Spatial analysis of flood susceptibility in Coastal area of Pakistan using machine learning models and SAR imagery

Environmental Earth Sciences, Journal Year: 2025, Volume and Issue: 84(5)

Published: Feb. 18, 2025

Language: Английский

---

A Hybrid Multi-Hazard Susceptibility Assessment Model for a Basin in Elazig Province, Türkiye

International Journal of Disaster Risk Science, Journal Year: 2023, Volume and Issue: 14(2), P. 326 - 341

Published: March 29, 2023

Abstract Preparation of accurate and up-to-date susceptibility maps at the regional scale is mandatory for disaster mitigation, site selection, planning in areas prone to multiple natural hazards. In this study, we proposed a novel multi-hazard assessment approach that combines expert-based supervised machine learning methods landslide, flood, earthquake hazard assessments basin Elazig Province, Türkiye. To produce landslide map, an ensemble algorithm, random forest, was chosen because its known performance similar studies. The modified analytical hierarchical process method used flood map by using factor scores were defined specifically area study. seismic assessed ground motion parameters based on Arias intensity values. univariate synthesized with Mamdani fuzzy inference system membership functions designated expert. results show forest provided overall accuracy 92.3% mapping. Of study area, 41.24% found multi-hazards (probability value > 50%), but southern parts are more susceptible. model suitable although expert intervention may be required optimizing algorithms.

Language: Английский

---

Applying a 1D Convolutional Neural Network in Flood Susceptibility Assessments—The Case of the Island of Euboea, Greece

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(14), P. 3471 - 3471

Published: July 10, 2023

The main scope of the study is to evaluate prognostic accuracy a one-dimensional convolutional neural network model (1D-CNN), in flood susceptibility assessment, selected test site on island Euboea, Greece. Logistic regression (LR), Naïve Bayes (NB), gradient boosting (GB), and deep learning (DLNN) are benchmark models used compare their performance with that 1D-CNN model. Remote sensing (RS) techniques collect necessary related data, whereas thirteen flash-flood-related variables were as predictive variables, such elevation, slope, plan curvature, profile topographic wetness index, lithology, silt content, sand clay distance faults, river network. Weight Evidence method was applied calculate correlation among flood-related assign weight value each variable class. Regression analysis multi-collinearity assess collinearity Shapley Additive explanations rank features by importance. evaluation process involved estimating ability all via classification accuracy, sensitivity, specificity, area under success rate curves (AUC). outcomes confirmed provided higher (0.924), followed LR (0.904) DLNN (0.899). Overall, 1D-CNNs can be useful tools for analyzing using remote high predictions.

Language: Английский

---

Flood hazard assessment in Yemen using a novel hybrid approach of Grey Wolf and Levenberg Marquardt optimizers

Geocarto International, Journal Year: 2023, Volume and Issue: 38(1)

Published: Aug. 3, 2023

This study aims to map flood susceptibility in the Qaa'Jahran watersheds located Dhamar, Yemen, using geoprocessing and computational techniques. Historical data SAR imagery were used monitor create a inventory map. The Artificial Neutral Network (ANN) was trained novel algorithm called GWO_LM, which is hybridization between Levenberg-Marquardt (LM) Grey Wolf Optimizer (GWO) meta-heuristic compared results with state of art machine learning algorithms. GWO_LM_ANN model exhibited excellent performance evaluation, achieving precision 97.92%, sensitivity 100%, specificity F1 score 98.95%, accuracy 98.75%, AUC 98.48. indicates that GWO_LM for training ANN enhanced searching process optimal weights, resulting outperforming other state-of-the-art models. findings hold significant implications disaster preparedness response watersheds, enabling targeted efficient non-structural solutions mitigate detrimental effects flash floods particularly sensitive locations. use previously unexplored represents notable advancement assessment, surpassing traditional methods offering insights existing literature.

Language: Английский

---

Application of convolutional neural networks based on Bayesian optimization to landslide susceptibility mapping of transmission tower foundation

Bulletin of Engineering Geology and the Environment, Journal Year: 2023, Volume and Issue: 82(2)

Published: Jan. 18, 2023

Language: Английский

---

Novel optimized deep learning algorithms and explainable artificial intelligence for storm surge susceptibility modeling and management in a flood-prone island

Natural Hazards, Journal Year: 2024, Volume and Issue: 120(6), P. 5099 - 5128

Published: Feb. 2, 2024

Language: Английский

---

One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(5), P. 4419 - 4440

Published: July 6, 2024

Abstract Flash floods rank among the most catastrophic natural disasters worldwide, inflicting severe socio-economic, environmental, and human impacts. Consequently, accurately identifying areas at potential risk is of paramount importance. This study investigates efficacy Deep 1D-Convolutional Neural Networks (Deep 1D-CNN) in spatially predicting flash floods, with a specific focus on frequent tropical cyclone-induced Thanh Hoa province, North Central Vietnam. The 1D-CNN was structured four convolutional layers, two pooling one flattened layer, fully connected employing ADAM algorithm for optimization Mean Squared Error (MSE) loss calculation. A geodatabase containing 2540 flood locations 12 influencing factors compiled using multi-source geospatial data. database used to train check model. results indicate that model achieved high predictive accuracy (90.2%), along Kappa value 0.804 an AUC (Area Under Curve) 0.969, surpassing benchmark models such as SVM (Support Vector Machine) LR (Logistic Regression). concludes highly effective tool modeling floods.

Language: Английский

---

A hybrid data-driven approach for rainfall-induced landslide susceptibility mapping: Physically-based probabilistic model with convolutional neural network

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 1, 2024

Language: Английский

---

Leveraging machine learning algorithms for improved disaster preparedness and response through accurate weather pattern and natural disaster prediction

Frontiers in Environmental Science, Journal Year: 2023, Volume and Issue: 11

Published: Nov. 2, 2023

Globally, communities and governments face growing challenges from an increase in natural disasters worsening weather extremes. Precision disaster preparation is crucial responding to these issues. The revolutionary influence that machine learning algorithms have strengthening catastrophe response systems thoroughly explored this paper. Beyond a basic summary, the findings of our study are striking demonstrate sophisticated powers forecasting variety patterns anticipating range catastrophes, including heat waves, droughts, floods, hurricanes, more. We get practical insights into complexities applications, which support enhanced effectiveness predictive models preparedness. paper not only explains theoretical foundations but also presents proof significant benefits provide. As result, results open door for governments, businesses, people make wise decisions. These accurate predictions catastrophes emerging may be used implement pre-emptive actions, eventually saving lives reducing severity damage.

Language: Английский

---

Flood hazard mapping using GIS-based statistical model in vulnerable riparian regions of sub-tropical environment

Geocarto International, Journal Year: 2023, Volume and Issue: 38(1)

Published: Nov. 20, 2023

Floods are a recurrent natural calamity that presents substantial hazards to human lives and infrastructure. The study indicates significant proportion of the area, specifically 27.05%, is classified as moderate flood risk zone (FRZ), while 20.78% designated high or very FRZ. region's low FRZ at 52.17%. GIS-based AHP model demonstrated exceptional predictive precision, achieving score 0.749 (74.90%) determined by AUC-ROC, widely used statistical evaluation tool. current has identified areas with in affected CD blocks, which situated low-lying plains, regions gentle slopes, drainage density, TWI, NDVI, MNDWI, population intensive agricultural land. findings this research offer perspectives for decision-makers, city planners, emergency management agencies devising efficient measures mitigate risks.

Language: Английский

---