Articles | Volume 28, issue 24
https://doi.org/10.5194/hess-28-5443-2024
© 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-28-5443-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
18 Dec 2024
Research article |
| 18 Dec 2024
| 18 Dec 2024
Enhancing generalizability of data-driven urban flood models by incorporating contextual information
Institute of Earth Surface Dynamics, University of Lausanne, Lausanne, Switzerland
Milton Salvador Gomez
Institute of Earth Surface Dynamics, University of Lausanne, Lausanne, Switzerland
Expertise Center for Climate Extremes, University of Lausanne, Lausanne, Switzerland
Tom Beucler
Institute of Earth Surface Dynamics, University of Lausanne, Lausanne, Switzerland
Expertise Center for Climate Extremes, University of Lausanne, Lausanne, Switzerland
Jovan Blagojevic
Institute of Environmental Engineering, ETH Zurich, Zurich, Switzerland
João Paulo Leitao
Department of Urban Water Management, Swiss Federal Institute of Aquatic Science and Technology, Dubendorf, Switzerland
Nadav Peleg
Institute of Earth Surface Dynamics, University of Lausanne, Lausanne, Switzerland
Expertise Center for Climate Extremes, University of Lausanne, Lausanne, Switzerland
Related authors
No articles found.
Francesco Marra, Nadav Peleg, Elena Cristiano, Efthymios I. Nikolopoulos, Federica Remondi, and Paolo Tarolli
Nat. Hazards Earth Syst. Sci., 25, 2565–2570, https://doi.org/10.5194/nhess-25-2565-2025, https://doi.org/10.5194/nhess-25-2565-2025, 2025
Short summary
Short summary
Climate change is escalating the risks related to hydro-meteorological extremes. This preface introduces a special issue originating from a European Geosciences Union (EGU) session. It highlights the challenges posed by these extremes, ranging from hazard assessment to mitigation strategies, and covers both water excess events like floods, landslides, and coastal hazards and water deficit events such as droughts and fire weather. The collection aims to advance understanding, improve resilience, and inform policy-making.
Qi Zhuang, Marika Koukoula, Shuguang Liu, Zhengzheng Zhou, and Nadav Peleg
EGUsphere, https://doi.org/10.5194/egusphere-2025-1002, https://doi.org/10.5194/egusphere-2025-1002, 2025
Short summary
Short summary
Understanding how projected urbanization and climate change affect typhoons, which may cause the most destructive natural catastrophes, is crucial. Based on numerical simulations of five landfalling typhoons in Shanghai, China, our results highlight that warming sea surface temperatures significantly shift typhoon tracks with intensified structures (increased size, intensity, and affected time) on the big scale. At the meantime, urbanization further enhances local rainfall intensity.
Mosisa Tujuba Wakjira, Nadav Peleg, Johan Six, and Peter Molnar
Hydrol. Earth Syst. Sci., 29, 863–886, https://doi.org/10.5194/hess-29-863-2025, https://doi.org/10.5194/hess-29-863-2025, 2025
Short summary
Short summary
In this study, we implement a climate, water, and crop interaction model to evaluate current conditions and project future changes in rainwater availability and its yield potential, with the goal of informing adaptation policies and strategies in Ethiopia. Although climate change is likely to increase rainfall in Ethiopia, our findings suggest that water-scarce croplands in Ethiopia are expected to face reduced crop yields during the main growing season due to increases in temperature.
Janbert Aarnink, Tom Beucler, Marceline Vuaridel, and Virginia Ruiz-Villanueva
Earth Surf. Dynam., 13, 167–189, https://doi.org/10.5194/esurf-13-167-2025, https://doi.org/10.5194/esurf-13-167-2025, 2025
Short summary
Short summary
This study presents a novel convolutional-neural-network approach for detecting instream large wood in rivers, addressing the need for flexible monitoring methods across diverse data sources. Using a database of 15 228 fully labelled images, the model achieved a weighted mean average precision of 67 %. Fine-tuning parameters and sampling techniques can improve performance by over 10 % in some cases, offering valuable insights into ecosystem management.
Judith Eeckman, Brian De Grenus, Floreana Miesen, James Thornton, Philip Brunner, and Nadav Peleg
EGUsphere, https://doi.org/10.5194/egusphere-2024-1832, https://doi.org/10.5194/egusphere-2024-1832, 2024
Short summary
Short summary
The fate of liquid water from melting snow in winter and spring is difficult to understand in the mountains. This work uses uncommon methods to accurately track the dynamics of snowmelt and infiltration at different depths in the ground and at different altitudes. The results show that melting snow quickly infiltrates into the upper layers of the soil but is also quickly transferred into the surface layer of the soil along the slopes towards the river.
Francesco Marra, Marika Koukoula, Antonio Canale, and Nadav Peleg
Hydrol. Earth Syst. Sci., 28, 375–389, https://doi.org/10.5194/hess-28-375-2024, https://doi.org/10.5194/hess-28-375-2024, 2024
Short summary
Short summary
We present a new physical-based method for estimating extreme sub-hourly precipitation return levels (i.e., intensity–duration–frequency, IDF, curves), which are critical for the estimation of future floods. The proposed model, named TENAX, incorporates temperature as a covariate in a physically consistent manner. It has only a few parameters and can be easily set for any climate station given sub-hourly precipitation and temperature data are available.
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.
Michael Schirmer, Adam Winstral, Tobias Jonas, Paolo Burlando, and Nadav Peleg
The Cryosphere, 16, 3469–3488, https://doi.org/10.5194/tc-16-3469-2022, https://doi.org/10.5194/tc-16-3469-2022, 2022
Short summary
Short summary
Rain is highly variable in time at a given location so that there can be both wet and dry climate periods. In this study, we quantify the effects of this natural climate variability and other sources of uncertainty on changes in flooding events due to rain on snow (ROS) caused by climate change. For ROS events with a significant contribution of snowmelt to runoff, the change due to climate was too small to draw firm conclusions about whether there are more ROS events of this important type.
Nadav Peleg, Chris Skinner, Simone Fatichi, and Peter Molnar
Earth Surf. Dynam., 8, 17–36, https://doi.org/10.5194/esurf-8-17-2020, https://doi.org/10.5194/esurf-8-17-2020, 2020
Short summary
Short summary
Extreme rainfall is expected to intensify with increasing temperatures, which will likely affect rainfall spatial structure. The spatial variability of rainfall can affect streamflow and sediment transport volumes and peaks. The sensitivity of the hydro-morphological response to changes in the structure of heavy rainfall was investigated. It was found that the morphological components are more sensitive to changes in rainfall spatial structure in comparison to the hydrological components.
Matthew Moy de Vitry, Simon Kramer, Jan Dirk Wegner, and João P. Leitão
Hydrol. Earth Syst. Sci., 23, 4621–4634, https://doi.org/10.5194/hess-23-4621-2019, https://doi.org/10.5194/hess-23-4621-2019, 2019
Short summary
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.
