Flood Hotspots Research Articles

Urban Flooding Disaster Risk Assessment Utilizing the MaxEnt Model and Game Theory: A Case Study of Changchun, China

This research employs the maximum entropy (MaxEnt) model alongside game theory, integrated with an extensive framework of natural disaster risk management theory, to conduct a thorough analysis of the indicator factors related to urban flooding. This study conducts an assessment of the risks associated with urban flooding disasters using Changchun city as a case study. The validation outcomes pertaining to urban flooding hotspots reveal that 88.66% of the identified flooding sites are situated within areas classified as high-risk and very high-risk. This finding is considered to be more reliable and justifiable when contrasted with the 77.73% assessment results derived from the MaxEnt model. Utilizing the methodology of exploratory spatial data analysis (ESDA), this study applies both global and local spatial autocorrelation to investigate the disparities in the spatial patterns of flood risk within Changchun. This study concludes that urban flooding occurs primarily in the city center of Changchun and shows a significant agglomeration effect. The region is economically developed, with a high concentration of buildings and a high percentage of impervious surfaces. The Receiver Operating Characteristic (ROC) curve demonstrates that the MaxEnt model achieves an accuracy of 90.3%. On this basis, the contribution of each indicator is analyzed and ranked using the MaxEnt model. The primary determinants affecting urban flooding in Changchun are identified as impervious surfaces, population density, drainage density, maximum daily precipitation, and the Normalized Difference Vegetation Index (NDVI), with respective contributions of 20.6%, 18.1%, 13.1%, 9.6%, and 8.5%. This research offers a scientific basis for solving the urban flooding problem in Changchun city, as well as a theoretical reference for early warnings for urban disaster, and is conducive to the realization of sustainable urban development.

Smart hotspot detection using geospatial artificial intelligence: A machine learning approach to reduce flood risk

This study employs Geospatial Artificial Intelligence (GeoAI) and the Random Forest Machine Learning (ML) algorithm to enhance flood hazard assessments in Portugal. It utilizes NASA's LP DAAC (2023) Digital Elevation Model (DEM) and slope data from EPIC WEBGIS PORTUGAL DATA, offering detailed topographical insights for environmental planning. Additionally, it incorporates data on proximity to water bodies from the Portuguese Environment Agency and the European Environment Agency, and soil characteristics from EPIC WEBGIS PORTUGAL DATA, facilitating a thorough examination of flood risks. This approach prioritizes long-term land features over short-term weather patterns, providing a comprehensive understanding of flood vulnerability. The study processes data at a 1 km x 1 km resolution, adapting TIFF maps for compatibility with the Random Forest model. The produced flood hazard maps identify potential flood hotspots at both national and city levels, crucial for urban planning. These maps aid in assessing the vulnerability of key infrastructure and assets, such as transport networks and buildings. The research highlights the importance of integrating additional data on assets and socioeconomic factors to enhance urban resilience. It sets the stage for future research aimed at improving predictive accuracy and underscores the necessity of extensive geospatial analytics in managing infrastructure risks.

An integrated urban flooding risk analysis framework leveraging machine learning models: A case study of Xi'an, China

As global climate change intensifies and urbanization progresses, the frequency and extent of urban flooding have been increasing. This trend poses a significant threat to the safety and property of urban residents and severely impedes the advancement of sustainable development goals (SDGs). This study proposed an integrated urban flooding risk analysis framework to provide an essential basis for developing effective adaptation and mitigation measures. The kernel density estimation was adopted to analyze the distribution characteristics of urban flooding hotspots. The maximum entropy (MaxEnt) model was adopted for urban flooding risk probability assessment based on multi-source data. This study conducted an in-depth analysis from three perspectives including spatial analysis, risk planning and model comparison. The MaxEnt model and multiple exploratory spatial data analysis methods were combined to reveal spatial distribution patterns at grid cell scale. The MaxEnt and Zonation models were coupled to generate an urban flooding risk map. Further, six traditional machine learning models were compared with the MaxEnt model. The results indicate that rapid urbanization and intense human activities have significantly increased the number of buildings, leading to loss of previously existing blue and green spaces. These urban characteristics increase the vulnerability of cities to extreme rainfall. Compared to traditional machine learning models, the MaxEnt model has significant advantages. In the field of urban flooding risk, the MaxEnt model demonstrates significant potential for practical application. In summary, the framework empowers urban managers to comprehensively evaluate flooding risk in planning, supporting urban design and risk prevention.

