng. Water Manag., 167, 17–29, https://doi.org/10.1680/wama.12.00051,
2014.
Kim, J., Han, Y., and Hahn, H.: Embedded implementation of image-based
water-level measurement system, IET Comput. Vis., 5, 125–133, https://doi.org/10.1049/Iet-Cvi.2009.0144, 2011.
Kingma, D. P. and Ba, J. L.: Adam: A method for stochastic gradient descent,
ICLR Int. Conf. Learn. Represent., 7–9 May 2015, San Diego, CA, USA, 1–15, 2015.
Leandro, J., Chen, A. S., Djordjević, S., and Savić, D. A.:
Comparison of 1D/1D and 1D/2D Coupled (Sewer/Surface) Hydraulic Models for
Urban Flood Simulation, J. Hydraul. Eng., 135, 495–504,
https://doi.org/10.1061/(ASCE)HY.1943-7900.0000037, 2009.
Levandowsky, M. and Winter, D.: Distance between Sets, Nature, 234,
34–35, https://doi.org/10.1038/234034a0, 1971.
Liu, L., Liu, Y., Wang, X., Yu, D., Liu, K., Huang, H., and Hu, G.: Developing an effective 2-D urban flood inundation model for city emergency management based on cellular automata, Nat. Hazards Earth Syst. Sci., 15, 381–391, https://doi.org/10.5194/nhess-15-381-2015, 2015.
Lo, S. W., Wu, J. H., Lin, F. P., and Hsu, C. H.: Visual sensing for urban
flood monitoring, Sensors (Switzerland), 15, 20006–20029,
https://doi.org/10.3390/s150820006, 2015.
Long, J., Shelhamer, E., and Darrell, T.: Fully Convolutional Networks for
Semantic Segmentation, in: Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition,
7–12 June 2015, Boston, MA, USA, 3431–3440, 2015.
Lv, Y., Gao, W., Yang, C., and Wang, N.: Inundated Areas Extraction Based on
Raindrop Photometric Model (RPM) in
Surveillance Video, Water, 10, 1332, https://doi.org/10.3390/w10101332, 2018.
McKinney, W.: Data Structures for Statistical Computing in Python, in:
Proceedings of the 9th Python in Science Conference, 28 June–3 July 2010,
Austin, Texas, USA, 2010.
Mousa, M., Zhang, X., and Claudel, C.: Flash Flood Detection in Urban Cities
Using Ultrasonic and Infrared Sensors, IEEE Sens. J., 16, 7204–7216,
https://doi.org/10.1109/JSEN.2016.2592359, 2016.
Moy de Vitry, M.: Data for: Scalable Flood Level Trend Monitoring with Surveillance Cameras using a Deep Convolutional Neural Network, Zenodo, https://doi.org/10.25678/000150, 2019.
Moy de Vitry, M. and Kramer, S.: Water level trend monitoring with a surveillance camera using a deep convolutional neural network, https://doi.org/10.5446/43637, 2019.
Moy de Vitry, M., Dicht, S., and Leitão, J. P.: floodX: urban flash flood experiments monitored with conventional and alternative sensors, Earth Syst. Sci. Data, 9, 657–666, https://doi.org/10.5194/essd-9-657-2017, 2017.
Noh, H., Hong, S., and Han, B.: Learning Deconvolution Network for Semantic
Segmentation, in: 2015 IEEE International Conference on Computer Vision
(ICCV), 2015 Inter,
Santiago, Chile, 7–13 December 2015, 1520–1528, 2015.
Paprotny, D., Sebastian, A., Morales-Nápoles, O., and Jonkman, S. N.:
Trends in flood losses in Europe over the past 150 years, Nat. Commun.,
9, 1985, https://doi.org/10.1038/s41467-018-04253-1, 2018.
Pröve, P.-L.: Unet-keras, available at:
https://github.com/pietz/unet-keras (last access: 13 November 2019), 2017.
Roisman, D.: Houston Harvey Flood – Meyerland Neighborhood – August 27 2017
– Garage Time Lapse, available at:
https://www.youtube.com/watch?v=ZOpWO7rJbtU (last access: 8 October 2018),
2017.
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for
biomedical image segmentation, Lect. Notes Comput. Sci. (including Subser.
Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 9351, 234–241,
https://doi.org/10.1007/978-3-319-24574-4_28, 2015.
