Agent-based intelligent real-time control for pluvial flood mitigation at urban scale

Quantifying socioeconomic impacts of urban pluvial flooding using social media and SDGSAT-1 nighttime light data: A case study of Kunming, China

A physically constrained proxy framework considering a process-aware gating mechanism for urban flood simulation.

Integrating MIKE model simulations with CNNs for rapid and accurate urban flood prediction

SynxFlow-based urban pluvial flood simulation and sensitivity evaluation in the central urban area of Shenzhen

An attention-based super-resolution model for high-accuracy urban pluvial flood forecasting in coastal megacities

Abstract Urban flood risk poses an escalating threat to urban safety and sustainable development amid climate change and rapid urbanization. Although various flood risk assessment methods exist, most studies rely on single analytical approaches, neglecting the advantages of methodological integration and the multifaceted nature of risk characterization. Furthermore, prevailing assessment frameworks apply uniform hydrodynamic models across entire urban areas, inadequately capturing the diverse inundation processes arising from spatial heterogeneity of urban surfaces. This research developed an integrated multi-method framework for cities exhibiting significant spatial heterogeneity in environmental, infrastructural, and socioeconomic characteristics, enabling efficient high-precision flood simulation and risk assessment by coupling the indicator system method (ISM) with the cloud model (CM). The framework comprises: (1) spatially-differentiated hydrodynamic modeling for pipeline-dense and pipeline-sparse areas; (2) entropy-analytic hierarchy process weighted grid-based flood risk assessment across multiple rainfall scenarios; and (3) cloud model-driven risk evaluation at sub-drainage functional zones to address uncertainty in assessment. The results indicate that the integrated multi-model approach effectively captures flood formation mechanisms and identify an expansion of high-risk areas. Grid-based assessment delineates fine-grained risk distribution, while the cloud model assessment reveals the stability and uncertainty of risk levels. This research advances flood risk assessment methodology by bridging sophisticated hydrodynamic modeling integration with multi-scale risk evaluation, providing a robust framework for urban flood management.

Pluvial floods can cause severe socio-economic impacts on coastal urban areas like the Metropolitan Area of Barcelona. This study combined the development of high-resolution flood maps, based on a large-scale coupled 1D/2D model and empirical functions, to quantify direct economic damage to buildings and determine risk to pedestrians and vehicles. Importantly, the flood model included a network of 36 municipalities and covered 636 km2. Three scenarios were considered: single-hazard (extreme precipitation), multi-hazard (coincident extreme precipitation and storm surge), and adaptation (implementation of resilience measures). In total, 20 rain events were applied for each scenario: 5 were historic design storms, while 15 considered the effect of climate change (60 simulations in total). By the end of the century, results show potential increases in expected annual damage of up to 36%, from €139.8 M to €190.3 M. Risk for pedestrians could increase by 25% (494 ha to 620 ha) and for vehicles by 26% (59 km to 75 km) in the T10 single-hazard scenario. In the multi-hazard case, the socio-economic impacts are approximately 5% higher, while the adaptation simulations considering sustainable urban drainage systems show reductions between 6 and 18%. The metropolitan results were compared and validated with a previous assessment done in the City of Barcelona. Based on these results, urban planners, emergency responders, and public administrations can develop effective adaptation measures based on cost–benefit analyses for current and future climate scenarios. Compared to previous studies, this approach adapts existing urban-scale methodologies to regional-scale flood risk assessment.

An integrated framework for pluvial flood and tsunami hazard assessment at coastal sites: application to cultural heritage