A geospatial perspective of flood risk hotspots, transport networks and emergency response services in Accra, Ghana

ABSTRACT This paper adds to existing knowledge about flood management in Accra and contributes insights into emergency responses to major flood events in a geospatial context. The study identifies and analyses the specific routes from the facilities of emergency responders to designated flood-prone areas within four sites in the peripheral areas of the Greater Accra Metropolitan Area. Flood hotspots were ascertained from several sources including local knowledge and bluespot maps derived from a 10 m resolution elevation model. GIS-based network analysis was used to determine the fastest routes from emergency responder facilities to flood hotspots, based on OpenStreetMap data. Interviews revealed that the computed routes are unsuitable for emergency services due to narrow passages and prevailing conditions during the floods. It is necessary to incorporate the individual responder’s knowledge gained through familiarization with the local terrain to identify the optimal routes. The study further analysed the accessibility of emergency response services using indicative service area maps that present an account of time-distance from various emergency responders’ bases. Finally, the study recommends the need for better planning of the expanding areas of the Greater Accra Metropolitan Area, in terms of accessibility for emergency responders.

Interpretable machine learning for predicting urban flash flood hotspots using intertwined land and built-environment features

Pluvial flash floods are fast-moving hazards and causes significant disruptions in urban areas. With the increase in heavy precipitations, the ability to proactively identify flash floods hotspots in cities is critical for flood nowcasting and predictive monitoring of risks. While rainfall runoff models and hydrologic models are useful models for flash flood prediction, these models are computationally expensive and effort intensive to be used for flood nowcasting. To address this challenge, this study presents interpretable machine learning models for predicting urban flash flood hotspots based on intertwined land and built environment features. The task of predicting flash flood hotspots is formulated as a binary classification problem, and three recent flash flood events in U.S. cities are selected for data collection and model validation. Various features related to land and built environment characteristics are constructed using diverse datasets, and the occurrences of flash floods are captured using crowdsource data from the events. Using these features and datasets, the flash flood hotspots of cities are predicted with two ensemble models based on decision trees. The results demonstrate that the models can achieve good accuracy (0.8) in identifying flooded/non-flooded locations. Especially, the models can achieve high true positive rate (0.83–0.89) and low missing rate, demonstrating the methods' practicability for accurately predicting flooded hotspots. The model interpretation results indicate that land features related to hydrological and topological features have greater impacts on flash flood risk, than built environment features. Further analysis reveals that the feature importance, model performance, and model transferability performance vary among cities and localized specifications of the models are needed for accurate prediction of flash flood for a particular city. The data-driven machine learning models presented in this study provide a useful tool for predicting flash flood hotspots based on the intertwined features of land and the built environment in cities to enable nowcasting and proactive monitoring of flash flood hotspots for emergency response and also inform integrated urban design and development towards flash flood risk reduction.

Integrating multi-criteria analysis and geospatial applications for mapping flood hazards in Sekondi-Takoradi Metropolis, Ghana

Despite numerous structural and non-structural measures to curb the problem, flood disasters have become a recurring theme globally. Reducing vulnerability to flooding requires a constant reassessment of flood hazard areas since their spatial extent keeps changing. This paper sought to map flood hazards in the Sekondi-Takoradi Metropolis (STM) of Ghana. STM experiences frequent flooding incidents, rapid urbanization, and massive encroachment of lands, partly due to a booming petroleum industry. However, an empirical spatial assessment of its flood hotspots is non-existent. We applied a multi-criteria analysis (specifically the Analytical Hierarchy Process [AHP]) to address this issue by processing causative flood parameters derived from remotely sensed images using a geographical information system. The principal results show that about 12% and 24% of STM lands are in very high and high flood zones, respectively. The rest of the land is in moderate (24.6%), low (24.3%), and very low (15%) flood zones. Areas along the lower portions of STM are identified as most susceptible to inundation. A computed consistency ratio of 0.03 is indicative of the efficiency of the study's model. These findings provide relevant stakeholders with an extensive understanding of the different flood zones for effective flood planning and prevention in STM.

