Application of Machine Learning to the Estimation of Intact Rock Strength from Core Logging Data: A Case Study at the Newcrest Cadia East Mine

Abstract

ABSTRACT: Understanding the spatial variation in intact and defected rock strength is critical to geomechanical mine design. At the Newcrest Cadia East mine, systematic point load testing (PLT) was used to measure the strength of intact rock and individual defects (e.g., veins) at regular closely spaced intervals along several boreholes. The systematic PLT data collection covers only 1.3% of the 590 km of hole logged at Cadia East. A procedure was developed to homogenize the available geotechnical and geological logging data, infill missing values, and encode raw data into engineered features for use in a machine learning model. A random forest classifier was applied to predict point load index (Is50) from core logging data where tests were not performed. The random forest model predicts the rolling average Is50 value within 1 MPa 48% of the time. The model gives insights into which core logging quantities have the strongest controls on rock strength and provides the basis for developing more detailed geospatial models of intact and defected rock strength. 1. INTRODUCTION Understanding the spatial variation in intact and defected rock strength is critical to many aspects of geotechnical mine design, including predicting caveability, and excavation and ground support design. At the Newcrest Cadia East mine, there are 590 kilometers of logged core. Having measurements or estimates of point load index at every meter along each core enables the production of geospatial models of rock strength for use in predictive models. While point load testing is relatively quick and inexpensive, performing point load tests at a tight spacing along 590 km of core would be costly and impractical (see ASTM, 2016 and Franklin, 1985). Systematic point load testing (PLT) was used to measure rock strength based on guidelines provided by Pierce Engineering (Pierce, 2019; Pierce, 2020). It offers a means to quantify the variability in both intact and structural tensile strength over the largest possible volume with a minimum of bias. It involves performing diametral point load tests at strict 1-2m intervals along core from multiple boreholes and taking care to recognize both structure (which requires careful alignment of the test platens in order to test the strength of the structure itself) and pre-disturbed sections of core (which should be registered as having zero tensile strength, unless marked as an induced break). Axial tests are also conducted periodically to check for anisotropy. The testing is carried out in accordance with ISRM standards (ISRM, 1989), with careful attention paid to the maintenance of the radius of curvature on testing points to ensure a high proportion of valid tests.