A Synthetic Aperture Radar-Based Robust Satellite Technique (RST) for Timely Mapping of Floods

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(12), P. 2193 - 2193

Published: June 17, 2024

Satellite data have been widely utilized for flood detection and mapping tasks, in recent years, there has a growing interest using Synthetic Aperture Radar (SAR) due to the increased availability of missions with enhanced temporal resolution. This capability, when combined inherent advantages SAR technology over optical sensors, such as spatial resolution independence from weather conditions, allows timely accurate information on event dynamics. In this study, we present an innovative automated approach, SAR-RST-FLOOD, flooded areas data. Based multi-temporal analysis Sentinel 1 data, approach would allow robust automatic identification areas. To assess its reliability accuracy, analyzed five case studies where floods caused significant damage. Performance metrics, overall (OA), user (UA), producer (PA) well Kappa index (K), were used evaluate methodology by considering several reference maps. The results demonstrate accuracy exceeding 0.78 each test map compared observed Additionally, values surpassed 0.96, kappa exceeded processes or other datasets Copernicus Emergency Management System. Considering these fact that proposed implemented within Google Earth Engine framework, potential global-scale applications is evident.

Language: Английский

---

Cyclone surge inundation susceptibility assessment in Bangladesh coast through geospatial techniques and machine learning algorithms: a comparative study between an island and a mangrove protected area

Frontiers in Earth Science, Journal Year: 2025, Volume and Issue: 13

Published: March 18, 2025

Tropical cyclones, including surge inundation, are a joint event in the coastal regions of Bangladesh. The washes out life and property within very short period. Besides, most cases, area remains flooded for several days. Prediction inundation susceptibility due to cyclone is one key issues reducing vulnerability. Surge can be analyzed effectively through geospatial techniques various algorithms. Two techniques, such as GIS-based Analytical Hierarchy Process (AHP) multi-criteria analysis bivariate Frequency Ratio (FR) three algorithms, i.e., Artificial Neural Network (ANN), k -nearest neighbor (KNN) Random Forest (RF), were applied understand comparative level between an island, Sandwip protected by mangrove, Dacope on Bangladesh coast. A total ten criteria considered influential flooding, Elevation, Slope, Topographic Wetness Index, Drainage density, Distance from river sea, Wind flow distance, LULC, NDVI, Precipitation, Soil types. Among them, distance sea (16.34%) elevation (15.01%) found crucial analysis, according AHP expert’s opinions. Similarly, precipitation (9.88) (6.92) LULC (4.16) NDVI (4.33) highest PR values FR analysis. factor maps final ArcGIS 10.8. categorized into five classes, low, moderate, high, high. Very high was around boundary island upper portion upazila. (45.07%) (49.41%) observed KNN ANN, respectively. receiver operating characteristic (ROC) all acceptable prediction; however, possessed better consistent under curve (AUC) value than algorithms both study sites. Policymakers professionals plan manage disaster reduction activities based outcomes.

Language: Английский

---

Enhancing flood prediction through remote sensing, machine learning, and Google Earth Engine

Frontiers in Water, Journal Year: 2025, Volume and Issue: 7

Published: March 18, 2025

Floods are the most common natural hazard, causing major economic losses and severely affecting people’s lives. Therefore, accurately identifying vulnerable areas is crucial for saving lives resources, particularly in regions with restricted access insufficient data. The aim of this study was to automate identification flood-prone within a data-scarce, mountainous watershed using remote sensing (RS) machine learning (ML) models. In study, we integrate Normalized Difference Flood Index (NDFI), Google Earth Engine generate flood inventory, which considered step susceptibility mapping. Seventeen determining factors, namely, elevation, slope, aspect, curvature, Stream Power (SPI), Topographic Wetness (TWI), Ruggedness (TRI), Position (TPI), distance from roads, rivers, stream density, rainfall, lithology, Vegetation (NDVI), land use, length slope (LS) factor, Convergence were used map vulnerability. This aimed assess predictive performance gradient boosting, AdaBoost, random forest. model evaluated area under curve (AUC). assessment results showed that forest (RF) achieved highest accuracy (1), followed by boosting ensemble (RF-GB) (0.96), (GB) (0.95), AdaBoost (AdaB) (0.83). Additionally, research employed Shapely Additive Explanations (SHAP) method, explain predictions determine contributing factor each model. introduces novel approach providing significant insights into mapping, offering potential pathways future practical applications. Overall, emphasizes need urban planning emergency preparedness build safer more resilient communities.

