application of artificial intelligence in predicting physical and mechanical properties of rocks

The accurate determination of physical and mechanical properties of rocks is a cornerstone of geotechnical engineering, with direct implications for the safety, efficiency, and cost-effectiveness of projects in mining, tunneling, and petroleum engineering. conventional laboratory methods for measuring properties such as uniaxial compressive strength (ucs), tensile strength, and elastic modulus are often constrained by being time-consuming, costly, destructive, and requiring high-quality core samples. this study explores the transformative potential of artificial intelligence (ai) and machine learning (ml) as robust, non-destructive, and efficient alternatives to overcome these limitations. a comprehensive dataset encompassing key index parameters like p-wave velocity, point load index, density, and porosity was utilized to develop and train a suite of ml models, including artificial neural networks (ann), support vector machines (svm), and random forest (rf). the models were rigorously evaluated using standard metrics such as coefficient of determination (r²), root mean square error (rmse), and mean absolute error (mae). results indicate that all ai models achieved significant predictive accuracy, with the random forest algorithm demonstrating superior performance in most scenarios. the findings conclusively affirm that ai techniques can reliably predict critical rock properties, offering a paradigm shift towards more rapid and data-driven decision-making in geotechnical practice. this research underscores the viability of ai as a powerful tool that can complement traditional methods, potentially reducing reliance on extensive laboratory testing.