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.
Francesco Marra, Efrat Morin, Nadav Peleg, Yiwen Mei, and Emmanouil N. Anagnostou
Hydrol. Earth Syst. Sci., 21, 2389–2404, https://doi.org/10.5194/hess-21-2389-2017, https://doi.org/10.5194/hess-21-2389-2017, 2017
Short summary
Short summary
Rainfall frequency analyses from radar and satellite estimates over the eastern Mediterranean are compared examining different climatic conditions. Correlation between radar and satellite results is high for frequent events and decreases with return period. The uncertainty related to record length is larger for drier climates. The agreement between different sensors instills confidence on their use for rainfall frequency analysis in ungauged areas of the Earth.
Nadav Peleg, Frank Blumensaat, Peter Molnar, Simone Fatichi, and Paolo Burlando
Hydrol. Earth Syst. Sci., 21, 1559–1572, https://doi.org/10.5194/hess-21-1559-2017, https://doi.org/10.5194/hess-21-1559-2017, 2017
Short summary
Short summary
We investigated the relative contribution of the spatial versus climatic rainfall variability for flow peaks by applying an advanced stochastic rainfall generator to simulate rainfall for a small urban catchment and simulate flow dynamics in the sewer system. We found that the main contribution to the total flow variability originates from the natural climate variability. The contribution of spatial rainfall variability to the total flow variability was found to increase with return periods.
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.
N. Peleg, E. Shamir, K. P. Georgakakos, and E. Morin
Hydrol. Earth Syst. Sci., 19, 567–581, https://doi.org/10.5194/hess-19-567-2015, https://doi.org/10.5194/hess-19-567-2015, 2015
N. Peleg, M. Ben-Asher, and E. Morin
Hydrol. Earth Syst. Sci., 17, 2195–2208, https://doi.org/10.5194/hess-17-2195-2013, https://doi.org/10.5194/hess-17-2195-2013, 2013
Related subject area
Subject: Urban Hydrology | Techniques and Approaches: Modelling approaches
Analysis of past and future droughts causing clay shrinkage in France
Pluvial and potential compound flooding in a coupled coastal modeling framework: New York City during post-tropical Cyclone Ida (2021)
Beyond total impervious area: a new lumped descriptor of basin-wide hydrologic connectivity for characterizing urban watersheds
INSPIRE game: integration of vulnerability into impact-based forecasting of urban floods
Exploring the driving factors of compound flood severity in coastal cities: a comprehensive analytical approach
Simulation of spatially distributed sources, transport, and transformation of nitrogen from fertilization and septic systems in a suburban watershed
Combining statistical and hydrodynamic models to assess compound flood hazards from rainfall and storm surge: a case study of Shanghai
An optimized long short-term memory (LSTM)-based approach applied to early warning and forecasting of ponding in the urban drainage system
A deep-learning-technique-based data-driven model for accurate and rapid flood predictions in temporal and spatial dimensions
Impact of urban geology on model simulations of shallow groundwater levels and flow paths
Technical note: Modeling spatial fields of extreme precipitation – a hierarchical Bayesian approach
Intersecting near-real time fluvial and pluvial inundation estimates with sociodemographic vulnerability to quantify a household flood impact index
Forecasting green roof detention performance by temporal downscaling of precipitation time-series projections
Evaluating different machine learning methods to simulate runoff from extensive green roofs
Modeling and interpreting hydrological responses of sustainable urban drainage systems with explainable machine learning methods
The impact of the spatiotemporal structure of rainfall on flood frequency over a small urban watershed: an approach coupling stochastic storm transposition and hydrologic modeling
Space variability impacts on hydrological responses of nature-based solutions and the resulting uncertainty: a case study of Guyancourt (France)
Urban surface water flood modelling – a comprehensive review of current models and future challenges
Resampling and ensemble techniques for improving ANN-based high-flow forecast accuracy
Event selection and two-stage approach for calibrating models of green urban drainage systems
Modeling the high-resolution dynamic exposure to flooding in a city region
Drainage area characterization for evaluating green infrastructure using the Storm Water Management Model
Critical scales to explain urban hydrological response: an application in Cranbrook, London
Increase in flood risk resulting from climate change in a developed urban watershed – the role of storm temporal patterns
Patterns and comparisons of human-induced changes in river flood impacts in cities
Scale effect challenges in urban hydrology highlighted with a distributed hydrological model
Comparison of the impacts of urban development and climate change on exposing European cities to pluvial flooding
Spatial and temporal variability of rainfall and their effects on hydrological response in urban areas – a review
Hydrodynamics of pedestrians' instability in floodwaters
Formulating and testing a method for perturbing precipitation time series to reflect anticipated climatic changes
Using rainfall thresholds and ensemble precipitation forecasts to issue and improve urban inundation alerts
Enhancing the T-shaped learning profile when teaching hydrology using data, modeling, and visualization activities
On the sensitivity of urban hydrodynamic modelling to rainfall spatial and temporal resolution
Precipitation variability within an urban monitoring network via microcanonical cascade generators
Estimation of peak discharges of historical floods
Indirect downscaling of hourly precipitation based on atmospheric circulation and temperature
Assessing the hydrologic restoration of an urbanized area via an integrated distributed hydrological model
Using the Storm Water Management Model to predict urban headwater stream hydrological response to climate and land cover change
Evaluating scale and roughness effects in urban flood modelling using terrestrial LIDAR data
Contribution of directly connected and isolated impervious areas to urban drainage network hydrographs
Thermal management of an unconsolidated shallow urban groundwater body
Online multistep-ahead inundation depth forecasts by recurrent NARX networks
A statistical analysis of insurance damage claims related to rainfall extremes
Joint impact of rainfall and tidal level on flood risk in a coastal city with a complex river network: a case study of Fuzhou City, China
Urbanization and climate change impacts on future urban flooding in Can Tho city, Vietnam
Multi-objective optimization for combined quality–quantity urban runoff control
Development of flood probability charts for urban drainage network in coastal areas through a simplified joint assessment approach
Auto-control of pumping operations in sewerage systems by rule-based fuzzy neural networks
Coupling urban event-based and catchment continuous modelling for combined sewer overflow river impact assessment
Dynamic neural networks for real-time water level predictions of sewerage systems-covering gauged and ungauged sites
Sophie Barthelemy, Bertrand Bonan, Miquel Tomas-Burguera, Gilles Grandjean, Séverine Bernardie, Jean-Philippe Naulin, Patrick Le Moigne, Aaron Boone, and Jean-Christophe Calvet
Hydrol. Earth Syst. Sci., 29, 2321–2337, https://doi.org/10.5194/hess-29-2321-2025, https://doi.org/10.5194/hess-29-2321-2025, 2025
Short summary
Short summary
A drought index is developed that quantifies drought on an annual scale, making it applicable to monitoring clay shrinkage damage to buildings. A comparison with the number of insurance claims for subsidence shows that the presence of trees near individual houses must be taken into account. Significant soil moisture droughts occurred in France in 2003, 2018, 2019, 2020, and 2022. Particularly high index values are observed in 2022. It is found that droughts will become more severe in the future.
