Probabilistic back analysis based on Bayesian and multi-output support vector machine for a high cut rock slope

Abstract Uncertainty of geomechanical parameters is an important consideration for rock engineering and has a very important influence on safety evaluation, design, and construction. Back analysis is a common method of determining geomechanical parameters but traditional deterministic back analysis cannot allow for consideration of this uncertainty. In this study, a new probabilistic back analysis method is proposed that integrates Bayesian methods and a multi-output support vector machine (B–MSVM). In this B–MSVM back analysis method, Bayesian was used to deal with the uncertainty of geomechanical parameters and a multi-output support vector machine (MSVM) was adopted to build the relationships between displacements and those parameters. The proposed method was applied to a high abutment rock slope at the Longtan hydropower station, China. At Longtan, the uncertainty of the two types of geomechanical parameters, Young's modulus and lateral pressure coefficients of in situ stress, were modeled as random variables. Based on the parameters identified by probabilistic back analysis, the computed displacements agreed closely with the measured displacement data monitored in the field. The result showed that B–MSVM presented the uncertainty of the geomechanical parameters reasonably. Further study indicated that the performance of B–MSVM could be improved greatly by updating field monitoring information regularly. The proposed method provides a significant new approach for probabilistic back analysis and contributes to the determination of realistic geomechanical parameters.

[1]  Pierpaolo Oreste,et al.  Back-Analysis Techniques for the Improvement of the Understanding of Rock in Underground Constructions , 2005 .

[2]  Yuzhen Yu,et al.  An intelligent displacement back-analysis method for earth-rockfill dams , 2007 .

[3]  Nicholas Sitar,et al.  Use of stochastic stability analysis for Bayesian back calculation of pore pressures acting in a cut slope at failure , 1987 .

[4]  S. Sakurai,et al.  Back Analysis for Determining Material Characteristics in Cut Slopes , 1988 .

[5]  Luis Alonso,et al.  Multioutput Support Vector Regression for Remote Sensing Biophysical Parameter Estimation , 2011, IEEE Geoscience and Remote Sensing Letters.

[6]  C. H. Juang,et al.  Reliability-based method for assessing liquefaction potential of soils , 1999 .

[7]  Robert B. Gilbert,et al.  Uncertainty in back analysis of slopes: Kettleman Hills case history , 1998 .

[8]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[9]  Zhongliang Ru,et al.  Relevance vector machine applied to slope stability analysis , 2012 .

[10]  Xiao-Wei Tang,et al.  A Bayesian network approach for predicting seismic liquefaction based on interpretive structural modeling , 2015 .

[11]  Giancarlo Gioda,et al.  Numerical identification of soil‐structure interaction pressures , 1981 .

[12]  Zi-Jun Cao,et al.  Bayesian identification of soil strata in London Clay , 2014 .

[13]  Marte Gutierrez,et al.  Parameter identification in numerical modeling of tunneling using the Differential Evolution Genetic Algorithm (DEGA) , 2012 .

[14]  Dian-Qing Li,et al.  Effect of spatially variable shear strength parameters with linearly increasing mean trend on reliability of infinite slopes , 2014 .

[15]  Shadi Najjar,et al.  Importance of Lower-Bound Capacities in the Design of Deep Foundations , 2009 .

[16]  A. Gomes Correia,et al.  Bayesian methodology for updating geomechanical parameters and uncertainty quantification , 2009 .

[17]  Roland W. Lewis,et al.  Optimal estimation of in-situ ground stresses from displacement measurements , 1987 .

[18]  C. F. Lee,et al.  Displacement back analysis for a steep slope at the Three Gorges Project site , 2001 .

[19]  Zhe Luo,et al.  Probabilistic back analysis of slope failure – A case study in Taiwan , 2013 .

[20]  K. Takeuchi,et al.  Back analysis of measured displacements of tunnels , 1983 .

[21]  Li Min Zhang,et al.  Efficient Probabilistic Back-Analysis of Slope Stability Model Parameters , 2010 .

[22]  Shaojun Li,et al.  Slope reliability analysis by updated support vector machine and Monte Carlo simulation , 2012, Natural Hazards.

[23]  Shunde Yin,et al.  Geomechanical parameters identification by particle swarm optimization and support vector machine , 2009 .

[24]  Richard J. Jardine,et al.  Reliability updating and geotechnical back-analysis , 2004 .

[25]  G. L. Sivakumar Babu,et al.  Methodology for Pavement Design Reliability and Back Analysis Using Markov Chain Monte Carlo Simulation , 2013 .

[26]  Lulu Zhang,et al.  Probabilistic parameter estimation and predictive uncertainty based on field measurements for unsaturated soil slope , 2013 .

[27]  Li Min Zhang,et al.  Microporosity Structure of Coarse Granular Soils , 2010 .

[28]  Shaojun Li,et al.  A new displacement back analysis to identify mechanical geo‐material parameters based on hybrid intelligent methodology , 2004 .

[29]  Jack W. Baker,et al.  Uncertainty treatment in earthquake modelling using Bayesian probabilistic networks , 2011 .

[30]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[31]  Johan A. K. Suykens,et al.  Weighted least squares support vector machines: robustness and sparse approximation , 2002, Neurocomputing.

[32]  W. H. Tang,et al.  Model Uncertainty in Offshore Geotechnical Reliability , 1995 .

[33]  Chen Wei-hong General situations of engineering geologic conditions of Longtan Hydropower Station , 2003 .

[34]  Hyuck-Jin Park,et al.  Probabilistic analysis of rock slope stability and random properties of discontinuity parameters, Interstate Highway 40, Western North Carolina, USA , 2005 .

[35]  Kenny Q. Ye Orthogonal Column Latin Hypercubes and Their Application in Computer Experiments , 1998 .

[36]  Wilson H. Tang,et al.  REALISTIC ASSESSMENT OF SLOPE RELIABILITY FOR EFFECTIVE LANDSLIDE HAZARD MANAGEMENT , 2005 .

[37]  Roman Lackner,et al.  Back analysis of model parameters in geotechnical engineering by means of soft computing , 2003 .

[38]  Xing Zheng Wu Development of fragility functions for slope instability analysis , 2015, Landslides.