Landslide susceptibility mapping using Genetic Algorithm for the Rule Set Production (GARP) model

Adineh, Fatemeh; Motamedvaziri, Baharak; Hasan, Ahmadi; Moeini, Abolfazl

doi:10.1007/s11629-018-4833-5

Cited by 20 publications

(15 citation statements)

References 115 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the performance of the different algorithms in the computation of spatial landslide probability distribution is still poorly known. More precisely, as shown in previous studies, the GARP algorithm has good performance in spatial modeling (Stockman et al 2006;Sánchez-Flores, 2007;Wang et al 2010;Adineh et al 2018). However, this model has been rarely used in landslide studies.…”

Section: Introductionmentioning

confidence: 75%

“…For instance, GIS-based multi-criteria decision-making approaches, such as Fuzzy Analytic Hierarchy Process (FAHP), have been applied to identifying areas susceptible to damaging landslides (Ercanoglu & Gokceoglu 2002;Gorsevski et al 2006;Gorsevski & Jankowski 2010;Vahidnia et al 2010;Pourghasemi et al 2012;Feizizadeh et al 2013;Tazik et al 2014;Roodposhti et al 2014;Feizizadeh et al 2014;Zhao et al 2017;El Bcharia et al 2019;Roy & Saha, 2019). Moreover, various machine learning algorithms, including support vector machine (SVM) (Pourghasemi & Kerle 2016;Youssef et al 2016;Pandy et al 2018), Maximum Entropy (MaxEnt) (Park, 2015;Kornejady et al 2017;Pandy et al 2018;Mokhtari & Abedian, 2019), Genetic Algorithm Rule-Set Production (GARP) (Stockwell, 1999;Rahmati et al 2019;Adineh et al 2018) and Random forest (RF) (Goetz et al 2015;Pourghasemi & Kerle 2016;Sevgen et al 2019;Pourghasemi et al 2020), and also, deep learning techniques including recurrent neural network (RNN) and Convolution Neural Networks (CNN) (Xiao et al 2018; assessing have been applied to Ngo et al 2021) ; Mohan et al 2020;Bui et al 2020Bui et al et al 2019; Ghorbanzadeh landslide hazard within a broad range of geographical locations and conditions of soil type, topography, land use/land cover, climate and anthropogenic influences (for a recent discussion, see Achour and Pourghasemi, 2020). However, the performance of the different algorithms in the computation of spatial landslide probability distribution is still poorly known.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid model using data mining and multi-criteria decision-making methods for landslide risk mapping at Golestan Province, Iran

et al. 2021

View full text Add to dashboard Cite

The accurate modelling of landslide risk is essential pre-requisite for the development of reliable landslide control and mitigation strategies. However, landslide risk depends on the poorly known environmental and socioeconomic factors for regional patterns of landslide occurrence probability and vulnerability, which constitute still a matter of research. Here, a hybrid model is described that couples data mining and multi-criteria decision-making methods for hazard and vulnerability mapping and presents its application to landslide risk assessment in Golestan Province, Northeastern Iran. To this end, landslide probability is mapped using three state-of-the-art machine learning (ML) algorithms -Maximum Entropy, Support Vector Machine and Genetic Algorithm for Rule Set Productionand combine the results with Fuzzy Analytical Hierarchy Process computations of vulnerability to obtain the landslide risk map. Based on obtained results, a discussion is presented on landslide probability as a function of the main relevant human-environmental conditioning factors in Golestan Province. In particular, from the response curves of the machine learning algorithms, it can be found that the probability of landslide occurrence decreases nearly exponentially with the distance to the next road, fault or river. Specifically, the results indicated that ≈ exp(− ), where the length-scale is about 0.0797 km − for road, 0.108 km − for fault and 0.734 km − for river. Furthermore, according to the results, follows, approximately, a lognormal function of elevation, while the equation = 0 − • ( − 0 ) 2 fits well the dependence of landslide modeling on the 2 slope-angle , with 0 ≈ 0.64, ≈ 25.6° and | | ≈ 6.6 × 10 −4 . However, the highest predicted landslide risk levels in Golestan Province are located in the south and southwest areas surrounding Gorgan City, owing to the combined effect of dense local human occupation and strongly landslide-prone environmental conditions.Obtained results provide insights for quantitative modelling of landslide risk, as well as for priority planning in landslide risk management.

show abstract

Section: Introductionmentioning

confidence: 75%

Section: Introductionmentioning

confidence: 99%

A hybrid model using data mining and multi-criteria decision-making methods for landslide risk mapping at Golestan Province, Iran

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Dynamic analysis models are calculation schemes based on the physical mechanisms of events (Li andZhao 2019, Zhiyun et al 2020); hence, these models are limited to data from the test site or to the research and exploration of a single landslide area and thus cannot meet the requirements for investigating landslide groups in different geological environments (Shu-lin et al 2020. In contrast, logistic regression models employ mathematical statistics to perform logistic regression and determine the critical value of landslide rainfall and the probability of landslide occurrence (Yi-ting et al 2015, ADINEH et al 2018; however, this method is suitable only for smallscale quantitative research and cannot be used for different categories.…”