Shima Kasaei, Philip M. Orton, David K. Ralston, and John C. Warner
Hydrol. Earth Syst. Sci., 29, 2043–2058, https://doi.org/10.5194/hess-29-2043-2025, https://doi.org/10.5194/hess-29-2043-2025, 2025
Short summary
Short summary
Coastal urban areas are highly prone to flooding from rainfall, storm surge, and the combination of both. We improve a coastal model and use it to quantify flooding from Hurricane Ida in the Jamaica Bay watershed of New York City (NYC), creating a flood map and flooded area estimation. Experiments with shifted storm tracks and rainfall timing at high tide show that Ida, already the worst rainfall in NYC, could have been worse. This highlights the area's vulnerability and the need for thorough flood risk analysis.
Francesco Dell'Aira and Claudio I. Meier
Hydrol. Earth Syst. Sci., 29, 1001–1032, https://doi.org/10.5194/hess-29-1001-2025, https://doi.org/10.5194/hess-29-1001-2025, 2025
Short summary
Short summary
Scientists and engineers need better indices to frame the hydrologic effects of land development. Existing approaches are not able to reflect the interactions due to the spatial arrangement of distinct land patches, which affect how much runoff is generated and how fast it can travel downstream, impacting flood response. Our novel, GIS-based modeling framework explicitly considers these aspects and is applicable to a wide range of problems, including peak-flow predictions in ungauged basins.
Akshay Singhal, Louise Crochemore, Isabelle Ruin, and Sanjeev K. Jha
Hydrol. Earth Syst. Sci., 29, 947–967, https://doi.org/10.5194/hess-29-947-2025, https://doi.org/10.5194/hess-29-947-2025, 2025
Short summary
Short summary
A serious game experiment is presented which assesses the interplay between hazard, exposure, and vulnerability in a flash flood event. The results show that participants' use of information to make decisions was based on the severity of the situation. Participants used precipitation forecast and exposure to make correct decisions in the first round, while they used precipitation forecast and vulnerability information in the second round.
Yan Liu, Ting Zhang, Yi Ding, Aiqing Kang, Xiaohui Lei, and Jianzhu Li
Hydrol. Earth Syst. Sci., 28, 5541–5555, https://doi.org/10.5194/hess-28-5541-2024, https://doi.org/10.5194/hess-28-5541-2024, 2024
Short summary
Short summary
In coastal cities, rainfall and tides contribute to compound flooding. This study quantifies the impacts of rainfall and tides on compound flooding and analyzes interactions between different flood types. Findings show that rainfall generally has a greater effect on flooding than tide levels. The interaction between fluvial and pluvial flooding amplifies the flood disaster, with tide levels having the most significant impact during the interaction phase.
Ruoyu Zhang, Lawrence E. Band, Peter M. Groffman, Laurence Lin, Amanda K. Suchy, Jonathan M. Duncan, and Arthur J. Gold
Hydrol. Earth Syst. Sci., 28, 4599–4621, https://doi.org/10.5194/hess-28-4599-2024, https://doi.org/10.5194/hess-28-4599-2024, 2024
Short summary
Short summary
Human-induced nitrogen (N) from fertilization and septic effluents is the primary N source in urban watersheds. We developed a model to understand how spatial and temporal patterns of these loads affect hydrologic and biogeochemical processes at the hillslope level. The comparable simulations to observations showed the ability of our model to enhance insights into current water quality conditions, identify high-N-retention locations, and plan future restorations to improve urban water quality.
Hanqing Xu, Elisa Ragno, Sebastiaan N. Jonkman, Jun Wang, Jeremy D. Bricker, Zhan Tian, and Laixiang Sun
Hydrol. Earth Syst. Sci., 28, 3919–3930, https://doi.org/10.5194/hess-28-3919-2024, https://doi.org/10.5194/hess-28-3919-2024, 2024
Short summary
Short summary
A coupled statistical–hydrodynamic model framework is employed to quantitatively evaluate the sensitivity of compound flood hazards to the relative timing of peak storm surges and rainfall. The findings reveal that the timing difference between these two factors significantly affects flood inundation depth and extent. The most severe inundation occurs when rainfall precedes the storm surge peak by 2 h.
Wen Zhu, Tao Tao, Hexiang Yan, Jieru Yan, Jiaying Wang, Shuping Li, and Kunlun Xin
Hydrol. Earth Syst. Sci., 27, 2035–2050, https://doi.org/10.5194/hess-27-2035-2023, https://doi.org/10.5194/hess-27-2035-2023, 2023
Short summary
Short summary
To provide a possibility for early warning and forecasting of ponding in the urban drainage system, an optimized long short-term memory (LSTM)-based model is proposed in this paper. It has a remarkable improvement compared to the models based on LSTM and convolutional neural network (CNN) structures. The performance of the corrected model is reliable if the number of monitoring sites is over one per hectare. Increasing the number of monitoring points further has little impact on the performance.
Qianqian Zhou, Shuai Teng, Zuxiang Situ, Xiaoting Liao, Junman Feng, Gongfa Chen, Jianliang Zhang, and Zonglei Lu
Hydrol. Earth Syst. Sci., 27, 1791–1808, https://doi.org/10.5194/hess-27-1791-2023, https://doi.org/10.5194/hess-27-1791-2023, 2023
Short summary
Short summary
A deep-learning-based data-driven model for flood predictions in temporal and spatial dimensions, with the integration of a long short-term memory network, Bayesian optimization, and transfer learning is proposed. The model accurately predicts water depths and flood time series/dynamics for hyetograph inputs, with substantial improvements in computational time. With transfer learning, the model was well applied to a new case study and showed robust compatibility and generalization ability.
Ane LaBianca, Mette H. Mortensen, Peter Sandersen, Torben O. Sonnenborg, Karsten H. Jensen, and Jacob Kidmose
Hydrol. Earth Syst. Sci., 27, 1645–1666, https://doi.org/10.5194/hess-27-1645-2023, https://doi.org/10.5194/hess-27-1645-2023, 2023
Short summary
Short summary
The study explores the effect of Anthropocene geology and the computational grid size on the simulation of shallow urban groundwater. Many cities are facing challenges with high groundwater levels close to the surface, yet urban planning and development seldom consider its impact on the groundwater resource. This study illustrates that the urban subsurface infrastructure significantly affects the groundwater flow paths and the residence time of shallow urban groundwater.
