<p>Rock Quality Designation (RQD) is a crucial parameter in rock mechanics and engineering, fundamental for the design and stability analysis of rock structures. Traditional methods for acquiring RQD data are often limited by high costs and restricted spatial coverage, underscoring the need for more efficient and accurate estimation techniques. This study introduces a novel approach by integrating the Gray Wolf Optimization (GWO) algorithm with the Inverse Distance Weighting (IDW) method, addressing the limitations of traditional IDW, such as its sensitivity to fixed parameters and its tendency to oversimplify complex geological variations. The proposed GWO-GEP method dynamically optimizes interpolation parameters, significantly enhancing the accuracy of RQD predictions. Utilizing data from 577 RQD observations across 15 boreholes in the Azad Dam area, the study compares the performance of the traditional IDW method with the GWO-GEP hybrid approach. The results show that while IDW provides satisfactory accuracy (with a coefficient of determination of 0.91 for the training set and 0.90 for the test set); the GWO-GEP method outperforms it with higher predictive accuracy (achieving a coefficient of determination of 0.99 for the training set and 0.98 for the test set). Additionally, the GWO-GEP model demonstrates lower Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) values, along with higher Nash–Sutcliffe efficiency (NSE) values, highlighting its superiority in handling spatial complexity and reducing prediction errors. These findings validate the effectiveness of the GWO-GEP method as a robust tool for RQD estimation, particularly in challenging geological settings. This study not only advances the methodology for RQD estimation but also emphasizes the practical benefits of applying intelligent optimization techniques in geotechnical engineering, ultimately contributing to more reliable and cost-effective engineering designs.</p>