A Marble-Specific Rock Mass Classification Framework Integrating Empirical Parameters and Machine Learning Validation

Sinha, Shambhavi; Tripathi, Anup; Avchar, Akhil; Kumar, Mritunjay

doi:10.22044/jme.2026.17326.3432

Document Type : Original Research Paper

Authors

¹ National Institute of Technology Karnataka

² NITK Surathkal

10.22044/jme.2026.17326.3432

Abstract

Accurate assessment of rock mass quality in marble quarries remains challenging because conventional empirical classification systems are largely strength-dominated and insufficiently sensitive to discontinuity-controlled block instability. This study proposes a quarry-specific empirical framework, termed the Marble Rock System (MRS), designed to explicitly capture structural, hydro-mechanical, and alteration-driven controls governing bench-scale stability in dimension stone marble quarries. The primary objective was to develop and validate an empirically grounded classification system using machine learning as an independent diagnostic tool rather than as a black-box predictor.
A comprehensive geomechanical database comprising 85 quarry-scale records was developed from three active marble quarries in southern Rajasthan, India. Six physically interpretable parameters intact strength, weathering or serpentinization, joint frequency, joint surface condition, groundwater influence, and block stability were incorporated into the MRS framework. Supervised machine learning models, including artificial neural networks, support vector machines, and linear regression, were trained to predict independently derived factors of safety for validation. Model performance was evaluated using coefficient of determination, root mean square error, cross-validation, and classification metrics.
Results show that MRS-based models achieved consistently higher predictive accuracy, improved class separability, and more stable generalization than models trained using conventional Rock Mass Rating inputs. Sensitivity analysis revealed that block stability and joint characteristics dominate stability prediction, while intact strength plays a secondary role. These findings confirm that marble quarry slope behaviour is primarily discontinuity-controlled. The proposed MRS provides a physically interpretable, empirically validated framework for quarry-scale stability assessment and offers a robust alternative to conventional classification systems for operational decision-making.

Keywords

Main Subjects

Dimensional Stone Mining

References

[1]. Bieniawski, Z. T. (1993). Engineering rock mass classification: A textbook for geologists and mining engineers. In J. A. Hudson (Ed.), Comprehensive rock engineering (Vol. 2, pp. 97-106).

[2]. Bustos, N. (2022). An integrated approach for design and construction of drawbells in block cave mines. PhD thesis, Curtin University, Kalgoorlie, Australia.

[3]. Hoek, E., Carranza-Torres, C., & Corkum, B. (2002). Hoek-Brown failure criterion-2002 edition. In Proceedings of the 5th North American Rock Mechanics Symposium (pp. 267-273).

[4]. Price, L. (2016). The interaction of groundwater with rock masses and the implications for slope stability. In Proceedings of the 14th International Conference of the International Association for Computer Methods and Advances in Geomechanics (IACMAG).

[5]. Villaescusa, E. (2014). Geotechnical design for sublevel open stoping. Taylor & Francis.

[6]. Dyke, C. G. (1988). In situ stress indicators for rock at great depth. PhD thesis, Imperial College London, UK.

[7]. Scavia, C., Giani, G. P., & Semprich, S. (2009). The Randa rockslides: An investigation of the discontinuity network influence on rock slope stability. Landslides, 6(3), 267-279.

[8]. Rana, M. J., Mussa, S. M., Ahmed, K. A., & Buniya, M. K. (2024). Geomechanical characterization and stability analysis of rock for optimizing slope design in open pit mines. Mining, 4(1), Article 11.

[9]. Davoodi, P. K., Hajizadeh, F., & Rezaei, M. (2025). Application of the metaheuristic algorithms to quantify the GSI based on the RMR classification. Scientific Reports, 15(1), 28950.

[10]. Davoodi, P. K., Hajizadeh, F., & Rezaei, M. (2025). Evaluating the RMR correlation with the rock mass wave velocity using meta-heuristic algorithms. Scientific Reports, 15(1), 17716.

[11]. Drover, C. (2019). Logging of core disking in diamond drill holes using the database of photographs. Western Australian School of Mines, Curtin University.

[12]. Liu, Q., Wang, H., Tan, Y., Lu, H., Huang, R., & Wu, X. (2024). Real-time prediction and reliability analysis of surrounding rock classification based on improved hybrid random forest models during TBM tunneling. Buildings, 15(2), 47.

[13]. Wang, L., Ma, S., Lu, H., & Tian, G. (2023). Discussion on the quantification of the Geological Strength Index (GSI) and its application in rock engineering: A perspective review. Sustainability, 15(14), 11233.

[14]. Matsuki, K., Kaga, N., Yokoyama, T., & Tsuda, N. (2004). Determination of three-dimensional in situ stress from core discing based on analysis of principal tensile stress. International Journal of Rock Mechanics and Mining Sciences, 41(7), 1167-1190.

[15]. Dershowitz, W. S., Finnila, A., Rogers, S., Hamdi, P., & Moffitt, K. M. (2017). Step path rock bridge percentage for analysis of slope stability. In Proceedings of the 51st US Rock Mechanics/Geomechanics Symposium.

[16]. Rezaei, M., & Habibi, A. (2023). Predicting the production of dimension stone quarries using a modified rock mass classification system. Journal of Mining and Environment, 14(1), 125-142.

[17]. Palmstrom, A., & Broch, E. (2008). Use and misuse of rock mass classification systems. Tunnelling and Underground Space Technology, 23(6), 575-593.

[18]. Wei, D., Li, Z., & Yang, B. (2024). Comprehensive evaluation of rock mass classification systems. Rock Mechanics and Rock Engineering, 57(3), 1897-1915.