Bianca Rahill-Marier, Naresh Devineni, and Upmanu Lall
Hydrol. Earth Syst. Sci., 26, 5685–5695, https://doi.org/10.5194/hess-26-5685-2022, https://doi.org/10.5194/hess-26-5685-2022, 2022
Short summary
Short summary
We present a new approach to modeling extreme regional rainfall by considering the spatial structure of extreme events. The developed models allow a probabilistic exploration of how the regional drainage network may respond to extreme rainfall events and provide a foundation for how future risks may be better estimated.
Matthew Preisser, Paola Passalacqua, R. Patrick Bixler, and Julian Hofmann
Hydrol. Earth Syst. Sci., 26, 3941–3964, https://doi.org/10.5194/hess-26-3941-2022, https://doi.org/10.5194/hess-26-3941-2022, 2022
Short summary
Short summary
There is rising concern in numerous fields regarding the inequitable distribution of human risk to floods. The co-occurrence of river and surface flooding is largely excluded from leading flood hazard mapping services, therefore underestimating hazards. Using high-resolution elevation data and a region-specific social vulnerability index, we developed a method to estimate flood impacts at the household level in near-real time.
Vincent Pons, Rasmus Benestad, Edvard Sivertsen, Tone Merete Muthanna, and Jean-Luc Bertrand-Krajewski
Hydrol. Earth Syst. Sci., 26, 2855–2874, https://doi.org/10.5194/hess-26-2855-2022, https://doi.org/10.5194/hess-26-2855-2022, 2022
Short summary
Short summary
Different models were developed to increase the temporal resolution of precipitation time series to minutes. Their applicability under climate change and their suitability for producing input time series for green infrastructure (e.g. green roofs) modelling were evaluated. The robustness of the model was validated against a range of European climates in eight locations in France and Norway. The future hydrological performances of green roofs were evaluated in order to improve design practice.
Elhadi Mohsen Hassan Abdalla, Vincent Pons, Virginia Stovin, Simon De-Ville, Elizabeth Fassman-Beck, Knut Alfredsen, and Tone Merete Muthanna
Hydrol. Earth Syst. Sci., 25, 5917–5935, https://doi.org/10.5194/hess-25-5917-2021, https://doi.org/10.5194/hess-25-5917-2021, 2021
Short summary
Short summary
This study investigated the potential of using machine learning algorithms as hydrological models of green roofs across different climatic condition. The study provides comparison between conceptual and machine learning algorithms. Machine learning models were found to be accurate in simulating runoff from extensive green roofs.
Yang Yang and Ting Fong May Chui
Hydrol. Earth Syst. Sci., 25, 5839–5858, https://doi.org/10.5194/hess-25-5839-2021, https://doi.org/10.5194/hess-25-5839-2021, 2021
Short summary
Short summary
This study uses explainable machine learning methods to model and interpret the statistical correlations between rainfall and the discharge of urban catchments with sustainable urban drainage systems. The resulting models have good prediction accuracies. However, the right predictions may be made for the wrong reasons as the model cannot provide physically plausible explanations as to why a prediction is made.
Zhengzheng Zhou, James A. Smith, Mary Lynn Baeck, Daniel B. Wright, Brianne K. Smith, and Shuguang Liu
Hydrol. Earth Syst. Sci., 25, 4701–4717, https://doi.org/10.5194/hess-25-4701-2021, https://doi.org/10.5194/hess-25-4701-2021, 2021
Short summary
Short summary
The role of rainfall space–time structure in flood response is an important research issue in urban hydrology. This study contributes to this understanding in small urban watersheds. Combining stochastically based rainfall scenarios with a hydrological model, the results show the complexities of flood response for various return periods, implying the common assumptions of spatially uniform rainfall in urban flood frequency are problematic, even for relatively small basin scales.
Yangzi Qiu, Igor da Silva Rocha Paz, Feihu Chen, Pierre-Antoine Versini, Daniel Schertzer, and Ioulia Tchiguirinskaia
Hydrol. Earth Syst. Sci., 25, 3137–3162, https://doi.org/10.5194/hess-25-3137-2021, https://doi.org/10.5194/hess-25-3137-2021, 2021
Short summary
Short summary
Our original research objective is to investigate the uncertainties of the hydrological responses of nature-based solutions (NBSs) that result from the multiscale space variability in both the rainfall and the NBS distribution. Results show that the intersection effects of spatial variability in rainfall and the spatial arrangement of NBS can generate uncertainties of peak flow and total runoff volume estimations in NBS scenarios.
Kaihua Guo, Mingfu Guan, and Dapeng Yu
Hydrol. Earth Syst. Sci., 25, 2843–2860, https://doi.org/10.5194/hess-25-2843-2021, https://doi.org/10.5194/hess-25-2843-2021, 2021
Short summary
Short summary
This study presents a comprehensive review of models and emerging approaches for predicting urban surface water flooding driven by intense rainfall. It explores the advantages and limitations of existing models and identifies major challenges. Issues of model complexities, scale effects, and computational efficiency are also analysed. The results will inform scientists, engineers, and decision-makers of the latest developments and guide the model selection based on desired objectives.
Everett Snieder, Karen Abogadil, and Usman T. Khan
Hydrol. Earth Syst. Sci., 25, 2543–2566, https://doi.org/10.5194/hess-25-2543-2021, https://doi.org/10.5194/hess-25-2543-2021, 2021
Short summary
Short summary
Flow distributions are highly skewed, resulting in low prediction accuracy of high flows when using artificial neural networks for flood forecasting. We investigate the use of resampling and ensemble techniques to address the problem of skewed datasets to improve high flow prediction. The methods are implemented both independently and in combined, hybrid techniques. This research presents the first analysis of the effects of combining these methods on high flow prediction accuracy.
Ico Broekhuizen, Günther Leonhardt, Jiri Marsalek, and Maria Viklander
Hydrol. Earth Syst. Sci., 24, 869–885, https://doi.org/10.5194/hess-24-869-2020, https://doi.org/10.5194/hess-24-869-2020, 2020
Short summary
Short summary
Urban drainage models are usually calibrated using a few events so that they accurately represent a real-world site. This paper compares 14 single- and two-stage strategies for selecting these events and found significant variation between them in terms of model performance and the obtained values of model parameters. Calibrating parameters for green and impermeable areas in two separate stages improved model performance in the validation period while making calibration easier and faster.
Xuehong Zhu, Qiang Dai, Dawei Han, Lu Zhuo, Shaonan Zhu, and Shuliang Zhang
Hydrol. Earth Syst. Sci., 23, 3353–3372, https://doi.org/10.5194/hess-23-3353-2019, https://doi.org/10.5194/hess-23-3353-2019, 2019
Short summary
Short summary
Urban flooding exposure is generally investigated with the assumption of stationary disasters and disaster-hit bodies during an event, and thus it cannot satisfy the increasingly elaborate modeling and management of urban floods. In this study, a comprehensive method was proposed to simulate dynamic exposure to urban flooding considering human mobility. Several scenarios, including diverse flooding types and various responses of residents to flooding, were considered.