Roadway floods and their associated weather-related conditions: New insights using CARS 511 data for state and federal highways in Nebraska, USA

This study examined roadway flooding event data provided by the Nebraska Department of Transportation via the Condition Acquisition Reporting System (CARS) 511 archive (2016–2021). With these data, a novel analysis was completed to further the understanding of where, when, and why (meteorologically) roadway flooding occurs on Nebraska state and federal highways. In the study period, 298 roadway floods occurred, with an annual median of 16 per year. There was a greater risk for roadway floods to transpire more frequently in eastern Nebraska, which was attributed to the spatial climatology of heavy rainfall and the higher density of roadways and rivers. Consequently, this increases the exposure and vulnerability of the highway system across the eastern portion of the state. Further, precursor soil moisture and river conditions proved to be critical initiators of roadway floods, as precipitation totals prior to each flood only averaged at 40 mm, while precursor Palmer Hydrological Drought Index values for 75% of events were above 4.0 and river levels were 200 cm above its daily medians. Overall, the complexities of these roadway flooding events are challenging for proactively forecasting as opposed to reacting to the situation. With the top roadway flooding locations identified along with the weather-related causes, further investigation of roadway flooding hotspots across the state needs to take place for mitigation and resiliency in a changing climate. The methods of this research can be used across other states and by other agencies to analyze and increase the resilience of their respective roadway networks.

A Novel Response Priority Framework for an Urban Coastal Catchment Using Global Weather Forecasts‐Based Improved Flood Risk Estimates

AbstractA novel flood risk forecasting‐based response priority framework is proposed in this study, which will facilitate efficient decision‐making ahead of an extreme precipitation event. This study is demonstrated over a highly flood‐prone and geomorphologically diverse coastal catchment in Mumbai city, the financial capital of India, and is subjected to high spatio‐temporal variability of precipitation. A regional precipitation forecast model is developed, where a quantile regression (QR)‐based statistical approach is applied to the global weather forecasts for improvement in finer resolution extreme precipitation estimates. A QR is performed between the observed synoptic‐scale predictors obtained from ERA‐Interim Reanalysis data set and the observed subdaily precipitation within the study area. Subsequently, a set of reliably well‐simulated forecasted predictors obtained from the ensemble members of the Global Ensemble Forecast System are used in the established relationship to obtain extreme precipitation forecasts for higher quantile levels. The forecasted precipitation data serves as an essential input to a comprehensive hydrodynamic flood modeling framework. The flood inundation maps corresponding to different quantiles of forecasted precipitation are quantified to identify the flood hotspots. The set of flood inundations maps developed for different quantiles are utilized to demarcate the areas based on critical response time, that is, the time required by each cell within the study area to be inundated to a certain threshold depth, and the response priority levels for each cell are determined. This information is combined with socioeconomic vulnerability (SEV), a critical component of flood risk, to derive conjugated SEV‐based response priority maps.

ON-DEVICE MACHINE LEARNING FOR IDENTIFYING THE SPATIAL EXTENT OF CHRONIC COASTAL FLOODS

Coastal communities around the world are experiencing flooding due to sea level rise (SLR). At a local level, flood hot spots are often well known, but the causes and frequency of flooding are not well understood. This is in part because the floods are hyper-local and therefore difficult to monitor, and in part because there are many drivers that contribute to flooding. Data on flood incidence, spatial extent, and frequency are needed to better understand the causes and social consequences of chronic coastal flooding. The objective of this study is to develop smart, low-cost sensors with onboard machine learning (ML) for automated detection of flood incidence and spatial extent along roadways. By automating detection of flood incidence and extent, we will be able to gather fine-grained measures of human exposure to flooding at high spatial resolution.