[19]. Kumar, M., Avchar, A., Sinha, S., & Swamy, S. V. (2026). Integrated approaches for pillar design and stability assessment in underground hard rock mining: From empirical models to machine learning. Physics and Chemistry of the Earth, Parts A/B/C, 142, 104235.

[20]. Kumar, M., Avchar, A., & Sinha, S. (2026). A hybrid empirical-numerical framework for pillar stability and reinforcement in deep underground marble mines: A case study. International Journal of Mining and Geo-Engineering, 60(1), 25-33.

[21]. Sinha, S., Tripathi, A. K., Avchar, A., Kumar, M., & Swamy, S. V. (2026). Influence of angle of internal friction and slope face angle on kinematic failures in marble mines: A predictive approach. Indian Geotechnical Journal, 56, 1581-1589.

[22]. Ma, J., He, P., & Zhang, D. (2018). Challenges in applying machine learning to geotechnical engineering: A review. Computers and Geotechnics, 95, 103-114.

[23]. Raghuvanshi, C., Mishra, V., Prakash, P., & Tiwari, A. (2022). Predictive modeling of rock mass deformation modulus using artificial intelligence techniques. Sustainability, 14(22), 15225.

[24]. Miranda, T., Sousa, L. R., Roggenthen, W., & Sousa, R. L. (2013). Application of data mining techniques for the development of new rock mechanics constitutive models. In Springer Series in Geomechanics and Geoengineering (pp. 735-740).

[25]. Han, M., & Yang, B. (2024). Prediction of slope stability based on five machine learning techniques: A comparative study. Multiscale and Multidisciplinary Modeling, Experiments and Design, 7(2), 1521-1535.

[26]. Rahimi, M., & Mirmozaffari, M. (2024). Deep learning-powered rock mass classification: Predicting RMR from Q-system parameters with high accuracy. Rock Mechanics Bulletin, 3(3), 100152.

[27]. Niu, L., Feng, Y., Liu, H., & Zhang, X. (2024). Deep learning-based rockburst prediction in tunneling: A review. Tunnelling and Underground Space Technology, 145, 105583.

[28]. Bieniawski, Z. T. (1989). Engineering rock mass classifications. John Wiley & Sons.

[29]. Barton, N. (2000). TBM tunnelling in jointed and faulted rock. A.A. Balkema.

[30]. Hong, Y., Zhang, Y., He, C., & Zhang, H. (2024). A study on the correlation between rock mass rating (RMR) and Q-system for faulted and weak rock masses in South Korea. PLOS ONE, 19(5), e0301985.

[31]. Sun, Z., Wang, B., & Zhang, Q. (2024). Research on the applicability of rock mass classification system in deep-buried hard rock tunnels. Frontiers in Earth Science, 12, 1453912.

[32]. Yang, J., Rong, G., Hou, D., Peng, J., & Zhou, C. (2022). Application of mining rock mass rating (MRMR) in underground mining engineering. Rock Mechanics and Rock Engineering, 55(8), 4523-4541.

[33]. El-Naqa, A. (1996). Assessment of geotechnical characterization of a proposed dam site using geophysical and geotechnical data. Geotechnical and Geological Engineering, 14(1), 35-57.

[34]. Ghorbani, M., Sharifzadeh, M., Masoudi, R., & Noaslati, A. (2025). Investigating scale effects on the mechanical properties of rock joints using a lower bound limit analysis. Rock Mechanics and Rock Engineering, 58(3), 1123-1145.

[35]. Wu, Q., Weng, L., & Zhao, Y. (2023). Anisotropic time-dependent modeling of basic creep of weak sandstone considering crack deformation. International Journal of Rock Mechanics and Mining Sciences, 162, 105305.

[36]. Zhao, H., Li, T., & Liu, Q. (2019). Integration of machine learning with traditional geomechanical models for enhanced prediction accuracy. International Journal of Rock Mechanics and Mining Sciences, 123, 104092.

[37]. Heidarzadeh, S., Saeidi, A., & Rouleau, A. (2021). Evaluation of the effect of geometrical parameters of rock joints on the stability of underground excavations. Geotechnical and Geological Engineering, 39(3), 2197-2215.

[38]. Yang, B., Liu, Y., Liu, Z., Zhu, Q., & Li, D. (2024). A novel hybrid optimization XGBoost model for rock mass quality classification using incomplete dataset. Applied Sciences, 14(16), 7074.

[39]. Miranda, T., Sousa, L. R., Gomes, A. T., Tinoco, J., & Ferreira, C. (2018). Geomechanical characterization of volcanic rocks using empirical systems and data mining techniques. Journal of Rock Mechanics and Geotechnical Engineering, 10(1), 138-150.

[40]. Singh, R., Umrao, R. K., & Singh, T. N. (2023). Probabilistic stability analysis of failed rock slope using machine learning algorithms. Geomechanics and Engineering, 32(5), 513-524.

[41]. Garg, A., Garg, A., Tai, K., & Sreedeep, S. (2014). An integrated SRM-multi-gene genetic programming approach for prediction of factor of safety of 3-D soil nailed slopes. Engineering Applications of Artificial Intelligence, 30, 30-40.

[42]. Gulli, D., Greco, R., Lo Presti, D. C. L., Squeglia, N., & Vessia, G. (2013). A laboratory study on serpentinized ultrabasic rocks from Valmalenco (Central Alps, N. Italy). Procedia Earth and Planetary Science, 7, 322-325.

[43]. Goodman, R. E., & Shi, G. H. (1985). Block theory and its application to rock engineering. Prentice-Hall.

A Marble-Specific Rock Mass Classification Framework Integrating Empirical Parameters and Machine Learning Validation

References

References

Volume 17, Issue 4July and August 2026Pages 1285-1306

Volume 17, Issue 4
July and August 2026
Pages 1285-1306