Joong Gwang Lee, Christopher T. Nietch, and Srinivas Panguluri
Hydrol. Earth Syst. Sci., 22, 2615–2635, https://doi.org/10.5194/hess-22-2615-2018, https://doi.org/10.5194/hess-22-2615-2018, 2018
Short summary
Short summary
This paper demonstrates an approach to spatial discretization for analyzing green infrastructure (GI) using SWMM. Besides DCIA, pervious buffers should be identified for GI modeling. Runoff contributions from different spatial components and flow pathways would impact GI performance. The presented approach can reduce the number of calibration parameters and apply scale–independently to a watershed scale. Hydrograph separation can add insights for developing GI scenarios.
Elena Cristiano, Marie-Claire ten Veldhuis, Santiago Gaitan, Susana Ochoa Rodriguez, and Nick van de Giesen
Hydrol. Earth Syst. Sci., 22, 2425–2447, https://doi.org/10.5194/hess-22-2425-2018, https://doi.org/10.5194/hess-22-2425-2018, 2018
Short summary
Short summary
In this work we investigate the influence rainfall and catchment scales have on hydrological response. This problem is quite relevant in urban areas, where the response is fast due to the high degree of imperviousness. We presented a new approach to classify rainfall variability in space and time and use this classification to investigate rainfall aggregation effects on urban hydrological response. This classification allows the spatial extension of the main core of the storm to be identified.
Suresh Hettiarachchi, Conrad Wasko, and Ashish Sharma
Hydrol. Earth Syst. Sci., 22, 2041–2056, https://doi.org/10.5194/hess-22-2041-2018, https://doi.org/10.5194/hess-22-2041-2018, 2018
Short summary
Short summary
The study examines the impact of higher temperatures expected in a future climate on how rainfall varies with time during severe storm events. The results show that these impacts increase future flood risk in urban environments and that current design guidelines need to be adjusted so that effective adaptation measures can be implemented.
Stephanie Clark, Ashish Sharma, and Scott A. Sisson
Hydrol. Earth Syst. Sci., 22, 1793–1810, https://doi.org/10.5194/hess-22-1793-2018, https://doi.org/10.5194/hess-22-1793-2018, 2018
Short summary
Short summary
This study investigates global patterns relating urban river flood impacts to socioeconomic development and changing hydrologic conditions, and comparisons are provided between 98 individual cities. This paper condenses and communicates large amounts of information to accelerate the understanding of relationships between local urban conditions and global processes, and to potentially motivate knowledge transfer between decision-makers facing similar circumstances.
Abdellah Ichiba, Auguste Gires, Ioulia Tchiguirinskaia, Daniel Schertzer, Philippe Bompard, and Marie-Claire Ten Veldhuis
Hydrol. Earth Syst. Sci., 22, 331–350, https://doi.org/10.5194/hess-22-331-2018, https://doi.org/10.5194/hess-22-331-2018, 2018
Short summary
Short summary
This paper proposes a two-step investigation to illustrate the extent of scale effects in urban hydrology. First, fractal tools are used to highlight the scale dependency observed within GIS data inputted in urban hydrological models. Then an intensive multi-scale modelling work was carried out to confirm effects on model performances. The model was implemented at 17 spatial resolutions ranging from 100 to 5 m. Results allow the understanding of scale challenges in hydrology modelling.
Per Skougaard Kaspersen, Nanna Høegh Ravn, Karsten Arnbjerg-Nielsen, Henrik Madsen, and Martin Drews
Hydrol. Earth Syst. Sci., 21, 4131–4147, https://doi.org/10.5194/hess-21-4131-2017, https://doi.org/10.5194/hess-21-4131-2017, 2017
Elena Cristiano, Marie-Claire ten Veldhuis, and Nick van de Giesen
Hydrol. Earth Syst. Sci., 21, 3859–3878, https://doi.org/10.5194/hess-21-3859-2017, https://doi.org/10.5194/hess-21-3859-2017, 2017
Short summary
Short summary
In the last decades, new instruments were developed to measure rainfall and hydrological processes at high resolution. Weather radars are used, for example, to measure how rainfall varies in space and time. At the same time, new models were proposed to reproduce and predict hydrological response, in order to prevent flooding in urban areas. This paper presents a review of our current knowledge of rainfall and hydrological processes in urban areas, focusing on their variability in time and space.
Chiara Arrighi, Hocine Oumeraci, and Fabio Castelli
Hydrol. Earth Syst. Sci., 21, 515–531, https://doi.org/10.5194/hess-21-515-2017, https://doi.org/10.5194/hess-21-515-2017, 2017
Short summary
Short summary
In developed countries, the majority of fatalities during floods occurs as a consequence of inappropriate high-risk behaviour such as walking or driving in floodwaters. This work addresses pedestrians' instability in floodwaters. It analyses both the contribution of flood and human physical characteristics in the loss of stability highlighting the key role of subject height (submergence) and flow regime. The method consists of a re-analysis of experiments and numerical modelling.
Hjalte Jomo Danielsen Sørup, Stylianos Georgiadis, Ida Bülow Gregersen, and Karsten Arnbjerg-Nielsen
Hydrol. Earth Syst. Sci., 21, 345–355, https://doi.org/10.5194/hess-21-345-2017, https://doi.org/10.5194/hess-21-345-2017, 2017
Short summary
Short summary
In this study we propose a methodology changing present-day precipitation time series to reflect future changed climate. Present-day time series have a much finer resolution than what is provided by climate models and thus have a much broader application range. The proposed methodology is able to replicate most expectations of climate change precipitation. These time series can be used to run fine-scale hydrological and hydraulic models and thereby assess the influence of climate change on them.
Tsun-Hua Yang, Gong-Do Hwang, Chin-Cheng Tsai, and Jui-Yi Ho
Hydrol. Earth Syst. Sci., 20, 4731–4745, https://doi.org/10.5194/hess-20-4731-2016, https://doi.org/10.5194/hess-20-4731-2016, 2016
Short summary
Short summary
Taiwan continues to suffer from floods. This study proposes the integration of rainfall thresholds and ensemble precipitation forecasts to provide probabilistic urban inundation forecasts. Utilization of ensemble precipitation forecasts can extend forecast lead times to 72 h, preceding peak flows and allowing response agencies to take necessary preparatory measures. This study also develops a hybrid of real-time observation and rainfall forecasts to improve the first 24 h inundation forecasts.