Evaluating the association between morphological characteristics of urban land and pluvial floods using machine learning methods

Spatial pattern of urban land plays a significant role in the occurrence of pluvial floods. While landscape metrics have been widely used to reflect land use spatial patterns, the association between the morphological spatial pattern of urban land and pluvial floods is much less understood. Unlike landscape metrics, morphological spatial pattern analysis could discover more spatial information on the formation and layout of land use. To fill such knowledge gap, this research evaluated whether the morphological characteristics of urban land matter to pluvial floods based on machine learning techniques. Pearson's correlation test and random forest algorithm were employed to discover the linear and non-linear associations between the density of flood hotspots and a set of underlying influencing factors, respectively. A case study in a low-lying coastal city has highlighted the strong influence of land use morphological characteristics on pluvial floods with baseline influencing factors considered. The density of flood hotspots was positively associated with the core, loop, edge, and bridge of urban land at sub-watershed level, but negatively associated with islet urban land. While it is unfeasible to restrain rapid urban sprawl and population growth in many developing countries, this research could give specific guidance for upgrading the morphological spatial pattern of urban land. A proper design of key morphological elements may overcome the negative influence of urban expansion on pluvial floods. These findings could help urban planners and policy makers to highlight the importance of land use morphological spatial patterns.

The Global Drivers of Chronic Coastal Flood Hazards Under Sea‐Level Rise

AbstractWe present the first global estimates of annual average exceedances of contemporary minor, moderate, and major flood levels under sea‐level rise (SLR). Applying established methods, we show that minor flooding will occur most days worldwide under 0.7 m global SLR. Moderate flooding occurs at the same frequency under 1.0 m SLR. Local and regional differences in flood threshold elevations, tidal ranges, and non‐tidal variability lead to differences in the SLR required for this chronic flooding to emerge. Lower flood thresholds, smaller tidal ranges, and larger extreme skew surges mean chronic flooding can emerge with less SLR. We discuss several implications of these findings for coastal flood hazard assessments. First, tide‐driven water level variability dominates weather‐driven water level variability when determining locations' propensities for frequent and chronic flooding under SLR. Second, centimeter‐accurate flood threshold information is necessary to accurately estimate present and future flood hazards. Third, locations with the most frequent floods at present may not be those that have the most frequent floods under SLR. We develop the Rapid Assessment Framework for Frequent Flood Transitions under SLR (RAFFFTS) to apply these findings to locations not previously considered in global coastal flood hazard studies. RAFFFTS can robustly identify potential future tidal flooding hotspots using only 1‐year observational records. We anticipate RAFFFTS will be a valuable tool for identifying locations at risk of chronic flooding under SLR, complementing existing tools for identifying changes in less frequent episodic floods.

The potential of open-access data for flood estimations: uncovering inundation hotspots in Ho Chi Minh City, Vietnam, through a normalized flood severity index

Abstract. Hydro-numerical models are increasingly important to determine the adequacy and evaluate the effectiveness of potential flood protection measures. However, a significant obstacle in setting up hydro-numerical and associated flood damage models is the tedious and oftentimes prohibitively costly process of acquiring reliable input data, which particularly applies to coastal megacities in developing countries and emerging economies. To help alleviate this problem, this paper explores the usability and reliability of flood models built on open-access data in regions where highly resolved (geo)data are either unavailable or difficult to access yet where knowledge about elements at risk is crucial for mitigation planning. The example of Ho Chi Minh City, Vietnam, is taken to describe a comprehensive but generic methodology for obtaining, processing and applying the required open-access data. The overarching goal of this study is to produce preliminary flood hazard maps that provide first insights into potential flooding hotspots demanding closer attention in subsequent, more detailed risk analyses. As a key novelty, a normalized flood severity index (INFS), which combines flood depth and duration, is proposed to deliver key information in a preliminary flood hazard assessment. This index serves as an indicator that further narrows down the focus to areas where flood hazard is significant. Our approach is validated by a comparison with more than 300 flood samples locally observed during three heavy-rain events in 2010 and 2012 which correspond to INFS-based inundation hotspots in over 73 % of all cases. These findings corroborate the high potential of open-access data in hydro-numerical modeling and the robustness of the newly introduced flood severity index, which may significantly enhance the interpretation and trustworthiness of risk assessments in the future. The proposed approach and developed indicators are generic and may be replicated and adopted in other coastal megacities around the globe.

