Search Results (194)

Flood impacts are intensifying due to the increasing frequency and severity of factors such as severe weather events, climate change, and unplanned urbanization. This study focuses on Briar Creek in Charlotte, North Carolina, an area historically affected by flooding. Three machine learning algorithms —bagging (random forest), extreme gradient boosting (XGBoost), and logistic regression—were used to develop a flood susceptibility model that incorporates topographical, hydrological, and meteorological variables. Key predictors included slope, aspect, curvature, flow velocity, flow concentration, discharge, and 8 years of rainfall data. A flood inventory of 750 data points was compiled from historic flood records. The dataset was divided into training (70%) and testing (30%) subsets, and model performance was evaluated using accuracy metrics, confusion matrices, and classification reports. The results indicate that logistic regression outperformed both XGBoost and bagging in terms of predictive accuracy. According to the logistic regression model, the study area was classified into five flood risk zones: 5.55% as very high risk, 8.66% as high risk, 12.04% as moderate risk, 21.56% as low risk, and 52.20% as very low risk. The resulting flood susceptibility map constitutes a valuable tool for emergency preparedness and infrastructure planning in high-risk zones. Full article

This study presents a novel bivariate-output deep learning framework based on LeNet-5 for the simultaneous prediction of urban flood susceptibility and inundation depth in Seoul, South Korea. Unlike previous studies that relied on single-output models, the proposed approach jointly learns classification and regression targets through a shared feature extraction structure, enhancing consistency and generalization. Among six tested architectures, the Le5SD_CBAM model—integrating a Convolutional Block Attention Module (CBAM)—achieved the best performance, with 83% accuracy, an Area Under the ROC Curve (AUC) of 0.91 for flood susceptibility classification, and a mean absolute error (MAE) of 0.12 m and root mean squared error (RMSE) of 0.18 m for depth estimation. The model’s spatial predictions aligned well with hydrological principles and past flood records, accurately identifying low-lying flood-prone zones and capturing localized inundation patterns influenced by infrastructure and micro-topography. Importantly, it detected spatial mismatches between susceptibility and depth, demonstrating the benefit of joint modeling. Variable importance analysis highlighted elevation as the dominant predictor, while distances to roads, rivers, and drainage systems were also key contributors. In contrast, secondary terrain attributes had limited influence, indicating that urban infrastructure has significantly altered natural flood flow dynamics. Although the model lacks dynamic forcings such as rainfall and upstream inflows, it remains a valuable tool for flood risk mapping in data-scarce settings. The bivariate-output framework improves computational efficiency and internal coherence compared to separate single-task models, supporting its integration into urban flood management and planning systems. Full article

Floods pose a substantial risk to human well-being. These risks encompass economic losses, infrastructural damage, disruption of daily life, and potential loss of life. This study presents a state-wide and county-level spatial exposure assessment of the Iowa railway network, emphasizing the resilience and reliability of essential services during such disasters. In the United States, the railway network is vital for the distribution of goods and services. This research specifically targets the railway network in Iowa, a state where the impact of flooding on railways has not been extensively studied. We employ comprehensive GIS analysis to assess the vulnerability of the railway network, bridges, rail crossings, and facilities under 100- and 500-year flood scenarios at the state level. Additionally, we conducted a detailed investigation into the most flood-affected counties, focusing on the susceptibility of railway bridges. Our state-wide analysis reveals that, in a 100-year flood scenario, up to 9% of railroads, 8% of rail crossings, 58% of bridges, and 6% of facilities are impacted. In a 500-year flood scenario, these figures increase to 16%, 14%, 61%, and 13%, respectively. Furthermore, our secondary analysis using flood depth maps indicates that approximately half of the railway bridges in the flood zones of the studied counties could become non-functional in both flood scenarios. These findings are crucial for developing effective disaster risk management plans and strategies, ensuring adequate preparedness for the impacts of flooding on railway infrastructure. Full article

Floods are considered one of the most devastating natural hazards, frequently resulting in substantial loss of lives and widespread damage to infrastructure. In the period of 4–7 September 2023, the region of Thessaly experienced unprecedented rainfall rates due to Storm Daniel, which caused significant flooding and many damages and fatalities. The southeastern areas of Trikala were among the many areas of Thessaly that suffered the effects of these rainfalls. In this research, a flood susceptibility assessment (FSA) of the broader area surrounding the settlement of Megala Kalyvia is carried out through the analytical hierarchy process (AHP) as a multicriteria analysis method, using Geographic Information Systems (GIS). The purpose of this study is to evaluate the prolonged flood susceptibility indicated within the area due to the past floods of 2018, 2020, and 2023. To determine the flood-prone areas, seven factors were used to determine the influence of flood susceptibility, namely distance from rivers and channels, drainage density, distance from confluences of rivers or channels, distance from intersections between channels and roads, land use–land cover, slope, and elevation. The flood susceptibility was classified as very high and high across most parts of the study area. Finally, a comparison was made between the modeled flood susceptibility and the maximum extent of past flood events, focusing on that of 2023. The results confirmed the effectiveness of the flood susceptibility assessment map and highlighted the need to adapt to the changing climate patterns observed in September 2023. Full article