Christopher A. Sanchez, Benjamin L. Ruddell, Roy Schiesser, and Venkatesh Merwade
Hydrol. Earth Syst. Sci., 20, 1289–1299, https://doi.org/10.5194/hess-20-1289-2016, https://doi.org/10.5194/hess-20-1289-2016, 2016
Short summary
Short summary
The use of authentic learning activities is especially important for place-based geosciences like hydrology, where professional breadth and technical depth are critical for practicing hydrologists. The current study found that integrating computerized learning content into the learning experience, using only a simple spreadsheet tool and readily available hydrological data, can effectively bring the "real world" into the classroom and provide an enriching educational experience.
G. Bruni, R. Reinoso, N. C. van de Giesen, F. H. L. R. Clemens, and J. A. E. ten Veldhuis
Hydrol. Earth Syst. Sci., 19, 691–709, https://doi.org/10.5194/hess-19-691-2015, https://doi.org/10.5194/hess-19-691-2015, 2015
P. Licznar, C. De Michele, and W. Adamowski
Hydrol. Earth Syst. Sci., 19, 485–506, https://doi.org/10.5194/hess-19-485-2015, https://doi.org/10.5194/hess-19-485-2015, 2015
J. Herget, T. Roggenkamp, and M. Krell
Hydrol. Earth Syst. Sci., 18, 4029–4037, https://doi.org/10.5194/hess-18-4029-2014, https://doi.org/10.5194/hess-18-4029-2014, 2014
F. Beck and A. Bárdossy
Hydrol. Earth Syst. Sci., 17, 4851–4863, https://doi.org/10.5194/hess-17-4851-2013, https://doi.org/10.5194/hess-17-4851-2013, 2013
D. H. Trinh and T. F. M. Chui
Hydrol. Earth Syst. Sci., 17, 4789–4801, https://doi.org/10.5194/hess-17-4789-2013, https://doi.org/10.5194/hess-17-4789-2013, 2013
J. Y. Wu, J. R. Thompson, R. K. Kolka, K. J. Franz, and T. W. Stewart
Hydrol. Earth Syst. Sci., 17, 4743–4758, https://doi.org/10.5194/hess-17-4743-2013, https://doi.org/10.5194/hess-17-4743-2013, 2013
H. Ozdemir, C. C. Sampson, G. A. M. de Almeida, and P. D. Bates
Hydrol. Earth Syst. Sci., 17, 4015–4030, https://doi.org/10.5194/hess-17-4015-2013, https://doi.org/10.5194/hess-17-4015-2013, 2013
Y. Seo, N.-J. Choi, and A. R. Schmidt
Hydrol. Earth Syst. Sci., 17, 3473–3483, https://doi.org/10.5194/hess-17-3473-2013, https://doi.org/10.5194/hess-17-3473-2013, 2013
J. Epting, F. Händel, and P. Huggenberger
Hydrol. Earth Syst. Sci., 17, 1851–1869, https://doi.org/10.5194/hess-17-1851-2013, https://doi.org/10.5194/hess-17-1851-2013, 2013
H.-Y. Shen and L.-C. Chang
Hydrol. Earth Syst. Sci., 17, 935–945, https://doi.org/10.5194/hess-17-935-2013, https://doi.org/10.5194/hess-17-935-2013, 2013
M. H. Spekkers, M. Kok, F. H. L. R. Clemens, and J. A. E. ten Veldhuis
Hydrol. Earth Syst. Sci., 17, 913–922, https://doi.org/10.5194/hess-17-913-2013, https://doi.org/10.5194/hess-17-913-2013, 2013
J. J. Lian, K. Xu, and C. Ma
Hydrol. Earth Syst. Sci., 17, 679–689, https://doi.org/10.5194/hess-17-679-2013, https://doi.org/10.5194/hess-17-679-2013, 2013
H. T. L. Huong and A. Pathirana
Hydrol. Earth Syst. Sci., 17, 379–394, https://doi.org/10.5194/hess-17-379-2013, https://doi.org/10.5194/hess-17-379-2013, 2013
S. Oraei Zare, B. Saghafian, and A. Shamsai
Hydrol. Earth Syst. Sci., 16, 4531–4542, https://doi.org/10.5194/hess-16-4531-2012, https://doi.org/10.5194/hess-16-4531-2012, 2012
R. Archetti, A. Bolognesi, A. Casadio, and M. Maglionico
Hydrol. Earth Syst. Sci., 15, 3115–3122, https://doi.org/10.5194/hess-15-3115-2011, https://doi.org/10.5194/hess-15-3115-2011, 2011
Y.-M. Chiang, L.-C. Chang, M.-J. Tsai, Y.-F. Wang, and F.-J. Chang
Hydrol. Earth Syst. Sci., 15, 185–196, https://doi.org/10.5194/hess-15-185-2011, https://doi.org/10.5194/hess-15-185-2011, 2011
I. Andrés-Doménech, J. C. Múnera, F. Francés, and J. B. Marco
Hydrol. Earth Syst. Sci., 14, 2057–2072, https://doi.org/10.5194/hess-14-2057-2010, https://doi.org/10.5194/hess-14-2057-2010, 2010
Yen-Ming Chiang, Li-Chiu Chang, Meng-Jung Tsai, Yi-Fung Wang, and Fi-John Chang
Hydrol. Earth Syst. Sci., 14, 1309–1319, https://doi.org/10.5194/hess-14-1309-2010, https://doi.org/10.5194/hess-14-1309-2010, 2010
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: Large-Scale Machine Learning on Heterogeneous Systems, https://www.tensorflow.org (last access: 10 October 2023), 2015. a
Ahmed, F., Moors, E., Khan, M. S. A., Warner, J., and van Scheltinga, C. T.: Tipping points in adaptation to urban flooding under climate change and urban growth: The case of the Dhaka megacity, Land Use Policy, 79, 496–506, https://doi.org/10.1016/j.landusepol.2018.05.051, 2018. a
Alsubaie, N., Shaban, M., Snead, D., Khurram, A., and Rajpoot, N.: A multi-resolution deep learning framework for lung adenocarcinoma growth pattern classification, Comm. Com. Inf. Sc., 894, 3–11, https://doi.org/10.1007/978-3-319-95921-4_1, 2018. a
Barnes, R.: RichDEM: Terrain Analysis Software, http://github.com/r-barnes/richdem (last access: 10 October 2023), 2016. a
BenTaieb, A., Li-Chang, H., Huntsman, D., and Hamarneh, G.: A structured latent model for ovarian carcinoma subtyping from histopathology slides, Med. Image Anal., 39, 194–205, https://doi.org/10.1016/j.media.2017.04.008, 2017. a
Bentivoglio, R., Isufi, E., Jonkman, S. N., and Taormina, R.: Deep learning methods for flood mapping: a review of existing applications and future research directions, Hydrol. Earth Syst. Sci., 26, 4345–4378, https://doi.org/10.5194/hess-26-4345-2022, 2022. a, b
Berkhahn, S. and Neuweiler, I.: Data driven real-time prediction of urban floods with spatial and temporal distribution, J. Hydro. X, 22, 100167, https://doi.org/10.1016/j.hydroa.2023.100167, 2024. a, b