Sakaino, H.: Camera-Vision-Based Water Level Estimation, IEEE Sens. J.,
16, 7564–7565, https://doi.org/10.1109/JSEN.2016.2603524, 2016.
Seibert, J.: Multi-criteria calibration of a conceptual runoff model using a genetic algorithm, Hydrol. Earth Syst. Sci., 4, 215–224, https://doi.org/10.5194/hess-4-215-2000, 2000.
Skougaard Kaspersen, P., Høegh Ravn, N., Arnbjerg-Nielsen, K., Madsen, H., and Drews, M.: Comparison of the impacts of urban development and climate change on exposing European cities to pluvial flooding, Hydrol. Earth Syst. Sci., 21, 4131–4147, https://doi.org/10.5194/hess-21-4131-2017, 2017.
Spearman, C.: The Proof and Measurement of Association between Two Things,
Am. J. Psychol., 15, 72–101, https://doi.org/10.2307/1412159, 1904.
Sperber, S., Seck, M., and Johnston, E.: Surveille Deliverable 2.3: Paper by
local authorities end-users, available at: https://surveille.eui.eu/wp-content/uploads/sites/19/2015/04/D2.3-Paper-by-Local-Authorities-End-Users.pdf
(last access: 13 November 2019), 2013.
ten Veldhuis, J. A. E.: How the choice of flood damage metrics influences
urban flood risk assessment, J. Flood Risk Manag., 4, 281–287,
https://doi.org/10.1111/j.1753-318X.2011.01112.x, 2011.
Tscheikner-Gratl, F., Zeisl, P., Kinzel, C., Leimgruber, J., Ertl, T.,
Rauch, W., and Kleidorfer, M.: Lost in calibration: why people still don't
calibrate their models, and why they still should – a case study from urban
drainage modelling, Water Sci. Technol., 395, 2337–2348, https://doi.org/10.2166/wst.2016.395,
2016.
van Meerveld, H. J. I., Vis, M. J. P., and Seibert, J.: Information content of stream level class data for hydrological model calibration, Hydrol. Earth Syst. Sci., 21, 4895–4905, https://doi.org/10.5194/hess-21-4895-2017, 2017.
van Riel, W.: Exploratory study of pluvial flood impacts in Dutch urban
areas, Deltares, Delft, the Netherlands, 2011.
Wang, R. Q., Mao, H., Wang, Y., Rae, C., and Shaw, W.: Hyper-resolution
monitoring of urban flooding with social media and crowdsourcing data,
Comput. Geosci., 111, 139–147,
https://doi.org/10.1016/j.cageo.2017.11.008, 2018.
Wani, O., Scheidegger, A., Carbajal, J. P., Rieckermann, J., and Blumensaat,
F.: Parameter estimation of hydrologic models using a likelihood function
for censored and binary observations, Water Res., 121, 290–301,
https://doi.org/10.1016/j.watres.2017.05.038, 2017.
Yu, D., Yin, J., and Liu, M.: Validating city-scale surface water flood
modelling using crowd-sourced data, Environ. Res. Lett., 11, 124011,
https://doi.org/10.1088/1748-9326/11/12/124011, 2016.
Zahnt, N., Eder, M., and Habersack, H.: Herausforderungen durch pluviale
Überflutungen – Grundlagen, Schäden und Lösungsansätze,
Osterr. Wasser Abfallwirtsch., 70, 64–77, 2018.
Zeiler, M. D., Taylor, G. W., and Fergus, R.: Adaptive deconvolutional
networks for mid and high level feature learning, in: Proceedings of the IEEE
International Conference on Computer Vision, 6–13 November 2011, Barcelona, Spain, 2018–2025, 2011.
Zou, K. H., Warfield, S. K., Bharatha, A., Tempany, C. M. C., Kaus, M. R.,
Haker, S. J., Wells, W. M., Jolesz, F. A., and Kikinis, R.: Statistical
Validation of Image Segmentation Quality Based on a Spatial Overlap Index,
Acad. Radiol., 11, 178–189, https://doi.org/10.1016/S1076-6332(03)00671-8, 2004.
Short summary
This work demonstrates a new approach to obtain flood level trend information from surveillance footage with minimal prior information. A neural network trained to detect flood water is applied to video frames to create a qualitative flooding metric (namely, SOFI). The correlation between the real water trend and SOFI was found to be 75 % on average (based on six videos of flooding under various circumstances). SOFI could be used for flood model calibration, to increase model reliability.
This work demonstrates a new approach to obtain flood level trend information from surveillance...