Language: Английский

---

Flood susceptibility assessment using deep neural networks and open-source spatial datasets in transboundary river basin

VIETNAM JOURNAL OF EARTH SCIENCES, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

The Mekong Basin is the most critical transboundary river basin in Asia. This provides an abundant source of fresh water essential for development agriculture, domestic consumption, and industry, as well production hydroelectricity, it also contributes to ensuring food security worldwide. region often subject floods that cause significant damage human life, society, economy. However, flood risk management challenges this are increasingly substantial due conflicting objectives between several countries data sharing. study integrates deep learning with optimization algorithms, namely Grasshopper Optimisation Algorithm (GOA), Adam Stochastic Gradient Descent (SGD), open-source datasets identify probably occurring basin, covering Vietnam Cambodia. Various statistical indices, Area Under Curve (AUC), root mean square error (RMSE), absolute (MAE), coefficient determination (R²), were used evaluate susceptibility models. results show proposed models performed AUC values above 0.8, specifying DNN-Adam model achieved 0.98, outperforming DNN-GOA (AUC = 0.89), DNN-SGD 0.87), XGB 0.82. Regions very high concentrated Delta along River findings supporting decision-makers or planners proposing appropriate mitigation strategies, planning policies, particularly watershed.

Language: Английский

---

Accelerated and Interpretable Flood Susceptibility Mapping Through Explainable Deep Learning with Hydrological Prior Knowledge

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(9), P. 1540 - 1540

Published: April 26, 2025

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) struggle capture spatial dependencies. To address this, we propose a modified U-Net architecture that integrates prior knowledge permanent water bodies improve flood susceptibility mapping in Northumberland County, UK. By embedding domain-specific insights, our model achieves higher area under curve (AUC) (0.97) compared standard (0.93), also reducing training time by converging three times faster. Additionally, integrate Grad-CAM module provide visualisations explaining areas attention from model, enabling interpretation its decision-making, thus barriers practical implementation.

Language: Английский

---

Analysis of the Utilization of Machine Learning to Map Flood Susceptibility

Journal of Flood Risk Management, Journal Year: 2025, Volume and Issue: 18(2)

Published: April 28, 2025

ABSTRACT This article provides an analysis of the utilization Machine Learning (ML) models in Flood Susceptibility Mapping (FSM), based on selected publications from past decade (2013–2023). Recognizing challenge that some stages ML modeling inherently rely experience or trial‐and‐error approaches, this work aims at establishing a clear roadmap for deployment ML‐based FSM frameworks. The critical aspects are identified, including data considerations, model's development procedure, and employed algorithms. A comparative different models, alongside their practical applications, is made. Findings suggest despite existing limitations, methods, when carefully designed implemented, can be successfully utilized to determine areas risk flooding. We show effectiveness significantly influenced by preprocessing, feature engineering, model using most impactful parameters, as well selection appropriate type configuration. Additionally, we introduce structured FSM, identification overlooked conditioning factors, analysis, integration all aimed enhancing quality effectiveness. comprehensive thereby serves resource professionals field FSM.

Language: Английский

---

Continuous flood monitoring using on-demand SAR data acquired with different geometries: Methodology and test on COSMO-SkyMed images

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2025, Volume and Issue: 225, P. 382 - 401

Published: May 9, 2025

Language: Английский

---

Assessing Flood and Landslide Susceptibility Using XGBoost: Case Study of the Basento River in Southern Italy

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(10), P. 5290 - 5290

Published: May 9, 2025

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 integrated topographical, geological, remote sensing datasets. Flood event data were collected from institutional sources multi-source high-resolution remotely sensed data. landslide inventory was compiled historical records geomorphological analysis. Key factors such as elevation, slope, lithology, land cover analyzed identify areas prone floods landslides. methodology Basento River basin in Southern Italy, region frequently impacted hazards, assess its vulnerability inform risk management strategies. While flood is primarily associated with low-lying near river networks, more steep slopes geological instability. XGBoost model achieved classification accuracy close 1 flood-prone 0.92 landslide-prone areas. Results showed that low Elevation Relative Elevation, high Drainage Density, whereas broader balanced set of including Distance Lithology. resulting offered critical approaches use planning, emergency management, mitigation. Overall, results demonstrated effectiveness multi-hazard assessments, offering scalable transferable similar at-risk regions worldwide.

Language: Английский

---

Regional Flood Risk Assessment and Prediction Based on Environmental Attributes and Pipe Operational Characteristics

Water, Journal Year: 2025, Volume and Issue: 17(10), P. 1477 - 1477

Published: May 14, 2025

Urban flood risk assessments play a crucial role in urban resilience and disaster management. This paper proposes comprehensive method for assessment prediction that is based on environmental attributes the operational characteristics of pipe networks. Using central area Zhengzhou as case study, an integrated evaluation index system was developed, entropy weight applied to quantify indicators. A loosely coupled RF-XGBoost model constructed predict different rainfall scenarios. The results indicate (1) overall study exhibits increasing trend from northeast southwest, with medium- high-risk zones being predominant; (2) spatial distribution pattern closely aligns but shows slight variations under influence network risks; (3) demonstrates superior predictive accuracy multi-factor coupling When characteristics, attributes, risks are comprehensively considered, Nash–Sutcliffe Efficiency (NSE) predictions improves 0.85 (when using only characteristics) 0.94. provides valuable insights technical support mitigating risks.

Language: Английский

---

The impact of dam management and rainfall patterns on flooding in the Niger Delta: using Sentinel-1 SAR data

Discover Water, Journal Year: 2024, Volume and Issue: 4(1)

Published: Dec. 18, 2024

Language: Английский

---