Abstract. The increasing frequency and intensity of extreme rainfall events present a critical global challenge for urban areas. While flood risk management has historically prioritised fluvial hazards, pluvial flooding and urban overland runoff pathways require local and global attention and scalable, community-inclusive solutions. This proof-of-concept paper presents the local-scale development and implementation of a prototype Citizen and Community Science mobile application, designed within a municipal extreme rainfall context, where both the app's testing environment and current operational scale are spatially limited to neighbourhood and city level in the Ahr valley. The prototype enables residents to document, classify, and report pluvial flood risks, while supporting community-based risk minimisation through enhanced awareness and embedded educational guidance on hazard categorisation and preventive actions. Crowdsourced observations are transferred to a Geo Data Warehouse, providing local authorities with customisable dashboards for analysis, visualisation, and decision support. Although technical constraints remain – particularly restricted offline functionality and variability in Global Navigation Satellite System accuracy – the system architecture was intentionally designed to support iterative refinement. Despite its present local application, the prototype is based on a fully open-source, modular, and scalable design, allowing international transferability and future expansion to regional, national, or global datasets and governance frameworks. This proof-of-concept thus demonstrates the global scaling potential of combining citizen-generated flood risk data with centralised geospatial infrastructure as a pathway toward more climate-resilient and participatory urban pluvial flood risk management worldwide.

This paper explores the behavioural change process initiated within the Gdańsk Coastal City Living Lab (CCLL)—a site-based effort, initiated under the H2020 SCORE project and significantly deepened through the Horizon Europe PRO-CLIMATE project—through the lens of transforming human–nature relationships for sustainable urban biodiversity conservation. While SCORE established the technical baseline for Nature-based Solutions (NbSs), PRO-CLIMATE provides the critical behavioural framework to ensure these solutions are socially adopted and sustained. Located in a flood-prone coastal city, the Gdańsk CCLL addresses the critical need for nature-based solutions (NbSs) in minimizing the negative impacts of climate change, particularly pluvial flooding. At the heart of this initiative is a participatory change process facilitated by local Change Agents in collaboration with key stakeholders across water management, local government, academia, and civil society. Drawing on interdisciplinary insights from social science, the paper uses the Nature Futures Framework to analyse how conservation actions are influenced by the relational, intrinsic, and instrumental values that stakeholders and residents attach to nature. The paper situates these values in the Gdańsk context and examines how they shape motivations and willingness to engage in urban NbS, such as green roofs, retention parks, and rainwater gardens. The study presents qualitative findings from stakeholder engagement workshops, Change Agents’ reflections, and support mechanisms from behavioural change experts. It evaluates how behavioural change was facilitated through shared vision building, feedback loops, and trust-based relationships, and how barriers were negotiated. A key contribution of the paper is the exploration of how bottom-up and top-down processes intersect in urban adaptation strategies and how behavioural change frameworks can be designed to institutionalise sustainable human–nature interactions in urban governance. The Gdańsk case offers transferable insights for other cities facing climate vulnerabilities while striving to embed biodiversity conservation into everyday practice.

Urban pluvial flooding presents growing challenges for disaster risk management, yet most susceptibility studies rely on watershed-based frameworks that inadequately capture the localized dynamics of urban systems. This study proposes a city-scale flood susceptibility modeling framework for Cincinnati, Ohio. Cincinnati was chosen because it is a city with a documented history of severe urban flooding, including a once-in-a-century storm in 2016. Multi-source historical flood data were compiled from NOAA storm event records and crowdsourced reports to enhance spatial coverage. Four machine learning algorithms (Random Forest, Support Vector Machine, XGBoost, and Logistic Regression) were implemented to identify the most effective approach for urban pluvial flood prediction. Random Forest (RF) and Support Vector Machine (SVM) achieved the highest accuracy (0.84) and demonstrated strong discriminatory power. RF was selected as the optimal model because it had a higher AUC (90%) and the lowest RMSE (0.35). To assess generalizability, the RF model was validated on updated land use data and flood records from a 2020 storm event. It demonstrated robust performance (accuracy = 0.89, RMSE = 0.36, precision = 0.75, recall = 1, and AUC = 0.95), despite urban development changes. This study’s novelty lies in combining multi-source flood records with a grid-based machine learning framework and rigorously validating model robustness under evolving urban conditions. The results advance urban pluvial flood susceptibility modeling and offer actionable guidance for evidence-based flood risk management worldwide.

