INVESTIGATION OF DISCONTINUITIES SPACING HISTOGRAMS BY THE USE MACHINE LEARNING METHOD

Abstract

Discontinuities are major geological features in the rock mass and discontinuity spacing is one of the important parameters in describing the rock mass. Relation between discontinuity spacing and relative spacing has described by different curve fittings. These curve fittings will show the type (negative exponential, log-normal or normal distribution) of the statistical distribution as histograms. Discontinuity spacing and frequency data obtained at a field site in southern Seydişehir (Turkey). Sampling methods vary from one study to another (core sampling, scan-line survey, aerial photograpy). In this study, the possible distributions of discontinuity spacing along a straight line through a rock mass are considered. In this study, 5 different drilling sampling have been used. We have examined discontinuity spacing and relative spacing relations that obtained from these core sampling with using machine learning method. Machine learning, a branch of artificial intelligence, is a scientific discipline that is concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data. Minitab (LEAD Technologies, Inc) and Weka (Waikato Environment for Knowledge Analysis) software where preferred in all analyses and interprets. Results of study, different empirical equation for each histogram have been constituted. Machine learning method has been treated on the obtained equations and reached interesting outputs.