Exploring the relationship between urban flood risk and resilience at a high-resolution grid cell scale

The assessment of flood risk and resilience has become increasingly important in recent years for effective urban flood management. While flood resilience and risk are two distinct concepts with unique assessment metrics, there is lack of quantitative analysis and understanding of the relationship between them. This study aims to investigate this relationship at the grid cell level in urban areas. To assess flood resilience for high-resolution grid cells, this study proposes a performance-based flood resilience metric, which is calculated using the system performance curve based on flood duration and magnitude. Flood risk is calculated as the product of maximum flood depth and probability, considering multiple storm events. The case study of Waterloo in London, UK is analyzed using a two-dimensional cellular automata-based model CADDIES, which consists of 2.7 million grid cells (5 m × 5 m). The results indicate that over 2 % of grid cells have risk values exceeding 1. Furthermore, there is a 5 % difference in resilience values below 0.8 between the 200-year and 2000-year design rainfall events, specifically 4 % for the former and 9 % for the latter. Additionally, the results reveal a complex relationship between flood risk and resilience, though decreasing flood resilience generally leads to increasing flood risk. However, this relationship varies depending on the land cover type, with building, green land, and water body cells showing higher resilience for the same level of flood risk compared to other land uses such as roads and railways. Classifying urban areas into four categories, including high risk vs. low resilience, high risk vs. high resilience, low risk vs. low resilience, and low risk vs. high resilience, is crucial in identifying flood hotspots for intervention development. In conclusion, this study provides an in-depth understanding of the relationship between risk and resilience in urban flooding, which could help improve urban flood management. The proposed performance-based flood resilience metric and the findings from the case study of Waterloo in London could be valuable for decision-makers in developing effective flood management strategies in urban areas.

High temporal resolution urban flood prediction using attention-based LSTM models

Rapid and accurate urban flood forecasting with high temporal resolution is critical to address future flood risks under urbanization and climate change. Machine learning models are increasingly used for flood forecasting, however, they are limited in their ability to extract effective features from rainfall data and capture dynamic runoff processes. This study proposes an attention mechanism-based Long Short-Term Memory (LSTM) network, named as ALSTM-DW, which uses double time sliding windows (DTSW), and a weighted mean square error (WMSE) loss function. The ALSTM-DW model was applied to three urban flooding hotspots in Shenzhen, China, and its effectiveness was verified through a series of comparative experiments. The results obtained show that: 1) the proposed model performs well, with a coefficient of determination larger than 0.85, peak flow error smaller than 0.015 m, and time to peak error smaller than 2 min on average in testing periods; 2) the use of DTSW helps extract effective rainfall features and mitigate excessive fluctuations in forecasted hydrographs caused by over-response to rainfall; 3) adding the attention mechanism to the LSTM network helps consider the varying contribution of each input factor over time; and 4) the WMSE improves the ability of the network to predict flood peaks, with an average decrease of 88% and 54% in peak flow error and time to peak error, respectively. Therefore, the ALSTM-DW model shows promising potential for providing accurate flood forecasting, which can support effective flood emergency operations.