Flood susceptibility mapping is essential for urban planning and disaster risk management, especially in rapidly urbanizing areas exposed to extreme rainfall events. This study applies an integrated approach combining Geographic Information Systems (GIS), map algebra, and the Analytic Hierarchy Process (AHP) to assess flood-prone zones in Ananindeua, Pará, Brazil. Five geoenvironmental criteria—rainfall, land use and land cover (LULC), slope, soil type, and drainage density—were selected and weighted using AHP to generate a composite flood susceptibility index. The results identified rainfall and slope as the most influential criteria, with both contributing to over 184 km² of high-susceptibility area. Spatial patterns showed that flood-prone zones are concentrated in flat urban areas with high drainage density and extensive impermeable surfaces. CHIRPS rainfall data were validated using Pearson’s correlation (r = 0.83) and the Nash–Sutcliffe efficiency (NS = 0.97), confirming the reliability of the precipitation input. The final susceptibility map, categorized into low, medium, and high classes, was validated using flood events derived from Sentinel-1 SAR data (2019–2025), of which 97.2% occurred in medium- or high-susceptibility zones. These findings demonstrate the model’s strong predictive performance and highlight the role of unplanned urban expansion, land cover changes, and inadequate drainage in increasing flood risk. Although specific to Ananindeua, the proposed methodology can be adapted to other urban areas in Brazil, provided local conditions and data availability are considered. Full article

The city of Uvira, located in the eastern Democratic Republic of Congo (DRC), is increasingly experiencing flood events with devastating impacts on human life, infrastructure, and livelihoods. This study evaluates flood susceptibility in Uvira using Geographic Information Systems (GISs), and an Analytical Hierarchy Process (AHP)-based Multi-Criteria Decision Making approach. It integrates eight factors contributing to flood occurrence: distance from water bodies, elevation, slope, rainfall intensity, drainage density, soil type, topographic wetness index, and land use/land cover. The results indicate that proximity to water bodies, drainage density and slope are the most influential factors driving flood susceptibility in Uvira. Approximately 87.3% of the city’s land area is classified as having high to very high flood susceptibility, with the most affected zones concentrated along major rivers and the shoreline of Lake Tanganyika. The reliability of the AHP-derived weights is validated by a consistency ratio of 0.008, which falls below the acceptable threshold of 0.1. This research provides valuable insights to support urban planning and inform flood management strategies. Full article

This research paper presents an assessment of geohazards on Lefkas Island, Greece, using Geographic Information System (GIS) technology to map risk and enhance public awareness through an interactive web application. Natural hazards such as landslides, floods, wildfires, and desertification threaten both the safety of residents and the island’s tourism-dependent economy, particularly due to its seismic activity and Mediterranean climate. By combining the Sendai Framework for Disaster Risk Reduction with GIS capabilities, we created detailed hazard maps that visually represent areas of susceptibility and provide critical insights for local authorities and the public. The web application developed serves as a user-friendly platform for disseminating hazard information and educational resources, thus promoting community preparedness and resilience. The findings highlight the necessity for proactive land management strategies and community engagement in disaster risk reduction efforts. This study underscores GIS’s pivotal role in fostering informed decision making and enhancing the safety of Lefkas Island’s inhabitants and visitors in the face of environmental challenges. Full article

Flooding poses significant challenges in semi-arid regions, where irregular rainfall patterns increase environmental vulnerability. This study explicitly aims to improve flood susceptibility mapping by integrating advanced machine learning (ML) algorithms with geographic information systems (GIS) and remote-sensing data. Using data from the Upper Drâa Basin in southern Morocco, we applied boosting algorithms, including XGBoost, CatBoost, LightGBM, and Hist Gradient Boosting, to enhance the accuracy of flood risk assessment. Quantitative model evaluation shows that Hist Gradient Boosting achieved the best performance, with the lowest mean squared error (MSE = 0.06897) and root mean squared error (RMSE = 0.2626). It also attained the highest F1 score (0.8), overall accuracy (93.1%), and area under the curve (AUC = 0.833), indicating its superior predictive capability. These findings highlight the strong potential of novel boosting ensemble learning methods in flood susceptibility prediction and contribute valuable, data-driven insights for policymakers and urban planners to support effective flood mitigation strategies in southern Morocco. Full article

