A comparative study for landslide susceptibility mapping using GIS-based multi-criteria decision analysis (MCDA), logistic regression (LR) and association rule mining (ARM)

2016-03-25
ERENER, ARZU
MUTLU, ALEV
Düzgün, Hafize Şebnem
Show full item record
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
115
views
0
downloads
Landslide susceptibility mapping is one of the crucial stages of landslide hazard and risk assessment. Moreover, the susceptibility maps assist planners, local administrations, and decision makers in disaster planning. Various approaches have been applied in the literature to increase the accuracy of landslide susceptibility maps. The determination of suitable susceptibility mapping method plays critical role for obtaining required accuracy. In this study, the performances of three quantitative susceptibility mapping methods are evaluated. The logistic regression (LR) analysis is the typical example of statistical methods, while GIS-based multi-criteria decision analyses (MCDA) and association rule mining (ARM) are the examples of heuristic and data mining methods, respectively. The susceptibility maps based on the three methods are obtained for Savsat in Artvin province (NE Turkey) where the region has intense landslides. The landslide influencing parameters for the study area are lithology, land use/land cover, soil type, erosion, altitude, slope, aspect, distance to drainage, soil depth, distance to fault, distance to road. The models for the three methods are then compared and evaluated by using pixel-based evaluation metrics. Results showed that ARM provides a higher quality percent (QP), whereas percent of damage detection (PDD) is higher for LR method. The lowest QP is obtained by GIS-based MCDA. It is found that LR and ARM methods are better than GIS-based MCDA in modeling the landslide susceptibility and they can be integrated to obtain better performance.
GEOGRAPHICAL INFORMATION-SYSTEM, ARTIFICIAL NEURAL-NETWORKS, LIKELIHOOD RATIO, STATISTICAL-ANALYSIS, HAZARD ASSESSMENT, FREQUENCY RATIO, AREA, MULTIVARIATE, WEIGHTS, FUZZY
https://hdl.handle.net/11511/57283
ENGINEERING GEOLOGY
Department of Mining Engineering, Article

Suggestions

An integrated seismic hazard framework for liquefaction triggering assessment of earthfill dams' foundation soils
Ünsal Oral, Sevinç; Çetin, Kemal Önder; Department of Civil Engineering (2009)
Within the confines of this study, seismic soil liquefaction triggering potential of a dam foundation is assessed within an integrated probabilistic seismic hazard assessment framework. More specifically, the scheme presented hereby directly integrates effective stress-based seismic soil liquefaction triggering assessment with seismic hazard analysis framework, supported by an illustrative case. The proposed methodology successively, i) processes the discrete stages of probabilistic seismic hazard workflow ...
A regional scale quantitative risk assessment for landslides: case of Kumluca watershed in Bartin, Turkey
ERENER, ARZU; Düzgün, Hafize Şebnem (2013-02-01)
The paper proposes a methodology for quantitative landslide risk assessment for regional-scale analysis. Each component of risk, i.e., hazard, vulnerability, and consequence analysis, is quantitatively assessed. The developed landslide risk assessment methodology is tested in Kumluca watershed, in BartA +/- n, Turkey. Geographic information systems and remote sensing techniques are used to create landslide factor maps, to obtain susceptibility maps, hazard maps, elements at risk, and risk maps. Susceptibili...
An approach for seismic damage assessment of residential buildings /
Demirci, Ceren; Erberik, Murat Altuğ; Askan Gündoğan, Ayşegül; Department of Civil Engineering (2014)
For developing countries in earthquake-prone regions, two main issues in seismic damage estimation are identification of seismic hazard in the region of interest and up-to-date information of the existing building stock. This study proposes an approach to handle these key issues and to obtain reliable measures for regional seismic damage estimation. The approach makes use of the basic structural information for different types of construction. This information can be readily available or may have been obtai...
The Effects of Implementing Different Ground-motionLogic-tree Frameworks on Seismic Risk Assessment
Ay, Bekir Özer (null; 2018-06-21)
This study investigates the link between probabilistic seismic hazard assessment and corresponding loss estimations by using different ground-motion logic-tree frameworks from reliable large scale seismic hazard projects as well as the logic-tree framework established in this study. The predictive models selected for these logic trees are expected to represent the center, body and range of ground-motion intensity measure estimates. Regarding with the hazard component of risk assessment, the ground motion in...
Data driven bivariate landslide susceptibility assessment using geographical information systems: A method and application to Asarsuyu catchment, Turkey
Süzen, Mehmet Lütfi (2004-01-01)
In the last decades, landslide hazard assessment has attracted many researchers' attention. A number of parameters are suggested to be responsible to quantitatively explain the mechanism of landslides; many of these parameters are very important and factual. However, some data types and models are site-specific and could not be applied to different locations. Furthermore, the data stored in continuous parameter maps are divided into a number of classes arbitrarily, depending on the vision of the expert. Bas...
Citation Formats
A. ERENER, A. MUTLU, and H. Ş. Düzgün, “A comparative study for landslide susceptibility mapping using GIS-based multi-criteria decision analysis (MCDA), logistic regression (LR) and association rule mining (ARM),” ENGINEERING GEOLOGY, pp. 45–55, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/57283.
METU IIS - Integrated Information Service open@metu.edu.tr