The usability of Cerchar abrasivity index for the prediction of UCS and E of Misis Fault Breccia: Regression and artificial neural networks analysis

Abstract

The derivation of some predictive models for the geomechanical properties of fault breccias will be useful due to the fact that the preparation of smooth specimens from the fault breccias is usually difficult and expensive. To develop some predictive models for the uniaxial compressive strength ( UCS) and elastic modulus ( E) from the indirect methods including the Cerchar abrasivity index ( CAI), regression and artificial neural networks ( ANNs) analysis were applied on the data pertaining to Misis Fault Breccia. The CAI was included to the best regression model for the prediction of UCS. However, the CAI was not included to the best regression model for the prediction of E. The developed ANNs model was also compared with the regression model. It was concluded that the CAI is a useful property for the prediction of UCS of Misis Fault Breccia. Another conclusion is that ANNs model is more reliable than the regression models.