Climate change and rapid urbanization are intensifying urban pluvial flooding and threatening sustainable urban development. This study proposes a three-stage, four-dimensional framework (TSFD-UPFR) to assess urban pluvial flood resilience across resistance, response, and recovery phases that integrate natural, infrastructural, social, and economic dimensions. Using a representative urban catchment affected by a typical extreme rainfall event, we couple hydrological–hydrodynamic simulations with multi-source remote sensing and socio-economic indicators at a 100 m grid resolution to enable spatially explicit assessment. The results indicate moderate overall resilience with pronounced spatial heterogeneity. Resistance is primarily constrained by drainage capacity and impervious surfaces, response is shaped by road connectivity and public service accessibility, and recovery is determined by essential facility restoration and economic support. Low-resilience clusters are concentrated in dense built-up areas and transport hubs, revealing structural weaknesses in adaptive capacity. By linking flood processes with socio-economic recovery dynamics, the framework captures cross-stage interactions within urban systems. The findings support climate-adaptive planning, targeted infrastructure investment, and resilience-oriented governance, contributing to sustainable and equitable urban transformation in megacities facing intensifying extreme rainfall.

The escalating frequency of extreme rainfall events necessitates scalable and dynamic tools for urban flood risk assessment. The primary objective of this study is to demonstrate and evaluate how a machine-learning–derived building-level pluvial flood susceptibility index can be operationalised through multi-resolution aggregation using the H3 Hexagonal Discrete Global Grid System (DGGS). The study builds on the building-level Pluvial Flood Index ( PFI b ) developed in the InzureFlood project, which derives susceptibility from historical insurance damage patterns and geospatial predictors. In the proposed methodology, the analysis domain is partitioned using H3, and building-level scores are aggregated within hexagonal cells to produce a scalable hexagon-level index ( PFI h ). Results indicate that this grid-based approach substantially improves computational efficiency, reducing spatial query operations by approximately 98% compared to traditional geometry-based workflows. The resulting maps show spatial patterns that are qualitatively consistent with expected topographic controls, such as depressions and flow paths. However, quantitative analysis of resolution effects reveals a critical trade-off: while overall susceptibility levels are preserved, aggregation increasingly smooths local extremes. A Jaccard Similarity Index of 0.14 between street-level (R13) and neighborhood-level (R10) hotspots indicates that most fine-scale susceptibility hotspots are not visible at intermediate scales. These findings imply that coarser resolutions may support regional strategic screening, whereas high-resolution grids are necessary for safety-critical tasks such as emergency response and local mitigation. The framework provides a scalable and updateable representation that supports consistent multi-scale communication from micro-scale screening to macro-scale planning.

In urban pluvial flood risk management, local authorities and local collectives (e.g. citizen groups) increasingly rely on each other's contributions to develop on-the-ground solutions, thereby creating an interdependent relationship. Although it is known that these interdependencies can be beneficial, most studies have focused on interaction processes between local authorities and local collectives, paying less attention to the underlying interdependencies. This study explores how interdependencies influence flood risk management by analysing two neighbourhood-level projects in the Netherlands: Oase Noord (Oasis North) in Amsterdam, which is characterised by a shared governance model, and Dakpark (Roof Park) in Rotterdam, which reflects a self-governance approach. Interviews were held with local authorities and local collectives from the two cases, and experts involved in similar projects. Our analysis demonstrates that interdependencies can benefit collaborative processes for developing integrated pluvial flood risk management strategies, and their forms are by and large similar in shared governance and self-governance. Our empirical findings also highlight institutional challenges in recognising and using interdependencies, particularly the absence of consistent government support across both approaches. This study underscores the interdependencies between local authorities and communities and the ability of citizens to take their part in the responsibility to manage flood risks and other climate-related transitions. • Interdependency enables mutual benefits for authorities and collectives in interconnected flood-societal challenges. • Government support is key to maintain the collaboration between authorities and collectives. • However, the continuity of government support is often lacking in practice. • Neutral neighbourhood managers and mediators can enhance authority–collective collaboration.

