Abstract
Azarshahr County in the northwest of Iran is predominantly covered by Azarshahr travertine, a prevailing sedimentary rock. This geological composition has led to extensive open-pit mining activities, particularly in the western and southwestern parts of the county. The rock's drillability and resistance to excavation play a pivotal role in determining its overall durability and hardness, crucial factors that influence the mining process. These attributes are intimately tied to the compressive strength of the rock. Accurate assessment of rock strength is vital for devising reliable excavation methodologies at mining sites. However, conventional approaches for analyzing rock strength have limitations that undermine the precision of strength estimations. In response, this study endeavors to leverage artificial intelligence techniques, specifically the Multilayer Perceptron (MLP), to enhance the prediction of travertine's compressive strength. To formulate a robust model, a comprehensive database containing data from 150 point-load index (I(s)) tests on Azarshahr travertine was compiled. This dataset serves as the foundation for the development of the MLP-based predictive model, which proves instrumental in projecting rock compressive strength. The model's accuracy and efficacy were rigorously assessed using the Receiver Operating Characteristic (ROC) curve, employing both training and testing datasets. The modeling outcomes reveal impressive results. The estimated R-squared coefficient attained an impressive value of 0.975 for axial strength and 0.975 for diametral strength. The overall accuracy, as indicated by the Area Under the Curve (AUC) metric, stands at an impressive 0.968. These exceptional performance metrics underscore the efficacy of the MLP model in accurately predicting compressive strength based on the point-load index of samples. The implications of this study are substantial. The predictive model, empowered by the MLP approach, has profound implications for excavation planning and drillability assessment within the studied region's travertine deposits. By facilitating accurate forecasts of rock strength, this model equips mining endeavors with valuable insights for effective planning and execution.