Berndtsson, R., Becker, P., Persson, A., Aspegren, H., Haghighatafshar, S., Jönsson, K., Larsson, R., Mobini, S., Mottaghi, M., Nilsson, J., Nordström, J., Pilesjö, P., Scholz, M., Sternudd, C., Sörensen, J., and Tussupova, K.: Drivers of changing urban flood risk: A framework for action, J. Environ. Manage., 240, 47–56, https://doi.org/10.1016/j.jenvman.2019.03.094, 2019. a
Cache, T. and Gomez, M. S.: Context-Aware Data-Driven Urban Flood Model, https://doi.org/10.5281/zenodo.10688079, 2024. a
Dallan, E., Marra, F., Fosser, G., Marani, M., Formetta, G., Schär, C., and Borga, M.: How well does a convection-permitting regional climate model represent the reverse orographic effect of extreme hourly precipitation?, Hydrol. Earth Syst. Sci., 27, 1133–1149, https://doi.org/10.5194/hess-27-1133-2023, 2023. a
do Lago, C. A., Giacomoni, M. H., Bentivoglio, R., Taormina, R., Gomes, M. N., and Mendiondo, E. M.: Generalizing rapid flood predictions to unseen urban catchments with conditional generative adversarial networks, J. Hydrol., 618, 129276, https://doi.org/10.1016/j.jhydrol.2023.129276, 2023. a, b, c
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., and Bengio, S.: Why Does Unsupervised Pre-training Help Deep Learning?, J. Mach. Learn. Res., 11, 625–660, 2010. a
Fowler, H. J., Lenderink, G., Prein, A. F., Westra, S., Allan, R. P., Ban, N., Barbero, R., Berg, P., Blenkinsop, S., Do, H. X., Guerreiro, S., Haerter, J. O., Kendon, E. J., Lewis, E., Schaer, C., Sharma, A., Villarini, G., Wasko, C., and Zhang, X.: Anthropogenic intensification of short-duration rainfall extremes, Nat. Rev. Earth Environ., 2, 107–122, https://doi.org/10.1038/s43017-020-00128-6, 2021. a
Fraehr, N., Wang, Q. J., Wu, W., and Nathan, R.: Supercharging hydrodynamic inundation models for instant flood insight, Nature Water, 1, 835–843, https://doi.org/10.1038/s44221-023-00132-2, 2023. a
Glorot, X. and Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks, https://proceedings.mlr.press/v9/glorot10a.html (last access: 28 February 2024), 2010. a
Guidolin, M., Chen, A. S., Ghimire, B., Keedwell, E. C., Djordjević, S., and Savić, D. A.: A weighted cellular automata 2D inundation model for rapid flood analysis, Environ. Modell. Softw., 84, 378–394, https://doi.org/10.1016/J.ENVSOFT.2016.07.008, 2016. a
Guo, Z.: Simulation data and source code for data-driven flood emulation of urban flood, Tech. rep., ETH Zurich, https://doi.org/10.3929/ethz-b-000365484, 2019. a
Han, J. Y. and Baik, J. J.: A theoretical and numerical study of urban heat island-induced circulation and convection, J. Atmos. Sci., 65, 1859–1877, https://doi.org/10.1175/2007JAS2326.1, 2008. a
Hirsch, R. M.: A Perspective on nonstationarity and water management, J. Am. Water Resour. As., 47, 436–446, https://doi.org/10.1111/j.1752-1688.2011.00539.x, 2011. a
Hollis, G. E.: The effect of urbanization on floods of different recurrence interval, Water Resour. Res., 11, 431–435, https://doi.org/10.1029/wr011i003p00431, 1975. a
Houston, D., Werritty, A., Bassett, D., Geddes, A., Hoolachan, A., and Mcmillan, M.: Pluvial (rain-related) flooding in urban areas: the invisible hazard, https://www.jrf.org.uk (last access: 28 February 2024), 2011. a
Huang, J., Fatichi, S., Mascaro, G., Manoli, G., and Peleg, N.: Intensification of sub-daily rainfall extremes in a low-rise urban area, Urban Climate, 42, 101124, https://doi.org/10.1016/j.uclim.2022.101124, 2022. a
IPCC: Impacts of 1.5 °C Global Warming on Natural and Human Systems, Cambridge University Press, 175–312, https://doi.org/10.1017/9781009157940.005, 2022. a, b
Kingma, D. P. and Ba, J. L.: Adam: A Method for Stochastic Optimization, 3rd International Conference on Learning Representations, ICLR 2015 – Conference Track Proceedings, arXiv [preprint], https://doi.org/10.48550/arxiv.1412.6980, 2014. a
Kourtis, I. M. and Tsihrintzis, V. A.: Adaptation of urban drainage networks to climate change: A review, Sci. Total Environ., 771, 145431, https://doi.org/10.1016/j.scitotenv.2021.145431, 2021. a
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089–5110, https://doi.org/10.5194/hess-23-5089-2019, 2019. a, b
Kundzewicz, Z. W. and Pińskwar, I.: Are Pluvial and Fluvial Floods on the Rise?, Water-Sui, 14, 2612 pp., https://doi.org/10.3390/w14172612, 2022. a
Kundzewicz, Z. W., Kanae, S., Seneviratne, S. I., Handmer, J., Nicholls, N., Peduzzi, P., Mechler, R., Bouwer, L. M., Arnell, N., Mach, K., Muir-Wood, R., Brakenridge, G. R., Kron, W., Benito, G., Honda, Y., Takahashi, K., and Sherstyukov, B.: Flood risk and climate change: global and regional perspectives, Hydrolog. Sci. J., 59, 1–28, https://doi.org/10.1080/02626667.2013.857411, 2014. a, b
Leopold, L. B.: Hydrology for Urban land Planning – A Guidebook on the Hydrologic Effects of Urban Land Use, vol. 554, Geological Survey Circular 554, US Geological Survey, https://doi.org/10.3133/cir554, 1968. a, b
Li, Y., Fowler, H. J., Argüeso, D., Blenkinsop, S., Evans, J. P., Lenderink, G., Yan, X., Guerreiro, S. B., Lewis, E., and Li, X. F.: Strong Intensification of Hourly Rainfall Extremes by Urbanization, Geophys. Res. Lett., 47, e2020GL088758, https://doi.org/10.1029/2020GL088758, 2020. a
Liu, W., Li, Q., Lin, X., Yang, W., He, S., and Yu, Y.: Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement, Int. J. Comput. Vision, 1–18 pp., https://doi.org/10.1007/s11263-024-02045-3, 2024. a, b
Liang, P. and Ding, Y.: The long-term variation of extreme heavy precipitation and its link to urbanization effects in Shanghai during 1916–2014, Adv. Atmos. Sci., 34, 321–334, https://doi.org/10.1007/s00376-016-6120-0, 2017. a