This study aims to enhance the accuracy and interpretability of flood susceptibility mapping (FSM) in Seoul, South Korea, by integrating automated machine learning (AutoML) with explainable artificial intelligence (XAI) techniques. Ten topographic and environmental conditioning factors were selected as model inputs. We first employed the Tree-based Pipeline Optimization Tool (TPOT), an evolutionary AutoML algorithm, to construct baseline ensemble models using Gradient Boosting (GB), Random Forest (RF), and XGBoost (XGB). These models were further fine-tuned using Bayesian optimization via Optuna. To interpret the model outcomes, SHAP (SHapley Additive exPlanations) was applied to analyze both the global and local contributions of each factor. The SHAP analysis revealed that lower elevation, slope, and stream distance, as well as higher stream density and built-up areas, were the most influential factors contributing to flood susceptibility. Moreover, interactions between these factors, such as built-up areas located on gentle slopes near streams, further intensified flood risk. The susceptibility maps were reclassified into five categories (very low to very high), and the GB model identified that approximately 15.047% of the study area falls under very-high-flood-risk zones. Among the models, the GB classifier achieved the highest performance, followed by XGB and RF. The proposed framework, which integrates TPOT, Optuna, and SHAP within an XAI pipeline, not only improves predictive capability but also offers transparent insights into feature behavior and model logic. These findings support more robust and interpretable flood risk assessments for effective disaster management in urban areas. Full article

Floods and landslides are two distinct natural phenomena influenced by different conditioning factors, though some environmental triggers may overlap. This study applied eXtreme Gradient Boosting (XGBoost) to develop susceptibility maps for both phenomena, using a unified approach based on the same geospatial predictors. The approach integrated topographical, geological, and remote sensing datasets. Flood event data were collected from institutional sources using multi-source and high-resolution remotely sensed data. The landslide inventory was compiled based on historical records and geomorphological analysis. Key conditioning factors such as elevation, slope, lithology, and land cover were analyzed to identify areas prone to floods and landslides. The methodology was applied to the Basento River basin in Southern Italy, a region frequently impacted by both hazards, to assess its vulnerability and inform risk management strategies. While flood susceptibility is primarily associated with low-lying areas near river networks, landslides are more influenced by steep slopes and geological instability. The XGBoost model achieved a classification accuracy close to 1 for flood-prone areas and 0.92 for landslide-prone areas. Results showed that flood susceptibility was primarily associated with low Elevation and Relative Elevation, and high Drainage Density, whereas landslide susceptibility was more influenced by a broader and balanced set of factors, including Elevation, Drainage Density, Relative Elevation, Distance and Lithology. The resulting susceptibility maps offered critical approaches for land use planning, emergency management, and risk mitigation. Overall, the results demonstrated the effectiveness of XGBoost in multi-hazard assessments, offering a scalable and transferable approach for similar at-risk regions worldwide. Full article

The frequency and magnitude of natural hazards have been steadily increasing, largely due to extreme weather events driven by climate change. These hazards pose significant global challenges, underscoring the need for accurate prediction models and systematic preparedness. This study aimed to predict multiple natural hazards in South Korea using various machine learning algorithms. The study area, South Korea (100,210 km²), was divided into a grid system with a 0.01° resolution. Meteorological, climatic, topographical, and remotely sensed data were interpolated into each grid cell for analysis. The study focused on three major natural hazards: drought, flood, and wildfire. Predictive models were developed using two machine learning algorithms: Random Forest (RF) and Extreme Gradient Boosting (XGB). The analysis showed that XGB performed exceptionally well in predicting droughts and floods, achieving ROC scores of 0.9998 and 0.9999, respectively. For wildfire prediction, RF achieved a high ROC score of 0.9583. The results were integrated to generate a multi-hazard susceptibility map. This study provides foundational data for the development of hazard management and response strategies in the context of climate change. Furthermore, it offers a basis for future research exploring the interaction effects of multi-hazards. Full article

