Flood Susceptibility Mapping Using Remote Sensing and Integration of Decision Table Classifier and Metaheuristic Algorithms DOI Open Access
Shavan Askar, Sajjad Zeraat Peyma, Mohanad Mohsen Yousef

и другие.

Water, Год журнала: 2022, Номер 14(19), С. 3062 - 3062

Опубликована: Сен. 28, 2022

Flooding is one of the most prevalent types natural catastrophes, and it can cause extensive damage to infrastructure environment. The primary method flood risk management susceptibility mapping (FSM), which provides a quantitative assessment region’s vulnerability flooding. objective this study develop new ensemble models for FSM by integrating metaheuristic algorithms, such as genetic algorithms (GA), particle swarm optimization (PSO), harmony search (HS), with decision table classifier (DTB). proposed were applied in province Sulaymaniyah, Iraq. Sentinel-1 synthetic aperture radar (SAR) data satellite images used monitoring (on 27 July 2019), 160 occurrence locations prepared modeling. For training validation datasets, coupled 1 flood-influencing parameters (slope, altitude, aspect, plan curvature, distance from rivers, land cover, geology, topographic wetness index (TWI), stream power (SPI), rainfall, normalized difference vegetation (NDVI)). certainty factor (CF) approach was determine spatial association between effective floods, resulting weights employed modeling inputs. According pairwise consistency technique, NDVI altitude are significant factors area under receiver operating characteristic (AUROC) curve evaluate accuracy effectiveness models. DTB-GA model found be accurate (AUC = 0.889), followed DTB-PSO 0.844) DTB-HS 0.812). This research’s hybrid provide reliable estimate risk, maps early-warning control systems.

Язык: Английский

Explainable step-wise binary classification for the susceptibility assessment of geo-hydrological hazards DOI
Ömer Ekmekcioğlu, Kerim Koç

CATENA, Год журнала: 2022, Номер 216, С. 106379 - 106379

Опубликована: Май 19, 2022

Язык: Английский

Процитировано

44
A hybrid of ensemble machine learning models with RFE and Boruta wrapper-based algorithms for flash flood susceptibility assessment DOI Creative Commons
A. Habibi, M. R. Delavar,

Mohammad Sadegh Sadeghian

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2023, Номер 122, С. 103401 - 103401

Опубликована: Июль 14, 2023

Flash floods are among the world most destructive natural disasters, and developing optimum hybrid Machine Learning (ML) models for flash flood susceptibility (FFS) modeling remains a challenge. This study proposed novel intelligence algorithms based on of several ensemble ML (i.e., Bagged Flexible Discriminant Analysis (BAFDA), Extreme Gradient Boosting (XBG), Rotation Forest (ROF) Boosted Generalized Additive Model (BGAM)) wrapper-based factor optimization Recursive Feature Elimination (RFE) Boruta) to improve accuracy FFS mapping at Neka-Haraz watershed in Iran. In addition, Random Search (RS) method is meta-optimization developed hyper-parameters. considers 20 conditioning factors (CgFs) 380 non-flood locations create geospatial database. The performance each model was evaluated by area under receiver operating characteristic (ROC) curve (AUC) validation methods, such as efficiency. demonstrated good performance, with BGAM-Boruta achieving highest (AUC = 0.953, Efficiency 0.910), followed ROF-Boruta 0.952), ROF-RFE 0.951), BAFDA-Boruta 0.950), BGAM-RFE ROF 0.949), BGAM 0.948), BAFDA-RFE 0.943), XGB-Boruta BAFDA 0.939), XGB-RFE 0.938) XGB 0.911). model, regional coverage about 46% high very areas. Moreover, revealed that distance river, slope, rainfall, altitude, road CgFs significant this region.

Язык: Английский

Процитировано

44
Multi-hazard spatial modeling via ensembles of machine learning and meta-heuristic techniques DOI Creative Commons
Mojgan Bordbar, Hossein Aghamohammadi, Hamid Reza Pourghasemi

и другие.

Scientific Reports, Год журнала: 2022, Номер 12(1)

Опубликована: Янв. 27, 2022

Abstract Considering the large number of natural disasters on planet, many areas in world are at risk these hazards; therefore, providing an integrated map as a guide for multiple hazards can be applied to save human lives and reduce financial losses. This study designed multi-hazard three important (earthquakes, floods, landslides) identify endangered Kermanshah province located western Iran using ensemble SWARA-ANFIS-PSO SWARA-ANFIS-GWO models. In first step, flood landslide inventory maps were generated at-risk areas. Then, occurrence places each hazard divided into two groups training susceptibility models (70%) testing (30%). Factors affecting hazards, including altitude, slope aspect, degree, plan curvature, distance rivers, roads, faults, rainfall, lithology, land use, used generate maps. The SWARA method was weigh subclasses influencing factors floods landslides. addition, peak ground acceleration (PGA) investigate earthquakes area. next ANFIS machine learning algorithm combination with PSO GWO meta-heuristic algorithms train data, separately hazards. predictive ability implemented validated receiver operating characteristics (ROC), root mean square error (RMSE), (MSE) methods. results showed that model had best performance generating ROC = 0.936, RMS 0.346, MSE 0.120. Furthermore, this excellent (ROC 0.894, 0.410, 0.168) map. Finally, PGA combined, (MHM) obtained Province. by managers planners practical sustainable development.

Язык: Английский

Процитировано

42
A comparison of performance measures of three machine learning algorithms for flood susceptibility mapping of river Silabati (tropical river, India) DOI
Md Hasanuzzaman, Aznarul Islam, Biswajit Bera

и другие.

Physics and Chemistry of the Earth Parts A/B/C, Год журнала: 2022, Номер 127, С. 103198 - 103198

Опубликована: Июль 11, 2022

Язык: Английский

Процитировано

42
Flood Susceptibility Mapping Using Remote Sensing and Integration of Decision Table Classifier and Metaheuristic Algorithms DOI Open Access
Shavan Askar, Sajjad Zeraat Peyma, Mohanad Mohsen Yousef

и другие.

Water, Год журнала: 2022, Номер 14(19), С. 3062 - 3062

Опубликована: Сен. 28, 2022

Flooding is one of the most prevalent types natural catastrophes, and it can cause extensive damage to infrastructure environment. The primary method flood risk management susceptibility mapping (FSM), which provides a quantitative assessment region’s vulnerability flooding. objective this study develop new ensemble models for FSM by integrating metaheuristic algorithms, such as genetic algorithms (GA), particle swarm optimization (PSO), harmony search (HS), with decision table classifier (DTB). proposed were applied in province Sulaymaniyah, Iraq. Sentinel-1 synthetic aperture radar (SAR) data satellite images used monitoring (on 27 July 2019), 160 occurrence locations prepared modeling. For training validation datasets, coupled 1 flood-influencing parameters (slope, altitude, aspect, plan curvature, distance from rivers, land cover, geology, topographic wetness index (TWI), stream power (SPI), rainfall, normalized difference vegetation (NDVI)). certainty factor (CF) approach was determine spatial association between effective floods, resulting weights employed modeling inputs. According pairwise consistency technique, NDVI altitude are significant factors area under receiver operating characteristic (AUROC) curve evaluate accuracy effectiveness models. DTB-GA model found be accurate (AUC = 0.889), followed DTB-PSO 0.844) DTB-HS 0.812). This research’s hybrid provide reliable estimate risk, maps early-warning control systems.

Язык: Английский

Процитировано

41