Performance of Statistical and Intelligent Methods in Estimating Rock Compressive Strength

This research was conducted to forecast the uniaxial compressive strength (UCS) of rocks via the random forest, artificial neural network, Gaussian process regression, support vector machine, K-nearest neighbor, adaptive neuro-fuzzy inference system, simple regression, and multiple linear regression approaches. For this purpose, geo-mechanical and petrographic characteristics of sedimentary rocks in southern Iran were measured. The effect of petrography on geo-mechanical characteristics was assessed. The carbonate and sandstone samples were classified as mudstone to grainstone and calc-litharenite, respectively. Due to the shallow depth of the studied mines and the low amount of quartz minerals in the samples, the rock bursting phenomenon does not occur in these mines. To develop UCS predictor models, porosity, point load index, water absorption, P-wave velocity, and density were considered as inputs. Using variance accounted for, mean absolute percentage error, root-mean-square-error, determination coefficient (R-2), and performance index (PI), the efficiency of the methods was evaluated. Analysis of model criteria using multiple linear regression allowed for the development of a user-friendly equation, which proved to have adequate accuracy. All intelligent methods (with R-2 > 90%) had excellent accuracy for estimating UCS. The percentage difference of the average of all six intelligent methods with the measured value was equal to +0.28%. By comparing the methods, the accuracy of the support vector machine with radial basis function in predicting UCS was (R-2 = 0.99 and PI = 1.92) and outperformed all the other methods investigated.

Automated summary

This research compared various machine learning models to forecast the uniaxial compressive strength (UCS) of rocks. The support vector machine with radial basis function outperformed all other methods and achieved high accuracy (R-2 = 0.99, PI = 1.92). The models showed excellent accuracy (R-2 > 90%) in estimating UCS, with a small average difference of +0.28% compared to the measured values.