Econ. Environ. Geol. 2002; 35(1): 67-74

Published online February 28, 2002

© THE KOREAN SOCIETY OF ECONOMIC AND ENVIRONMENTAL GEOLOGY

Weight Determination of Landslide Factors Using Artificial Neural Networks

Joo-Hyung Ryu1, Saro Lee2 and Joong-Sun Won1*

1Department of Earth System Sciences, Yonsei University, 134, Shinchon-Dong, Seodaemun-Gu, Seoul 120-749, Korea
2National Geoscience Information Center, Korea Institute of Geoscience and Mineral Resources, 30, Kajeong-Dong, Taejeon, 305-350, Korea

Correspondence to :

Joong-Sun Won

jswon@yonsei.ac.kr

Received: December 21, 2001; Accepted: February 21, 2002

Abstract

The purpose of this study is to determine the weights of the factors for landslide susceptibility analysis using artificial neural networks. Landslide locations were identified from interpretation of aerial photographs, field survey data, and topography. The landslide-related factors such as topographic slope, topographic curvature, soil drainage, soil effective thickness, soil texture, wood age and wood diameter were extracted from the spatial database in study area, Yongin. Using these factors, the weights of neural networks were calculated by backpropagation training algorithm and were used to determine the weight of landslide factors. Therefore, by interpreting the weights after training, the weight of each landslide factor can be ranked based on its contribution to the classification. The highest
weight is topographic slope that is 5.33 and topographic curvature and soil texture are 1 and 1.17, respectively. Weight determination using backprogpagation algorithms can be used for overlay analysis of GIS so the factor that have low weight can be excluded in future analysis to save computation time.

Keywords GIS, landslide, artificial neural network, backpropagation algorithm, weight determination

Article

Econ. Environ. Geol. 2002; 35(1): 67-74

Published online February 28, 2002

Copyright © THE KOREAN SOCIETY OF ECONOMIC AND ENVIRONMENTAL GEOLOGY.

Weight Determination of Landslide Factors Using Artificial Neural Networks

Joo-Hyung Ryu1, Saro Lee2 and Joong-Sun Won1*

1Department of Earth System Sciences, Yonsei University, 134, Shinchon-Dong, Seodaemun-Gu, Seoul 120-749, Korea
2National Geoscience Information Center, Korea Institute of Geoscience and Mineral Resources, 30, Kajeong-Dong, Taejeon, 305-350, Korea

Correspondence to:

Joong-Sun Won

jswon@yonsei.ac.kr

Received: December 21, 2001; Accepted: February 21, 2002

Abstract

The purpose of this study is to determine the weights of the factors for landslide susceptibility analysis using artificial neural networks. Landslide locations were identified from interpretation of aerial photographs, field survey data, and topography. The landslide-related factors such as topographic slope, topographic curvature, soil drainage, soil effective thickness, soil texture, wood age and wood diameter were extracted from the spatial database in study area, Yongin. Using these factors, the weights of neural networks were calculated by backpropagation training algorithm and were used to determine the weight of landslide factors. Therefore, by interpreting the weights after training, the weight of each landslide factor can be ranked based on its contribution to the classification. The highest
weight is topographic slope that is 5.33 and topographic curvature and soil texture are 1 and 1.17, respectively. Weight determination using backprogpagation algorithms can be used for overlay analysis of GIS so the factor that have low weight can be excluded in future analysis to save computation time.

Keywords GIS, landslide, artificial neural network, backpropagation algorithm, weight determination

    KSEEG
    Dec 31, 2024 Vol.57 No.6, pp. 665~835

    Stats or Metrics

    Share this article on

    • kakao talk
    • line

    Related articles in KSEEG

    Economic and Environmental Geology

    pISSN 1225-7281
    eISSN 2288-7962
    qr-code Download