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

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 136, P. 104357 - 104357

Published: Jan. 14, 2025

Language: Английский

---

A machine learning-based approach for flash flood susceptibility mapping considering rainfall extremes in the northeast region of Bangladesh

Advances in Space Research, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 1, 2024

Language: Английский

---

A Comparison of the AHP and BWM Models for the Flash Flood Susceptibility Assessment: A Case Study of the Ibar River Basin in Montenegro

Water, Journal Year: 2025, Volume and Issue: 17(6), P. 844 - 844

Published: March 14, 2025

Assessing flash flood susceptibility is crucial for disaster management, yet Montenegro lacks research using geoinformation technologies. In northeastern Montenegro, the Ibar River Basin, mainly in Rožaje, has a well-developed hydrological network with torrential streams prone to flooding. This study compares two multi-criteria GIS decision analysis (GIS–MCDA) methodologies, Analytic Hierarchy Process (AHP) and Best-Worst Method (BWM), assessing susceptibility. The uses Flash Flood Susceptibility Index (FFSI), integrating geoenvironmental climatic factors. criteria considered include terrain slope, distance from drainage network, geology, land cover, density, bare soil index, BIO16 variable, which represents mean monthly precipitation of wettest quarter enhance pattern assessment. AHP model classifies 2.78% area as high very susceptibility, while BWM identifies 3.21% these categories. Both models perform excellently based on AUC values, minor, non-significant differences. Sensitivity shows provides more stable weight distribution, whereas sensitive changes, emphasizing dominant strongly. introduces first time modeling, demonstrating its suitability key novelty lies comparative AHP, highlighting differences distribution stability.

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

---

Advancing Agricultural Land Suitability in Urbanized Semi-Arid Environments: Insights from Geospatial and Machine Learning Approaches

ISPRS International Journal of Geo-Information, Journal Year: 2024, Volume and Issue: 13(12), P. 436 - 436

Published: Dec. 3, 2024

Rising food demands are increasingly threatened by declining crop yields in urbanizing riverine regions of Southern Asia, exacerbated erratic weather patterns. Optimizing agricultural land suitability (AgLS) offers a viable solution for sustainable productivity such challenging environments. This study integrates remote sensing and field-based geospatial data with five machine learning (ML) algorithms—Naïve Bayes (NB), extra trees classifier (ETC), random forest (RF), K-nearest neighbors (KNN), support vector machines (SVM)—alongside land-use/land-cover (LULC) considerations the food-insecure Dharmapuri district, India. A grid searches optimized hyperparameters using factors as slope, rainfall, temperature, texture, pH, electrical conductivity, organic carbon, available nitrogen, phosphorus, potassium, calcium carbonate. The tuned ETC model showed lowest root mean squared error (RMSE = 0.15), outperforming RF 0.18), NB 0.20), SVM 0.22), KNN 0.23). AgLS-ETC map identified 29.09% area highly suitable (S1), 19.06% moderately (S2), 16.11% marginally (S3), 15.93% currently unsuitable (N1), 19.21% permanently (N2). By incorporating Landsat-8 derived LULC to exclude forests, water bodies, settlements, these estimates were adjusted 19.08% 14.45% 11.40% 10.48% 9.58% Focusing on model, followed land-use analysis, provides robust framework optimizing planning, ensuring protection ecological social developing countries.

Language: Английский

---

SAR-driven flood inventory and multi-factor ensemble susceptibility modelling using machine learning frameworks

Geomatics Natural Hazards and Risk, Journal Year: 2024, Volume and Issue: 15(1)

Published: Oct. 16, 2024

Climate change has substantially increased both the occurrence and intensity of flood events, particularly in Indian subcontinent, exacerbating threats to human populations economic infrastructure. The present research employed novel ML models—LR, SVM, RF, XGBoost, DNN, Stacking Ensemble—developed Python environment leveraged 18 flood-influencing factors delineate flood-prone areas with precision. A comprehensive inventory, obtained from Sentinel-1 Synthetic Aperture Radar (SAR) data using Google Earth Engine (GEE) platform, provided empirical for entire model training validation. Model performance was assessed precision, recall, F1-score, accuracy, ROC-AUC metrics. results highlighted Ensemble's superior predictive ability (0.965), followed closely by, XGBoost (0.934), DNN (0.929), RF (0.925), LR (0.921), SVM (0.920) respectively, establishing feasibility applications disaster management. maps depicting susceptibility flooding generated by current provide actionable insights decision-makers, city planners, authorities responsible management, guiding infrastructural community resilience enhancements against risks.

Language: Английский

---

Comprehensive evaluation of machine learning algorithms for flood susceptibility mapping in Wardha River sub-basin, India

Acta Geophysica, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 5, 2024

Language: Английский

---