Ready for the flood? Assessing the applicability of pluvial flood mapping based on the worst urban flood in Sweden

Urban pluvial flood susceptibility assessment for the central Lin’an District in Hangzhou, China, using the GNNWLR model with SHAP interpretability

Abstract Urban pluvial floods have become increasingly frequent under the combined effects of climate change and urbanization, leading to increased disaster losses. This study developed a data-driven urban pluvial flood prediction model using convolutional neural networks (CNNs) to enhance computational efficiency while maintaining simulation accuracy. A high-resolution cellular-based flood model generated the training dataset through systematic patch-based sampling combined with fixed step size selection strategies. The established framework enabled flood simulations through integrated analysis of topographic features and rainfall processes. Shapley additive explanations (SHAP) and Group masking analysis (GMA) were implemented to interpret the decision-making mechanisms of CNN model. The model was validated in a relatively independent drainage area, demonstrating strong agreement with conventional cellular model outputs across six design storm scenarios and two historical rainfall events. Computational experiments showed that the CNN model reduced simulation time from minutes to seconds compared to process-based approaches, while maintaining low absolute errors in water depth predictions. Both SHAP and GMA interpretation revealed that topographic features, particularly building, digital elevation model (DEM), and aspect, exert dominant influence on model predictions. This data-driven framework established an efficient computational paradigm for urban flood modeling, with SHAP and GMA analysis guiding input variable selection while explaining model behavior. The methodology demonstrated potential for real-time monitoring integration, supporting rapid flood risk assessment and resilience enhancement.

Aim of the study The study aims to simulate the extent and depth of fluvial and pluvial flooding under different scenarios using the 2D hydraulic MIKE+ model in combination with geographic information systems (GIS). Material and methods As for the fluvial floods, we used steady-state flow conditions for three flood scenarios (Q10, Q100, and Q1000). The modeled flood maps were compared to official flood maps created under the second cycle of EU Floods Directive (2007). Regarding the pluvial flooding, we used the rain-on-grid method, where the rainfall input was set to three constant intensities (20, 40, and 60 mm/hour) under two scenarios: fully saturated soils and infiltration losses. Study area was the Teplica River section (3.68 km) in western Slovakia. Results and conclusions Based on the results, the flood extent difference against the official flood maps was 0.009, 0.075, and 0.123 km2 for Q10, Q100, and Q1000, respectively. In case of 20, 40, and 60 mm/hour rainfall scenarios and fully saturated soils, 13.5, 22.1, and 29.2% of the domain, respectively, had flow depths between 0.005-0.1 m while 2.0, 4.2, and 6.1% of the domain had flow depths above 0.1 m. In case of 20, 40, and 60 mm/hour rainfall scenarios with infiltration losses, 6.0, 14.6, and 22.7% of the domain, respectively, had flow depths between 0.005-0.1 m while 0.4, 2.5, and 4.5% of the domain had flow depths above 0.1 m. When the infiltration rates of land cover classes are applied, pluvial flood extent decreases by 58.2%, 34.4%, and 23.2% for the 20, 40, and 60 mm/hour rainfall scenario, respectively.

Urban underground infrastructures are highly vulnerable to intense rainfall events, particularly access stairs, where preferential runoff paths and the most probable evacuation routes can conflict. This study presents a pluvial flood hazard assessment for underground access stairs in the Barcelona Metropolitan Area Metro network. It integrates the EU ICARIA project modeling framework and the hazard assessment criteria based on hydraulic parameters identified by the Spanish national research project FAVOUR. Both current and future climate change rainfall scenarios are considered. The results showed that out of 415 underground access points, 27 face a high risk of floods, while 35 more have potentially high-risk conditions. These figures could rise to 38 (40% increase) and 47 (74% increase) respectively by the end of the century since climate change is projected to increase rainfall intensity and frequency. By quantifying hazard levels across the network, this study allows the identification of points of the infrastructure where hazard conditions can be more critical. Furthermore, the results presented could potentially support targeted adaptation strategies such as entrance retrofitting, improved drainage design, and emergency planning to develop resilient and sustainable cities. The proposed methodology demonstrates how ICARIA’s modeling framework can effectively evaluate and anticipate flood hazards in complex urban environments at the asset level.