Landslide susceptibility mapping: A comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey)

Date

2005-07-01

Author

Yesilnacar, E
Topal, Tamer

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

229
views

0
downloads

Landslide susceptibility mapping is one of the most critical issues in Turkey. At present, geotechnical models appear to be useful only in areas of limited extent, because it is difficult to collect geotechnical data with appropriate resolution over larger regions. In addition, many of the physical variables that are necessary for running these models are not usually available, and their acquisition is often very costly. Conversely, statistical approaches are currently pursued to assess landslide hazard over large regions. However, these approaches cannot effectively model complicated landslide hazard problems, since there is a non-linear relationship between nature-based problems and their triggering factors. Most of the statistical methods are distribution-based and cannot handle multisource data that are commonly collected from nature. In this respect, logistic regression and neural networks provide the potential to overcome drawbacks and to satisfy more rigorous landslide susceptibility mapping requirements. In the Hendek region of Turkey, a segment of natural gas pipeline was damaged due to landslide. Re-routing of the pipeline is planned but it requires preparation of landslide susceptibility map. For this purpose, logistic regression analysis and neural networks are applied to prepare landslide susceptibility map of the problematic segment of the pipeline. At the end, comparative analysis is conducted on the strengths and weaknesses of both techniques. Based on the higher percentages of landslide bodies predicted in very high and high landslide susceptibility zones, and compatibility between field observations and the important factors obtained in the analyses, the result found by neural network is more realistic.

Subject Keywords

Geotechnical Engineering and Engineering Geology, Geology

URI

https://hdl.handle.net/11511/39197

Journal

ENGINEERING GEOLOGY

DOI

https://doi.org/10.1016/j.enggeo.2005.02.002

Collections

Department of Geological Engineering, Article

Suggestions

OpenMETU
Core

Geotechnical characteristics of residual soils in rainfall-triggered landslides in Rize, Turkey Üyetürk, Celal Emre; Huvaj Sarıhan, Nejan; Bayraktaroğlu, Hilmi; Huseyinpasaoglu, Mustafa (Elsevier BV, 2020-01-01) © 2019 Elsevier B.V.Every year, hundreds of landslides are triggered by rainfall in the city of Rize, northern Turkey, resulting in casualties and devastating social and economic consequences. Although these landslides have been observed every year, for a long time in Rize, there is limited data on characteristics of these soils in the literature. Characterizing these soils is of paramount importance for numerical modeling of the landslide mechanisms, for stabilization works, for landslide susceptibility ma...
Displacement-based fragility functions for low- and mid-rise ordinary concrete buildings Akkar, S; Sucuoğlu, Haluk; Yakut, Ahmet (SAGE Publications, 2005-11-01) Fragility functions are determined for low- and mid-rise ordinary concrete buildings, which constitute the most vulnerable construction type in Turkey as well as several other countries prone to earthquakes. A hybrid approach is employed where building capacities are obtained from field data and their dynamic responses are calculated by response history analyses. Field data consists of 32 sample buildings representing the general characteristics of two-to five-story substandard reinforced concrete buildings...
Seismic Resistance Evaluation of Traditional Ottoman Timber-Frame Himis Houses: Frame Loadings and Material Tests Aktas, Yasemin Didem; Akyüz, Uğurhan; Türer, Ahmet; Erdil, Barış; Şahin Güçhan, Neriman (SAGE Publications, 2014-11-01) Traditional Ottoman timber-frame houses ("himis") form the major part of the cultural heritage structures in Turkey. There are many studies in the literature regarding the seismic performance of himis houses, which claim that these structures have an inherent seismically resistant property. However, these studies lack a quantitative engineering approach and are based on observations made after contemporary earthquakes. This study presents the results of the seismic resistance evaluation of traditional Ottom...
Geotechnical rock-mass evaluation of the Anamur dam site, Turkey Ozsan, A; Karpuz, Celal (Elsevier BV, 1996-03-01) This paper describes a feasibility-level geotechnical evaluation carried out at Anamur dam site, in terms of stability analysis of dam foundation, excavation slopes and a diversion tunnel. The proposed Anamur dam will be built across the Anamur river on the Alanya metamorphic series which consists of phyllite, schist and slate units at the site. Geotechnical investigations included drilling for core, pumping tests, sampling for laboratory testing, and a detailed discontinuity survey.
Tectonic evolution of the Gediz Graben: field evidence for an episodic, two-stage extension in western Turkey Bozkurt, Erdin (Cambridge University Press (CUP), 2004-01-01) Western Turkey is one of the most spectacular regions of widespread active continental extension in the world. The most prominent structures of this region are E-W-trending grabens (e.g. Gediz and Buyuk Menderes grabens) and intervening horsts, exposing the Menderes Massif. This paper documents the result of a recent field campaign (field geological mapping and structural analysis) along the southern margin of the modern Gediz Graben of Pliocene (similar to 5 Ma) age. This work provides field evidence that ...

Citation Formats

E. Yesilnacar and T. Topal, “Landslide susceptibility mapping: A comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey),” ENGINEERING GEOLOGY, pp. 251–266, 2005, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/39197.