Explainable AI-Based Geophysical Logging Parameters Selection for Enhancing Rock Brittleness Prediction

Mohammad Islam Miah; Md. Maruf Alam; Travis Wiens

doi:10.38032/scse.2026.4.239

Authors

Mohammad Islam Miah Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A9, Canada.
Md. Maruf Alam Institute of Energy Technology, Chittagong University of Engineering & Technology, Chattogram-4349, Bangladesh.
Travis Wiens Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A9, Canada.

DOI:

https://doi.org/10.38032/scse.2026.4.239

Keywords:

Logging Data, Gradient Boosting, Random Forest, Artificial Intelligence, Features Attribute, Geomechanics

Abstract

A reliable rock brittleness index (BI) profile plays a key role in maintaining safe drilling operation and hydraulic fracturing during hydrocarbon exploration and field development. Also, BI is vital for mining projects such as tunneling and rock mass excavation for mineral extraction. Instead of destructive testing measurements for BI, the machine learning (ML) algorithms are widely used to obtain continuous BI profile using real field logging data. The major objectives of this study are a) to evaluate the efficacy of different ML algorithms and b) to find the most contributing geophysical logging parameters for predicting BI of clastic sedimentary formation. The data-driven computational models are developed and optimized using ML techniques of extreme gradient boosting (XGB) and random forest (RF) algorithms along with support vector regression (SVR) using a list of processed 1550 datasets from logging parameters. The explainable AI (XAI) of Shapley Additive Explanations (SHAP) is applied to identify features of importance to ensure transparency and interpretability of the BI model's predictions. Results revealed that XGB outperforms with high determination of coefficient (99%) and least statistical error compared to RF and SVR algorithms to predict BI using logging data of offshore Volve oil field. Based on XGB-based SHAP analysis, it is found that acoustic shear and compressional travel times are most contributing variables for BI forecasting other than deep resistivity, gamma ray, bulk density and neutron porosity. These features importance also verified and confirmed by SHAP value with RF. The applied methodological strategies and research findings from the study could be applied to refine the data-driven model architectures for better performance and reliability in forecasting geomechanical properties and formation evaluation with precise subsurface datasets in petroleum and mining operations.

Downloads

PDF

Downloads

Download data is not yet available.

References

[1] Zamanzadeh Talkhouncheh, M., Davoodi, S., Larki, B., Mehrad, M., Rashidi, S. and Vasfi, M., 2023. A new approach to mechanical brittleness index modeling based on conventional well logs using hybrid algorithms. Earth Science Informatics, 16(4), pp.3387-3416. DOI: https://doi.org/10.1007/s12145-023-01098-1

[2] Wood, D.A., 2021. Brittleness index predictions from Lower Barnett Shale well-log data applying an optimized data matching algorithm at various sampling densities. Geoscience Frontiers, 12(6), p.101087. DOI: https://doi.org/10.1016/j.gsf.2020.09.016

[3] Rana, M.R., Miah, M.I. and Abir, M.A.N., 2025. Experimental Study on Rock Strength Parameters for Brittleness Index Evaluation: A Case Study of the Sitakunda Anticline Area, Bengal Basin. Journal of Petroleum and Mining Engineering, 26(2), pp.87-97.

[4] Miah, M.I., Ahmed, S., Zendehboudi, S. and Butt, S., 2020. Machine learning approach to model rock strength: prediction and variable selection with aid of log data. Rock Mechanics and Rock Engineering, 53(10), pp.4691-4715. DOI: https://doi.org/10.1007/s00603-020-02184-2

[5] Miah, M.I., 2020. Predictive models and feature ranking in reservoir geomechanics: A critical review and research guidelines. Journal of Natural Gas Science and Engineering, 82, p.103493. DOI: https://doi.org/10.1016/j.jngse.2020.103493

[6] Ghobadi, M.H. and Naseri, F., 2016. Rock brittleness prediction using geomechanical properties of Hamekasi limestone: regression and artificial neural networks analysis. Geopersia, 6(1), pp.19-33.

[7] Kaunda, R.B. and Asbury, B., 2016. Prediction of rock brittleness using nondestructive methods for hard rock tunneling. Journal of Rock Mechanics and Geotechnical Engineering, 8(4), pp.533-540. DOI: https://doi.org/10.1016/j.jrmge.2016.03.002

[8] Ye, Y., Tang, S., Xi, Z., Jiang, D. and Duan, Y., 2022. A new method to predict brittleness index for shale gas reservoirs: Insights from well logging data. Journal of Petroleum Science and Engineering, 208, p.109431. DOI: https://doi.org/10.1016/j.petrol.2021.109431

[9] Mustafa, A., Tariq, Z., Mahmoud, M.A. and Abdulraheem, A., 2022, June. Artificial intelligence approach for predicting the shale brittleness index-a middle east basin case study. In SPE Europec featured at EAGE Conference and Exhibition? (p. D042S011R002). SPE. DOI: https://doi.org/10.2118/209707-MS

[10] Hassan, A., Chan, S., Mahmoud, M., Aljawad, M.S., Humphrey, J. and Abdulraheem, A., 2022. Artificial intelligence-based model of mineralogical brittleness index based on rock elemental compositions. Arabian Journal for Science and Engineering, 47(9), pp.11745-11761. DOI: https://doi.org/10.1007/s13369-021-06487-6

[11] Ore, T. and Gao, D., 2023. Prediction of reservoir brittleness from geophysical logs using machine learning algorithms. Computers & Geosciences, 171, p.105266. DOI: https://doi.org/10.1016/j.cageo.2022.105266

[12] Fereidooni, D. and Karimi, Z., 2023. Predicting rock brittleness indices from simple laboratory test results using some machine learning methods. Geomechanics and Engineering, 34(6), pp.697-726.

[13] Wu, H., Wu, D. and Wang, L., 2025. Assessment and Estimation of Sedimentary Rocks’ Brittleness Using Machine Learning and Statistical Methods. Mining, Metallurgy & Exploration, pp.1-31. DOI: https://doi.org/10.1007/s42461-025-01294-1

[14] Oloruntobi, O., Onalo, D., Adedigba, S., James, L., Chunduru, R. and Butt, S., 2019. Data-driven shear wave velocity prediction model for siliciclastic rocks. Journal of Petroleum Science and Engineering, 183, p.106293. DOI: https://doi.org/10.1016/j.petrol.2019.106293

[15] Miah, M.I., Ahmed, S. and Zendehboudi, S., 2021. Model development for shear sonic velocity using geophysical log data: Sensitivity analysis and statistical assessment. Journal of Natural Gas Science and Engineering, 88, p.103778. DOI: https://doi.org/10.1016/j.jngse.2020.103778

[16] Miah, M.I., Abir, M.A.N. and Shuvo, M.A.I., 2025. Improved model development and feature ranking for rock permeability prediction by coupling petrophysical log data and ensemble machine learning techniques. Earth Science Informatics, 18(1), p.93. DOI: https://doi.org/10.1007/s12145-024-01593-z

[17] Taylor, K.E., 2001. Summarizing multiple aspects of model performance in a single diagram. Journal of geophysical research: atmospheres, 106(D7), pp.7183-7192. DOI: https://doi.org/10.1029/2000JD900719

[18] Rahaman, M.S. and Miah, M.I., 2025. Data-driven resilient model development and feature selection for rock compressive strength prediction using machine learning and transformer techniques. Earth Science Informatics, 18(3), p.293. DOI: https://doi.org/10.1007/s12145-025-01803-2