Prediction of Uniaxial Compressive Strength of Rocks from Their Physical Properties Using Soft Computing Techniques

Rock engineering tasks like tunnelling, dam and building construction, and rock slope stability rely heavily on properly estimating the rock's uniaxial compressive strength (UCS), a crucial rock geomechanical characteristic. As high-quality specimen are not always possible, scientists often estimate UCS indirectly. The primary objective of this paper is to assess the efficacy of long short-term memory (LSTM), K-nearest neighbour (KNN), a combination of particle swarm optimisation (PSO) with an artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) to estimate the UCS of sandstones from Jharia, Dhanbad, India. Point load index (PLI), porosity (n), P-wave velocity (Vp), density (rho), and moisture content (%) are the parameters used for the present study. Finally, a comparison was made between the various prediction algorithms outputs. The findings of the study validated the effectiveness of computational intelligence methods in forecasting UCS compared to other models used in this paper. The KNN achieves overall the best results, with an R2 of 0.95 for training, 0.94 for testing, and an RMSE of 0.03 for training and 0.05 for testing.