Section: Introductionmentioning

confidence: 99%

Time-Domain Correlation Quantitative Analysis Method of Regional Rainfall-Landslide Displacement Responses Based on a Time-Domain Correlation Model

Xie

Zhu

et al. 2021

Preprint

View full text Add to dashboard Cite

Landslide deformation is the most intuitive and effective characterization of the evolution of landslides and reveals their inherent risk. Considering the inadequacy of existing deformation monitoring data in the early warning of landslide hazards, resulting in insufficient disaster response times, this paper proposes a time-domain correlation model. Based on a regional rainfall-landslide deformation response analysis method, a time-domain correlation measure between regional rainfall and landslide deformation and a calculation method based on impulse response functions are proposed for prevalent rainfall-induced landslide areas, and the correlation with the rainfall-triggered landslide deformation mechanism is quantitatively modeled. Furthermore, using rainfall monitoring data to optimize the indicator system for landslide deformation monitoring and early warning significantly improves the preliminary warning based on landslide deformation. The feasibility of the method proposed in this paper is verified by analyzing the historical monitoring data of rainfall and landslide deformation at 15 typical locations in 5 landslide hidden hazard areas in Fengjie County, Chongqing city. (1) The correlation models for the XP landslide and XSP landslide involve a 5-day lagged correlation under a 56-day cycle and a 18-21-day lagged correlation under a 49-52-day cycle, which means that the deformation in the above areas can be modeled cyclically according to monitoring data, and early landslide warnings can be provided in advance with a lag time. (2) The correlation models for the TMS landslide and OT landslide show consistent correlations under a 48-50-day cycle and a 58-day cycle, which means that the deformation in the above areas can be predicted based on rainfall accumulation, and real-time warnings of future landslide deformation and displacement can be obtained. (3) The HJWC landslide presents a disorderly correlation pattern, which means that a preliminary landslide deformation warning cannot be provided based on rainfall alone; other monitoring data need to be supplemented and analyzed.

show abstract

“…Therefore, these sorts of methods can be integrated with various objective algorithms to reduce the error. For this purpose, many researchers have recently tried to apply artificial intelligence algorithms, such as an adaptive neuro fuzzy inference system (ANFIS) [24][25][26] and evolutionary algorithms [27][28][29][30], in geological studies, especially seismic vulnerability assessment, with an emphasis on machine learning algorithms [31].…”

Section: Introductionmentioning

confidence: 99%

SEVUCAS: A Novel GIS-Based Machine Learning Software for Seismic Vulnerability Assessment

et al. 2019

View full text Add to dashboard Cite

Since it is not possible to determine the exact time of a natural disaster’s occurrence and the amount of physical and financial damage on humans or the environment resulting from their event, decision-makers need to identify areas with potential vulnerability in order to reduce future losses. In this paper, a GIS-based open source software entitled Seismic-Related Vulnerability Calculation Software (SEVUCAS), based on the Step-wise Weight Assessment Ratio Analysis (SWARA) method and geographic information system, has been developed to assess seismic vulnerability by considering four groups of criteria (i.e., geotechnical, structural, socio-economic, and physical distance to needed facilities and away from dangerous facilities). The software was developed in C# language using ArcGIS Engine functions, which provide enhanced visualization as well as user-friendly and automatic software for the seismic vulnerability assessment of buildings. Weighting of the criteria (indicators) and alternatives (sub-indicators) was done using SWARA. Also, two interpolation methods based on a radial basis function (RBF) and teaching–learning-based optimization (TLBO) were used to optimize the weights of the criteria and the classes of each alternative as well. After weighing the criteria and alternatives, the weighted overlay analysis was used to determine the final vulnerability map in the form of contours and statistical data. The difference between this software and similar ones is that people with a low level of knowledge in the area of earthquake crisis management can use it to determine and estimate the seismic vulnerabilities of their houses. This visualized operational forecasting software provides an applicable tool for both government and people to make quick and correct decisions to determine higher priority structures for seismic retrofitting implementation.

show abstract

Landslide susceptibility mapping using Genetic Algorithm for the Rule Set Production (GARP) model

Cited by 20 publications

References 115 publications

A hybrid model using data mining and multi-criteria decision-making methods for landslide risk mapping at Golestan Province, Iran

A hybrid model using data mining and multi-criteria decision-making methods for landslide risk mapping at Golestan Province, Iran

Time-Domain Correlation Quantitative Analysis Method of Regional Rainfall-Landslide Displacement Responses Based on a Time-Domain Correlation Model

SEVUCAS: A Novel GIS-Based Machine Learning Software for Seismic Vulnerability Assessment

Contact Info

Product

Resources

About