Metaheuristic-driven enhancement of categorical boosting algorithm for flood-prone areas mapping

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2025, Номер 136, С. 104357 - 104357

Опубликована: Янв. 14, 2025

Язык: Английский

---

Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment

Environmental Science and Pollution Research, Год журнала: 2024, Номер 31(35), С. 48497 - 48522

Опубликована: Июль 20, 2024

Flooding is a major natural hazard worldwide, causing catastrophic damage to communities and infrastructure. Due climate change exacerbating extreme weather events robust flood modeling crucial support disaster resilience adaptation. This study uses multi-sourced geospatial datasets develop an advanced machine learning framework for assessment in the Arambag region of West Bengal, India. The inventory was constructed through Sentinel-1 SAR analysis global databases. Fifteen conditioning factors related topography, land cover, soil, rainfall, proximity, demographics were incorporated. Rigorous training testing diverse models, including RF, AdaBoost, rFerns, XGB, DeepBoost, GBM, SDA, BAM, monmlp, MARS algorithms, undertaken categorical mapping. Model optimization achieved statistical feature selection techniques. Accuracy metrics model interpretability methods like SHAP Boruta implemented evaluate predictive performance. According area under receiver operating characteristic curve (AUC), prediction accuracy models performed around > 80%. RF achieves AUC 0.847 at resampling factor 5, indicating strong discriminative AdaBoost also consistently exhibits good ability, with values 0.839 10. indicated precipitation elevation as most significantly contributing area. Most pointed out southern portions highly susceptible areas. On average, from 17.2 18.6% hazards. In analysis, various nature-inspired algorithms identified selected input parameters assessment, i.e., elevation, precipitation, distance rivers, TWI, geomorphology, lithology, TRI, slope, soil type, curvature, NDVI, roads, gMIS. As per analyses, it found that rivers play roles decision-making process assessment. results majority building footprints (15.27%) are high very risk, followed by those low risk (43.80%), (24.30%), moderate (16.63%). Similarly, cropland affected flooding this categorized into five classes: (16.85%), (17.28%), (16.07%), (16.51%), (33.29%). However, interdisciplinary contributes towards hydraulic hydrological management.

Язык: Английский

---

Improving flood hazard susceptibility assessment by integrating hydrodynamic modeling with remote sensing and ensemble machine learning

Natural Hazards, Год журнала: 2025, Номер unknown

Опубликована: Янв. 11, 2025

Abstract Floods are natural disasters with significant economic and infrastructural impacts. Assessing flood susceptibility in mountainous urban regions is particularly challenging due to the complicated interaction which structures terrain affect behavior. This study employs two ensemble machine learning algorithms, Extreme Gradient Boosting (XGBoost) Random Forest (RF), develop maps for Hunza-Nagar region, has been experiencing frequent flooding past three decades. An unsteady flow simulation carried out HEC-RAS utilizing a 100-year return period hydrograph as an input boundary condition, output of provided spatial inundation extents necessary developing inventory. Ten explanatory factors, including climatic, geological, geomorphological features namely elevation, slope, curvature, topographic wetness index (TWI), normalized difference vegetation (NDVI), land use cover (LULC), rainfall, lithology, distance roads rivers considered mapping. For inventory, random sampling technique adopted create repository non-flood points, incorporating ten geo-environmental conditioning factors. The models’ accuracy assessed using area under curve (AUC) receiver operating characteristics (ROC). prediction rate AUC values 0.912 RF 0.893 XGBoost, also demonstrating superior performance accuracy, precision, recall, F1-score, kappa evaluation metrics. Consequently, model selected represent map area. resulting will assist national disaster management infrastructure development authorities identifying high susceptible zones carrying early mitigation actions future floods.

Язык: Английский

---

Interpretable flash flood susceptibility mapping in Yarlung Tsangpo River Basin using H2O Auto-ML

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 11, 2025

Flash flood susceptibility mapping is essential for identifying areas prone to flooding events and aiding decision-makers in formulating effective prevention measures. This study aims evaluate the flash Yarlung Tsangpo River Basin (YTRB) using multiple machine learning (ML) models facilitated by H2O automated ML platform. The best-performing model was used generate a map, its interpretability analyzed Shapley Additive Explanations (SHAP) tree interpretation method. results revealed that top four models, including both single ensemble demonstrated high accuracy tests. map generated eXtreme Randomized Trees (XRT) showed 8.92%, 12.95%, 15.42%, 31.34%, 31.37% of area exhibited very high, moderate, low, low susceptibility, respectively, with approximately 74.9% historical floods occurring classified as moderate susceptibility. SHAP plot identified topographic factors primary drivers floods, importance analysis ranking most influential such descending order DEM, wetness index, position normalized difference vegetation average multi-year precipitation. demonstrates benefits interpretable learning, which can provide guidance mitigation.

