A hybrid of ensemble machine learning models with RFE and Boruta wrapper-based algorithms for flash flood susceptibility assessment

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2023, Volume and Issue: 122, P. 103401 - 103401

Published: July 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.

Language: Английский

---

Leveraging machine learning and open-source spatial datasets to enhance flood susceptibility mapping in transboundary river basin

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: Feb. 9, 2024

Floods pose devastating effects on the resiliency of human and natural systems. flood risk management challenges are typically complicated in transboundary river basin due to conflicting objectives between multiple countries, lack systematic approaches data monitoring sharing, limited collaboration developing a unified system for hazard prediction communication. An open-source, low-cost modeling framework that integrates open-source models can help improve our understanding susceptibility inform design equitable strategies. This study datasets machine -learning techniques quantify across data-scare basin. The analysis focuses Gandak River Basin, spanning China, Nepal, India, where damaging recurring floods serious concern. is assessed using four widely used learning techniques: Long-Short-Term-Memory, Random Forest, Artificial Neural Network, Support Vector Machine. Our results exhibit improved performance Network Machine predicting maps, revealing higher vulnerability southern plains. demonstrates remote sensing prediction, mapping, environment.

Language: Английский

---

Flood susceptibility mapping using a novel integration of multi-temporal sentinel-1 data and eXtreme deep learning model

Geoscience Frontiers, Journal Year: 2024, Volume and Issue: 15(3), P. 101780 - 101780

Published: Jan. 9, 2024

Flash floods (FFs) are amongst the most devastating hazards in arid regions response to climate change and can cause loss of agricultural land, human lives infrastructure. One major challenges is high-intensity rainfall events affecting low-lying areas that vulnerable FF. Several works this field have been conducted using ensemble machine learning models geohydrological models. However, current advancement eXtreme deep learning, which named factorisation (xDeepFM), for FF susceptibility mapping (FSM) lacking literature. The study introduces a new model employs previously unapplied approach enhance FSM capturing severity floods. proposed has three main objectives: (i) During- after-flood effects assessed through flood detection techniques Sentinel-1 data. (ii) Flood inventory updated remote sensing-based methods. derived implemented next step. (iii) An map generated an xDeepFM model. Therefore, aims apply estimate susceptible 13 factors emirates Fujairah, UAE. performance metrics show recall 0.9488), F1-score 0.9107), precision (0.8756) overall accuracy 90.41%. applied compared with traditional models, specifically neural network (78%), support vector (85.4%) random forest (88.75%). Random achieves high accuracy, due its strong depends on contribution, dataset size quality, available computational resources. Comparatively, efficiently complicated prediction problems having non-collinearity huge datasets. obtained denotes narrow basins, lowland coastal riverbank up 5 km (Fujairah) highly prone FF, whilst alluvial plains Al Dhaid hilly Fujairah low probability. city bounded by high-rise steep hills Gulf Oman, elevate water levels during heavy rainfall. Four synchronised influencing factors, namely, rainfall, elevation, drainage density, distance from geomorphology, account nearly 50% total contributing very susceptibility. This offers platform planners decision makers take timely actions potential mitigating

Language: Английский

---

Identification of areas prone to flash-flood phenomena using multiple-criteria decision-making, bivariate statistics, machine learning and their ensembles

The Science of The Total Environment, Journal Year: 2020, Volume and Issue: 712, P. 136492 - 136492

Published: Jan. 7, 2020

Language: Английский

---

Using machine learning models, remote sensing, and GIS to investigate the effects of changing climates and land uses on flood probability

Journal of Hydrology, Journal Year: 2020, Volume and Issue: 595, P. 125663 - 125663

Published: Oct. 27, 2020

Language: Английский

---

GIS-Based Machine Learning Algorithms for Gully Erosion Susceptibility Mapping in a Semi-Arid Region of Iran

