Multivariate Adaptive Regression Spline (Mars) for Prediction of Elastic Modulus of Jointed Rock Mass

This article presents multivariate adaptive regression spline (MARS) for determination of elastic modulus (Ej) of jointed rock mass. MARS is a technique to estimate general functions of high-dimensional arguments given sparse data. It is a nonlinear and non-parametric regression methodology. The input variables of model are joint frequency (Jn), joint inclination parameter (n), joint roughness parameter (r), confining pressure (σ3) and elastic modulus (Ei) of intact rock. The developed MARS gives an equation for determination of Ej of jointed rock mass. The results from the developed MARS model have been compared with those of artificial neural networks (ANNs) using average absolute error. The developed MARS gives a robust model for determination of Ej of jointed rock mass.

[1]  Nick Barton,et al.  Some new Q-value correlations to assist in site characterisation and tunnel design , 2002 .

[2]  Edwin T. Brown,et al.  Strength of a Model of Jointed Rock , 1970 .

[3]  Nii O. Attoh-Okine,et al.  A new technique for using multivariate adaptive regression splines (MARS) in pavement roughness prediction , 2003 .

[4]  Yingjie Yang,et al.  A hierarchical analysis for rock engineering using artificial neural networks , 1997 .

[5]  Upmanu Lall,et al.  Nonlinear Dynamics of the Great Salt Lake: Nonparametric Short-Term Forecasting , 1996 .

[6]  Shear strength and deformation response of jointed rocks , 1984 .

[7]  Chung-Sik Yoo,et al.  Tunneling performance prediction using an integrated GIS and neural network , 2007 .

[8]  E. Hoeka,et al.  Empirical estimation of rock mass modulus , 2005 .

[9]  T. Hastie,et al.  Using multivariate adaptive regression splines to predict the distributions of New Zealand ’ s freshwater diadromous fish , 2005 .

[10]  Chul-Wook Lee,et al.  Artificial Neural Network Integrated With Expert System For Preliminary Design Of Tunnels And Slopes , 1995 .

[11]  J. Shi.  REDUCING PREDICTION ERROR BY TRANSFORMING INPUT DATA FOR NEURAL NETWORKS , 2000 .

[12]  Nii O. Attoh-Okine,et al.  Multivariate adaptive regression (MARS) and hinged hyperplanes (HHP) for doweled pavement performance modeling , 2009 .

[13]  Evaluation of the deformation modulus of rock masses using RMR: Comparison with dilatometer tests , 2007 .

[14]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[15]  Peter Craven,et al.  Smoothing noisy data with spline functions , 1978 .

[16]  T. G. Sitharam,et al.  Prediction of Elastic Modulus of Jointed Rock Mass Using Artificial Neural Networks , 2008 .

[17]  Tian-Shyug Lee,et al.  A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines , 2005, Expert Syst. Appl..

[18]  Jingsheng Shi,et al.  MODULAR NEURAL NETWORKS FOR PREDICTING SETTLEMENTS DURING TUNNELING , 1998 .

[19]  Herbert H. Einstein,et al.  Using RQD to estimate the deformation modulus of rock masses , 2004 .