American Society of Civil Engineers


Study on the Forecasting Models of Slope Stability under Data Mining


by Junhong Li, (State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering of Hohai University, P.O. Box 210098, Nanjing, PR China E-mail: ljh@hhu.edu.cn) and Fei Wang, (College of Water Conservancy and Hydropower Engineering, Hohai University, P.O. Box 210098, Nanjing, PR China E-mail: orangen@sina.com)
Section: Symposium 2: Advanced Materials for Sustainable Development, pp. 765-776, (doi:  http://dx.doi.org/10.1061/41096(366)77)

     Access full text
     Purchase Subscription
     Permissions for Reuse  

Document type: Conference Proceeding Paper
Part of: Earth and Space 2010: Engineering, Science, Construction, and Operations in Challenging Environments
Abstract: In this paper, the artificial neural network (ANN) and support vector machine (SVM) methods which are commonly used in data mining are introduced, both the advantages and disadvantages of between them are detailedly discussed in engineering application. Two forecasting models based on ANN and SVM are derived from the main factors for slope stability, in which the nonlinear relations between slope stability and main influencing factors are obtained from the finite empirical data. Compared the results with maximum likelihood estimation in details, it is concluded that SVM forecasting model has more advantages to slope stability evaluation over ANN model under the condition of limited data.


ASCE Subject Headings:
Forecasting
Slope stability
Data collection
Neural networks