Document Type : Original Research Paper

Authors

• Shirin Jahanmiri ¹
• Ali Aalianvari ²
• Majid Noorian-Bidgoli ¹
• Jamal Rostami ³

¹ Department of Mining Engineering, University of Kashan, Kashan, Iran

² Department of Mining and Environmental Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran

³ Department of Mining Engineering, Colorado School of Mines, Golden, Colorado, USA,

Abstract

Accurate prediction of rock brittleness is essential for tunneling, excavation, and rock engineering applications. This study develops and compares four intelligent predictive models, namely Gene Expression Programming (GEP), Artificial Rabbit Optimization–GEP (ARO-GEP), Grey Wolf Optimizer–GEP (GWO-GEP), and Crayfish Optimization Algorithm–GEP (COA-GEP), for estimating the rock brittleness index using uniaxial compressive strength (UCS) and tensile strength (TS). A comprehensive database containing 854 samples from 23 rock types was compiled from published literature. The dataset was divided into training (70%), validation (15%), and testing (15%) subsets. Model performance was evaluated using R², RMSE, MAE, and MAPE metrics. The results demonstrate that all models successfully captured the nonlinear relationship between UCS, TS, and rock brittleness. Among the investigated models, GEP achieved the highest predictive accuracy with a testing R² of 0.95 and RMSE of 1.24, followed closely by ARO-GEP and GWO-GEP. Sensitivity and SHAP analyses confirmed that UCS is the dominant parameter controlling rock brittleness, contributing approximately 60% of the predictive influence. The developed models provide practical tools for preliminary brittleness estimation in situations where direct laboratory determination is unavailable

Keywords

• Rock Brittleness Assessment
• Tunnel Engineering
• Artificial Rabbits Optimization
• Crayfish Optimization Algorithm
• Machine Learning Techniques

Main Subjects

• Exploration