The performance of ANFIS model for prediction of deformation modulus of rock mass

The purpose of this study is to investigate the performance of adaptive neuro-fuzzy inference system (ANFIS) model in the estimation of the deformation modulus of rock mass. ANFIS is a powerful processing tool which is used for the modeling of complex problems where the relationship between the model variables is unknown. For this reason, this model seems to be suited for the estimation of deformation modulus. In this paper, the ANFIS model was constructed and compared with empirical relation that was suggested for indirect estimation of this parameter. In the ANFIS model, five parameters, including depth, uniaxial compressive strength of intact rock, RQD, spacing of discontinuities, and the condition of discontinuities are considered. These parameters are the most effective parameters in the estimation of deformation modulus. Employing the ANFIS model for the estimation of rock mass deformation modulus shows a reliable performance. The values of correlation coefficient, variance accounted for, and root mean square error of the results for ANFIS model is obtained as 0.86, 85.3%, and 2.73, respectively, which indicates precise and correlate results.