Unveiling the role of contextual factors in the evolution of urban floods in Sub-Saharan Africa: Lessons from Kampala city

The understanding of the changing nature of recurrent and widespread urban flood risks across the rapidly urbanising Sub-Saharan African cities has, for long, been overshadowed by more general factors such as rainfall intensity, insufficient drainage systems, occupation of floodplains and, more recently, the climate change praxis. Yet, the impact of context-specific conditions on urban flood risks is still surrounded by ambiguity across the existing empirical research, policy and political arena. This research seeks to unveil the missing links regarding how contextual drivers of urban flood risks are understood across urban actors. Using Kampala city as the case study area, this research adopts multi-methods such as key informant semi-structured interviews, web-based surveys, GIS and policy reviews to gather relevant empirical data. The findings indicate that a) the nature of urban flooding is dictated by the level of interaction between socioeconomic, institutional, environmental and infrastructural factors and b) the negligence, ambiguity and inconsistency that characterise the institutional policy landscape plays a vital role in the co-evolution of urban flood hotspots. Overall, this research contributes to an in-depth understanding of the role of multiple context-specific urban conditions in urban flooding, a fundamental prerequisite for designing robust approaches to flood management.

EMPOWERING GEO-BASED AI ALGORITHM TO AID COASTAL FLOOD RISK ANALYSIS: A REVIEW AND FRAMEWORK DEVELOPMENT

Abstract. Climate change and current susceptibilities exacerbated the coastal flood loss and damage resulting in livelihoods and property damage. Urban areas in the Low to Lower-Middle Income Countries are expected to be disproportionately impacted by the disaster, given a higher share of citizens living in the Low Elevation Coastal Zone, limited financial resources, and poorly constructed disaster protection. Documentation of historical coastal floods, population, and property affected, could advance the assessment by considering those parameters in risk analysis. Besides, incorporating such geographic features e.g., mangroves as the ecological solution for alternative coastal flood protection in the prediction is also essential. Mangrove is considered fit for the LLMIC primarily situated in the tropical zone. The prediction utilizing spatial Machine Learning (ML) could aid climate-related disaster risk analysis and contribute to risk reduction and policy suggestions to improve disaster resilience. The research aims to archive recent studies on the application of geospatial science empowering Artificial Intelligence, notably ML in coastal flood risk assessment, so-called GIS-based AI. Another aim is to document population, property, and mangrove distribution across the LLMIC. Artificial Neural Networks were mostly utilized for disaster risk assessment in past research. The number of 58 historical coastal flood events and 908 expected coastal flood hotspots for 2006 to 2021 has been documented. Over 1,2 million Km2 falls under vulnerable areas toward coastal flood in LLMIC under different settlement types where Large City (urban areas) dominates it. Mangrove distribution is mainly distributed across tropical regions mostly distributed along the Southeast Asia coast.

The conterminous United States are projected to become more prone to flash floods in a high-end emissions scenario

Flash floods are largely driven by high rainfall rates in convective storms that are projected to increase in frequency and intensity in a warmer climate in the future. However, quantifying the changes in future flood flashiness is challenging due to the lack of high-resolution climate simulations. Here we use outputs from a continental convective-permitting numerical weather model at 4-km and hourly resolution and force a numerical hydrologic model at a continental scale to depict such change. As results indicate, US floods are becoming 7.9% flashier by the end of the century assuming a high-emissions scenario. The Southwest (+10.5%) has the greatest increase in flashiness among historical flash flood hot spots, and the central US (+8.6%) is emerging as a new flash flood hot spot. Additionally, future flash flood-prone frontiers are advancing northwards. This study calls on implementing climate-resilient mitigation measures for emerging flash flood hot spots.

Pluvial flooding: High-resolution stochastic hazard mapping in urban areas by using fast-processing DEM-based algorithms