Язык: Английский

---

Advancing flood risk assessment: Multitemporal SAR-based flood inventory generation using transfer learning and hybrid fuzzy-AHP-machine learning for flood susceptibility mapping in the Mahananda River Basin

Journal of Environmental Management, Год журнала: 2025, Номер 380, С. 124972 - 124972

Опубликована: Март 23, 2025

The Mahananda River basin, located in Eastern India, faces escalating flood risks due to its complex hydrology and geomorphology, threatening socioeconomic environmental stability. This study presents a novel approach susceptibility (FS) mapping updates the region's inventory. Multitemporal Sentinel-1 (S1) SAR images (2020-2022) were processed using U-Net transfer learning model generate water body frequency map, which was integrated with Global Flood Dataset (2000-2018) refined through grid-based classification create an updated Eleven geospatial layers, including elevation, slope, soil moisture, precipitation, type, NDVI, Land Use Cover (LULC), wind speed, drainage density, runoff, used as conditioning factors (FCFs) develop hybrid FS approach. integrates Fuzzy Analytic Hierarchy Process (FuzzyAHP) six machine (ML) algorithms models FuzzyAHP-RF, FuzzyAHP-XGB, FuzzyAHP-GBM, FuzzyAHP-avNNet, FuzzyAHP-AdaBoost, FuzzyAHP-PLS. Future trends (1990-2030) projected CMIP6 data under SSP2-4.5 SSP5-8.5 scenarios MIROC6 EC-Earth3 ensembles. SHAP algorithm identified LULC, type most influential FCFs, contributing over 60 % susceptibility. Results show that 31.10 of basin is highly susceptible flooding, western regions at greatest risk low elevation high density. projections indicate 30.69 area will remain vulnerable, slight increase SSP5-8.5. Among models, FuzzyAHP-XGB achieved highest accuracy (AUC = 0.970), outperforming FuzzyAHP-GBM 0.968) FuzzyAHP-RF 0.965). experimental results showed proposed can provide spatially well-distributed inventory derived from freely available remote sensing (RS) datasets robust framework for long-term assessment ML techniques. These findings offer critical insights improving management mitigation strategies basin.

Язык: Английский

---

Integrating Satellite Images and Machine Learning for Flood Prediction and Susceptibility Mapping for the Case of Amibara, Awash Basin, Ethiopia

Remote Sensing, Год журнала: 2024, Номер 16(12), С. 2163 - 2163

Опубликована: Июнь 14, 2024

Flood is one of the most destructive natural hazards affecting environment and socioeconomic system world. The effects are higher in developing countries due to their vulnerability disaster limited coping capacity. Awash basin flood-prone basins Ethiopia where frequency severity flooding has been increasing. Amibara district flood-affected areas basin. To minimize flooding, reliable up-to-date information on highly required. However, flood monitoring forecasting systems lacking including Therefore, this study aimed (i) identify important causative factors, (ii) evaluate performance random forest (RF), linear regression, support vector machine (SVM), long short-term memory (LSTM) learning models for prediction susceptibility mapping area. For modeling, nine factors were considered, namely elevation, slope, aspect, curvature, topographic wetness index, soil texture, rainfall, land use/land cover, curve number. Pearson correlation coefficient gain ratio (InGR) techniques used relative importance factors. trained tested using 400 historic points collected from 10 September 2020 Sentinel 2 image, during which a event occurred Multiple metrics, precession, recall, F1-score, accuracy, receiver operating characteristics (area under curve), models. results showed that all considered important; slope more while number, texture less important. Furthermore, outperformed predicting area whereas regression model next best RF. SVM performed poorly mapping. integration satellite field datasets coupled with state-of-the-art-machine novel approaches thus improved accuracy Such methodology improves state-of-the-art knowledge fills gaps traditional techniques. Thus, can provide crucial informed decision-making processes designing control strategies risk management.

Язык: Английский

---

A novel flood conditioning factor based on topography for flood susceptibility modeling

Geoscience Frontiers, Год журнала: 2024, Номер 16(1), С. 101960 - 101960

Опубликована: Ноя. 1, 2024

Язык: Английский

---

The ensemble learning combined with the pruning model reveals the spectral response mechanism of tidal flat mapping in China

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103104 - 103104

Опубликована: Март 1, 2025

Язык: Английский

---

FloodCNN-BiLSTM: Predicting flood events in urban environments

Engineering Analysis with Boundary Elements, Год журнала: 2025, Номер 177, С. 106277 - 106277

Опубликована: Апрель 28, 2025

Язык: Английский

---

Integrated Remote Sensing and Deep Learning Models for Flash Flood Detection Based on Spatio-temporal Land Use and Cover Changes in the Mediterranean Region

Environmental Modeling & Assessment, Год журнала: 2025, Номер unknown

Опубликована: Май 9, 2025

Язык: Английский

---