Marra, F., Zoccatelli, D., Armon, M., and Morin, E.: A simplified MEV formulation to model extremes emerging from multiple nonstationary underlying processes, Adv. Water Resour., 127, 280–290, https://doi.org/10.1016/j.advwatres.2019.04.002, 2019. a
Marra, F., Koukoula, M., Canale, A., and Peleg, N.: Predicting extreme sub-hourly precipitation intensification based on temperature shifts, Hydrol. Earth Syst. Sci., 28, 375–389, https://doi.org/10.5194/hess-28-375-2024, 2024. a
Miller, J. D. and Hutchins, M.: The impacts of urbanisation and climate change on urban flooding and urban water quality: A review of the evidence concerning the United Kingdom, J. Hydrol. Reg. Stud., 12, 345–362, https://doi.org/10.1016/j.ejrh.2017.06.006, 2017. a
Miller, J. D., Kim, H., Kjeldsen, T. R., Packman, J., Grebby, S., and Dearden, R.: Assessing the impact of urbanization on storm runoff in a peri-urban catchment using historical change in impervious cover, J. Hydrol., 515, 59–70, https://doi.org/10.1016/j.jhydrol.2014.04.011, 2014. a
Mou, L., Hua, Y., and Zhu, X. X.: Relation Matters: Relational Context-Aware Fully Convolutional Network for Semantic Segmentation of High-Resolution Aerial Images, IEEE T. Geosci. Remote, 58, 7557–7569, https://doi.org/10.1109/TGRS.2020.2979552, 2020. a
Moy de Vitry, M., Kramer, S., Wegner, J. D., and Leitão, J. P.: Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network, Hydrol. Earth Syst. Sci., 23, 4621–4634, https://doi.org/10.5194/hess-23-4621-2019, 2019. a
Nearing, G. S., Kratzert, F., Sampson, A. K., Pelissier, C. S., Klotz, D., Frame, J. M., Prieto, C., and Gupta, H. V.: What Role Does Hydrological Science Play in the Age of Machine Learning?, Water Resour. Res., 57, e2020WR028091, https://doi.org/10.1029/2020WR028091, 2021. a, b
Peduzzi, P., Chatenoux, B., Dao, H., Bono, A. D., Herold, C., Kossin, J., Mouton, F., and Nordbeck, O.: Global trends in tropical cyclone risk, Nat. Clim. Change, 2, 289–294, https://doi.org/10.1038/nclimate1410, 2012. a
Peleg, N., Blumensaat, F., Molnar, P., Fatichi, S., and Burlando, P.: Partitioning the impacts of spatial and climatological rainfall variability in urban drainage modeling, Hydrol. Earth Syst. Sci., 21, 1559–1572, https://doi.org/10.5194/hess-21-1559-2017, 2017. a
Peleg, N., Ban, N., Gibson, M. J., Chen, A. S., Paschalis, A., Burlando, P., and Leitão, J. P.: Mapping storm spatial profiles for flood impact assessments, Adv. Water Resour., 166, 104258, https://doi.org/10.1016/j.advwatres.2022.104258, 2022. a
Romano, Y. and Elad, M.: Con-Patch: When a Patch Meets its Context, IEEE, https://doi.org/10.1109/TIP.2016.2576402, 2016. a
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th international conference, Munich, Germany, 5–9 October 2015, proceedings, part III 18, edited by: Navab, N., Hornegger, J., Wells, W. M., and Frangi, A. F., Springer, https://doi.org/10.1007/978-3-319-24574-4_28, 2015. a
Rosenzweig, B. R., McPhillips, L., Chang, H., Cheng, C., Welty, C., Matsler, M., Iwaniec, D., and Davidson, C. I.: Pluvial flood risk and opportunities for resilience, WIRes Water, Wiley Online Library, 5, e1302, https://doi.org/10.1002/wat2.1302, 2018. a
Semadeni-Davies, A., Hernebring, C., Svensson, G., and Gustafsson, L. G.: The impacts of climate change and urbanisation on drainage in Helsingborg, Sweden: Suburban stormwater, J. Hydrol., 350, 114–125, https://doi.org/10.1016/j.jhydrol.2007.11.006, 2008. a
Shaban, M., Awan, R., Fraz, M. M., Azam, A., Snead, D., and Rajpoot, N. M.: Context-Aware Convolutional Neural Network for Grading of Colorectal Cancer Histology Images, IEEE transactions on medical imaging, 39, 295–2405, https://doi.org/10.1109/TMI.2020.2971006, 2020. a
Sirinukunwattana, K., Alham, N. K., Verrill, C., and Rittscher, J.: Improving Whole Slide Segmentation Through Visual Context – A Systematic Study, in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, edited by: Frangi, A. F., Schnabel, J. A., Davatzikos, C., Alberola-López, C., and Fichtinger, G., Springer International Publishing, Cham, 192–200, https://doi.org/10.1007/978-3-030-00934-2_22, 2018. a
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. a, b
Tabari, H., Madani, K., and Willems, P.: The contribution of anthropogenic influence to more anomalous extreme precipitation in Europe, Environ. Res. Lett., 15, 104077, https://doi.org/10.1088/1748-9326/abb268, 2020. a
tcache1: context_aware_flood_model, GitHub, https://github.com/tcache1/context_aware_flood_model (last access: 28 February 2024), 2024.
UN: World Urbanization Prospects: The 2018 Revision, United Nations, ISBN 9789211483192, 2018. a
Willems, P., Arnbjerg-Nielsen, K., Olsson, J., and Nguyen, V. T.: Climate change impact assessment on urban rainfall extremes and urban drainage: Methods and shortcomings, Atmos. Res., 103, 106–118, https://doi.org/10.1016/j.atmosres.2011.04.003, 2012. a
Winsemius, H. C., Aerts, J., van Beek, L., Bierkens, M., Bouwman, A., Jongman, B., Kwadijk, J., Ligtvoet, W., Lucas, P., van Vuuren, D., and Ward, P. J.: Global drivers of Future River Flood Risk, Nat. Clim. Change, 6, 381–385, https://doi.org/10.1038/nclimate2893, 2016. a
Zhang, Y., Ragettli, S., Molnar, P., Fink, O., and Peleg, N.: Generalization of an Encoder-Decoder LSTM model for flood prediction in ungauged catchments, J. Hydrol., 614, 128577, https://doi.org/10.1016/j.jhydrol.2022.128577, 2022. a
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.
We introduce a new deep-learning model that addresses the limitations of existing urban flood...