Climate change and rapid expansion of urban areas are expected to increase pluvial flood hazard and risk in the near future, and particularly so in large developed areas and cities. Therefore, large-scale and high-resolution pluvial flood hazard mapping is required to identify hotspots where mitigation measures may be applied to reduce flood risk. Depressions or low points in urban areas where runoff volumes can be stored are prone to pluvial flooding. The standard approach based on estimating synthetic design hyetographs assumes, in a given depression, that the T-year design storm generates the T-year pluvial flood. In addition, urban areas usually include several depressions even linked or nested that would require distinct design hyetographs instead of using a unique synthetic design storm. In this paper, a stochastic methodology is proposed to address the limitations of this standard approach, developing large-scale ∼ 2 m-resolution pluvial flood hazard maps in urban areas with multiple depressions. The authors present an application of the proposed approach to the city of Pamplona in Spain (68.26 km2). The Safer_RAIN fast-processing algorithm based on digital elevation models (DEMs) is compared with the IBER 2D hydrodynamic model in four real storms by using 10-min precipitation fields. Precipitation recorded at rainfall-gauging stations was merged with continuous fields obtained from a meteorological radar station. Given the hydrostatic limitations of Safer_RAIN, the benchmarking results are adequate in terms of water depths in depressions. A long set of 10 000 synthetic storms that maintain the statistical properties of observations in Pamplona is generated. Safer_RAIN is used to simulate runoff response, and filling and spilling processes, in depressions for the 10 000 synthetic storms, obtaining the probability distribution of water depths in each cell. Maps of pluvial flood hazards are developed in the Pamplona metropolitan area for 10 return periods in the range from two to 500 years from such pixel-based series of simulated water depths. Bivariate return-period curves are estimated in a set of cells, showing that several storms can generate a given T-year pluvial flood with an increasing precipitation with storm duration that depends on the draining catchment soil characteristics. The methodology proposed is useful to develop maps of pluvial flood hazards in large multi-depression urban areas in reasonable computation times, identifying the main pluvial flood hotspots.

Migrating rivers, consequent paleochannels: The unlikely partners and hotspots of flooding

Furious floods have become an omnipresent reality with the dawn of climate change and its transition to adulthood. Since climate change has now become an accepted reality, analysing the factors that favour or disfavour floods are an urgent requirement. Here we showcase the role of paleochannels, a product of migrating rivers, in a catastrophic flood in the south-western part of the Indian Peninsula. This study exposes whether these geomorphic features facilitate or impede floods. For the purpose of extracting paleochannels and floodwater mapping, we utilized multiple satellite datasets and took advantage of diversified feature selection algorithms. Paleochannels were demarcated viz., initial identification of a few paleochannels from literature and confirmation through high-resolution Google Earth (GE) images, followed by Principal Component Analysis (PCA) of Sentinel-2 images using Google Earth Engine (GEE), and a supervised classification of the principal bands 1, 2, and 3. False-positives were eliminated using Object-Oriented Analysis (OOA), which reduced the 964,254 polygons to 23,254. These polygons were visually affirmed using GE images that resulted in 115 paleochannels as the final collection. A few locations were verified through Vertical Electrical Sounding (VES) using the Schlumberger method. The features were analysed with the floodwaters of the 2018 catastrophic flood, extracted from Synthetic Aperture Radar (SAR) data, which was delineated for different temporal limits including the day of peak flood of August 17, 2018. During the peak flood, the inundation of the study area extended to 534.86 km2 with all the paleochannels getting immersed in floodwater. After 44 days of peak flood, the post-flood analysis revealed that when the floodwater receded 50%, the paleochannels emptied 87.39%, with the midland paleochannels discharging more than those of lowlands. Thus, such geomorphic features can be flood hotspots, but can be considered for discharging floodwater to mitigate flood risk in case of unprecedented rain.

Integrating user‐generated content to track urban flooding hotspots and foster emergency management: A case study in central China

AbstractThis study explores the potential for employing user‐generated content (UGC) during severe flooding to discover and track urban flooding disaster hotspots in a timely manner. A flooding case in central China was selected for this study. Crawlers, natural language processing, and geographic visualization methods were used to extract flood‐related UGC specific to severely flooded areas. Further, the quality of the geo‐tagged content on the web was verified using scientific gauge data (e.g., water level, digital elevation model, and rainfall). Based on our findings, we were able to deduce that UGC on the web is valuable for identifying flooding hotspots. In fact, this approach offers substantial advantages for addressing the emerging needs of data acquisition for flood emergency management. Notably, the values of urban stakeholders that share their observations on the web can be mined rapidly through the integration of various approaches. Overall, the findings of our study can contribute to the efficient mining of web data sources and development of disaster hotspot mapping systems at an urban scale to improve flood management and mitigation. The limitations of UGC and our study's future direction are also discussed.