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(15), P. 2478 - 2478

Published: Aug. 2, 2020

In the present study, gully erosion susceptibility was evaluated for area of Robat Turk Watershed in Iran. The assessment performed using four state-of-the-art data mining techniques: random forest (RF), credal decision trees (CDTree), kernel logistic regression (KLR), and best-first tree (BFTree). To best our knowledge, KLR CDTree algorithms have been rarely applied to modeling. first step, from 242 locations that were identified, 70% (170 gullies) selected as training dataset, other 30% (72 considered result validation process. next twelve conditioning factors, including topographic, geomorphological, environmental, hydrologic estimate susceptibility. under ROC curve (AUC) used performance models. results revealed RF model had (AUC = 0.893), followed by 0.825), 0.808), BFTree 0.789) Overall, significantly better than others, which may support application this method a transferable areas. Therefore, we suggest RF, KLR, CDT models mapping prone areas assess their reproducibility.

Language: Английский

---

Spatial predicting of flood potential areas using novel hybridizations of fuzzy decision-making, bivariate statistics, and machine learning

Journal of Hydrology, Journal Year: 2020, Volume and Issue: 585, P. 124808 - 124808

Published: March 9, 2020

Language: Английский

---

Novel hybrid models between bivariate statistics, artificial neural networks and boosting algorithms for flood susceptibility assessment

Journal of Environmental Management, Journal Year: 2020, Volume and Issue: 265, P. 110485 - 110485

Published: April 20, 2020

Language: Английский

---

DEM resolution effects on machine learning performance for flood probability mapping

Journal of Hydro-environment Research, Journal Year: 2021, Volume and Issue: 40, P. 1 - 16

Published: Nov. 9, 2021

Floods are among the devastating natural disasters that occurred very frequently in arid regions during last decades. Accurate assessment of flood susceptibility mapping is crucial sustainable development. It helps respective authorities to prevent as much possible their irreversible consequences. The Digital Elevation Model (DEM) spatial resolution one most base layer factors for modeling Flood Probability Maps (FPMs). Therefore, main objective this study was assess influence DEMs 12.5 m (ALOS PALSAR) and 30 (ASTER) on accuracy probability prediction using three machine learning models (MLMs), including Random Forest (RF), Artificial Neural Network (ANN), Generalized Linear (GLM). This selected 14 causative independent variables, 220 locations were dependent variables. Dependent variables divided into training (70%) validation (30%) modeling. Receiver Operating Characteristic Curve (ROC), Kappa index, accuracy, other statistical criteria used evaluate models' accuracy. results showed resolving DEM alone cannot significantly affect regardless applied MLM independently model performance In contrast, such altitude, precipitation, distance from river have a considerable impact floods region. Also, evaluation RF (AUC12.5,30m = 0.983, 0.975) more accurate preparing FPM than ANN 0.949, 0.93) GLM 0.965, 0.949) models. study's solution-oriented findings might help water managers decision-makers make effective adaptation mitigation measures against potential flooding.

Language: Английский

---

An Overview of Multi-Criteria Decision Analysis (MCDA) Application in Managing Water-Related Disaster Events: Analyzing 20 Years of Literature for Flood and Drought Events

Water, Journal Year: 2021, Volume and Issue: 13(10), P. 1358 - 1358

Published: May 13, 2021

This paper provides an overview of multi-criteria decision analysis (MCDA) applications in managing water-related disasters (WRD). Although MCDA has been widely used natural disasters, it appears that no literature review conducted on the disaster management phases mitigation, preparedness, response, and recovery. Therefore, this fills gap by providing a bibliometric flood drought events. Out 818 articles retrieved from scientific databases, 149 were shortlisted analyzed using Preferred Reporting Items for Systematic Reviews Meta-analyses (PRISMA) approach. The results show significant growth last five years, especially Most focused mitigation phase DMP, while other recovery remained understudied. analytical hierarchy process (AHP) was most common technique used, followed mixed-method techniques TOPSIS. article concludes discussion identifying number opportunities future research use disasters.

Language: Английский

---