Flash floods pose a significant threat to Bangladesh; in particular, on 20 August 2024, the Feni district experienced a major flash flood, affecting more than 550,000 people and causing widespread damage. To effectively mitigate the impacts of flash floods, it is essential to conduct a comprehensive flash flood vulnerability assessment, incorporating multiple triggering factors. This study aims to assess flash flood vulnerability in the Feni District through a unique approach, integrating various dimensions of vulnerability. The study utilizes a geospatial methodology, employing the formula of vulnerability developed by UNESCO-IHE. Four dimensions of vulnerability were analyzed: social, physical, economic, and environmental. For each dimension, specific variables were selected to assess exposure, susceptibility, and resilience. Principal Component Analysis (PCA) was used to assign weights to these variables. The geospatial layers of influencing vulnerability factors were integrated together to create flash flood vulnerability maps of four dimensions. These were then overlaid to generate a composite flash flood vulnerability map. The analysis revealed a distinct spatial distribution of vulnerability across Feni District. In terms of environmental vulnerability due to flash flood, about 14% of the total area falls into the very highly vulnerable zone, whereas 13%, 8% and 5% of the study area were found to be very highly vulnerable regarding social, economic and physical aspects, respectively. The composite flash flood vulnerability map identified key vulnerability hotspots, with the most vulnerable unions (the smallest administrative unit in Bangladesh) being Feni Pourashava (68% very high), Sonagazi Paurashava (40% very high), and Nawabpur (32% very high), while the least vulnerable areas were Jailashkara (58% very low), Anandapur (81% very low), and Darbarpur (82% very low). The results show that the Feni District’s flash flood susceptibility varies significantly throughout the region, which provide crucial insights for policymakers and local authorities in order to identify vulnerability hotspots, prioritize interventions in vulnerable areas, enhance flash flood resilience, and implement adaptive strategies. Full article

Floods are among the most destructive natural hazards globally, necessitating the identification of flood-prone areas for effective disaster risk management and sustainable urban development. Advanced data-driven techniques, including machine learning (ML), are increasingly used to map and mitigate flood risks. However, ML applications for flood risk assessment remain limited in Sorocaba, a sub-region of São Paulo, Brazil. This study employs four ML algorithms—differential evolution (DE), naïve Bayes (NB), random forest (RF), and support vector machines (SVMs)—to develop flood susceptibility models using 16 predictor variables. Key categorical factors influencing flood susceptibility included topographical, anthropogenic, and hydrometeorological, particularly elevation, slope, NDVI, NDWI, and distance to roads. Performance metrics (F1-score and AUC) showed strong results, ranging from 0.94 to 1.00, with the DE and RF models excelling in training, testing, and external datasets. The study highlights model transferability, demonstrating applicability to other regions. Findings reveal that 41% to 50% of Sorocaba is at high flood risk. The explainable artificial intelligence technique Shapley additive explanations (SHAP) further identified moisture and the stream power index (SPI) as significant factors influencing flood occurrence. The study underscores the ML-based model’s potential in highlighting flood-vulnerable areas and guiding flood mitigation strategies, land-use planning, and infrastructure resilience. Full article

Flooding is one of the most devastating natural disasters worldwide, with increasing frequency due to climate change. Traditional hydrological models require extensive data and computational resources, while machine learning (ML) models struggle to capture spatial dependencies. To address this, we propose a modified U-Net architecture that integrates prior hydrological knowledge of permanent water bodies to improve flood susceptibility mapping in Northumberland County, UK. By embedding domain-specific insights, our model achieves a higher area under the curve (AUC) (0.97) compared to the standard U-Net (0.93), while also reducing training time by converging three times faster. Additionally, we integrate a Grad-CAM module to provide visualisations explaining the areas of attention from the model, enabling interpretation of its decision-making, thus reducing barriers to its practical implementation. Full article

Traditional villages are vital repositories of China’s historical and cultural heritage. To enhance protection precision, this study develops a novel risk assessment framework integrating three dimensions: the natural environment, tangible heritage elements, and disaster prevention infrastructure. The framework mainly uses GIS spatial analysis and SPSS-based statistical modeling. It integrates traditional dwelling density as a key factor in vulnerability zoning by depicting assessment units with weighted vulnerability indicators. The study overlays kernel density maps of traditional buildings with natural hazard susceptibility data. This enables classification of villages and clusters into hierarchical disaster prevention tiers (core, key, and general zones). Core zones, characterized by high-density heritage structures and elevated flood risks, require structural reinforcement and ecological engineering, while key zones employ adaptive protection technologies. By incorporating traditional building density as a weighted vulnerability indicator, the framework enables hierarchical disaster zoning through spatial coupling of kernel density maps and flood susceptibility data. Taking the results of Lingshui Village as an example, an individual analysis was made, and the elements of the village were identified. Fourteen traditional villages in Mentougou District were graded and partitioned. Correlation examination of zoning findings and property damage, as well as an independent evaluation of categorization results and degree of calamity, demonstrated a correlation between the two. Therefore, empirical validation in Beijing’s Mentougou District demonstrates the efficacy of this approach. The methodology further establishes cross-village collaborative defense mechanisms under a “conservation–development–protection” paradigm, aligning administrative boundaries with spatial agglomeration patterns. The study establishes a hierarchical disaster prevention evaluation system and a regional technical pathway to bridge individual and cluster-level protection. Finally, by synergizing traditional dwelling conservation with ecological resilience, it explores bidirectional optimization between cultural heritage preservation and disaster prevention efficacy. Full article