A machine learning framework for mineralogical composition assessment in unconventional formations
Abstract
Quantitative determination of mineralogy, through laboratory core studies and high-definition spectroscopic logging, is effective but underutilized due to cost and complexity. Unconventional formations present additional challenges, such as kerogen presence, heterogeneity, and anisotropy. This problem can be addressed by utilizing well logs and thermal profiling with specialized wrappers, such as multioutput regressor and regressor chain. Several machine learning models and strategies for combining well logs on multiscale data from an unconventional formation in West Siberia were tested to predict the mass and volumetric fractions of minerals obtained from the Litho Scanner. The gradient boosting regressor, wrapped in a regressor chain and combined with conventional well logs, demonstrated superior performance in predicting both mineral weight and volume fractions, effectively capturing the heterogeneity of the rock structure. A comparison between the machine learning-based model and the Litho Scanner showed an average discrepancy, measured by the root mean squared error for weight fraction, of 0.026 in the Bazhenov Formation. The relationship between certain minerals and the thermal properties of the rock was validated by assessing the importance of thermal core logging data for quartz and pyrite. Moreover, the volume fraction of the rock matrix, composed of total organic carbon and other minerals, was predicted more accurately by incorporating thermal core logging data. The mineral densities, required for obtaining mineral volumes, were determined by solving an optimization problem. Subsequently, a theoretical model was used to calculate thermal conductivity from the mineral volume fractions, revealing a significant similarity between the predicted and experimental values.
Document Type: Original article
Cited as: Gainitdinov, B., Meshalkin, Y., Orlov, D., Chekhonin, E., Zagranovskaya, J., Koroteev, D., Popov, Y. A machine learning framework for mineralogical composition assessment in unconventional formations. Advances in Geo-Energy Research, 2026, 19(1): 14-29. https://doi.org/10.46690/ager.2026.01.02
DOI:
https://doi.org/10.46690/ager.2026.01.02Keywords:
Machine learning, well logs, mineral composition prediction, unconventional reservoir, gradient boosting, thermal profiling, subsurface characterizationReferences
Alekseev, A. D., Gavrilov, A. E. Methodical bases for the construction of integrated petrophysical models of unconventional and complex reservoirs based on the special core analysis results. PROneft Journal, 2019, 3: 2534. (in Russian).
Amosova, A., Panteeva, S., Tatarinov, V., et al. X-ray fluorescence determination of major rock-forming elements in small samples 50 and 110 mg. Analitika i Kontrol’, 2015, 19(2): 130-138. (in Russian).
Barham, A., Zainal Abidin, N. Machine learning approach to predict the illite weight percent of unconventional reservoirs from well-log data: An example from Montney Formation, NE British Columbia, Canada. Applied Sciences, 2023, 14: 318.
Barshad, I. Thermal analysis techniques for mineral identification and mineralogical composition. Methods of Soil Analysis: Part 1. Physical and Mineralogical Properties, Including Statistics of Measurement and Sampling, 1965, 9: 699-742.
Beck, A. E., Darbha, D. M., Schloessin, H. H. Lattice conductivities of single-crystal and polycrystalline materials at mantle pressures and temperatures. Physics of the Earth and Planetary Interiors, 1978, 17(1): 35-53.
Breiman, L. Random forests. Machine Learning, 2001, 45: 5-32. Brigham, E. O. The Fast Fourier Transform and Its Applications. Prentice-Hall, Englewood Cliffs, USA, 1988.
Chai, T., Draxler, R. R. Root mean square error (RMSE) or mean absolute error (MAE)?– Arguments against avoiding rmse in the literature. Geoscientific Model Development, 2014, 7: 1247-1250.
Chekhonin, E., Popov, Y., Romushkevich, R., et al. Integration of thermal core profiling and scratch testing for the study of unconventional reservoirs. Geosciences, 2021, 11(6): 260.
Clauser, C., Huenges, E. Thermal conductivity of rocks and minerals, in Rock Physics and Phase Relations: A Handbook of Physical Constants, edited by T. J. Ahrens, American Geophysical Union, Washington, DC, USA, pp. 105-126, 1995.
Conn, A. R., Gould, N. I. M., Toint, P. L. Trust Region Methods. Society for Industrial and Applied Mathematics, Philadelphia, USA, 2000.
Craddock, P., Srivastava, P., Datir, H., et al. Enhanced mineral quantification and uncertainty analysis from downhole spectroscopy logs using variational autoencoders. Paper SPWLA 2021-v62n6a2 Presented at Proceedings of the SPWLA Annual Symposium, Virtual, 17-20 May, 2021.
Cui, Q., Yang, H., Li, X., et al. Identification of lithofacies and prediction of mineral composition in shales: A case study of the shahejie formation in the bozhong sag. Unconventional Resources, 2022, 2: 72-84.
Dang, S. T., Sondergeld, C. H., Rai, C. S. A new approach to measuring organic density. Petrophysics, 2016, 57(2): 112-120.
Gavrilov, A. E., Zhukovskaya, E. A., Tugarova, M. A., et al. Objective bazhenov rocks classification (the case of the west siberia central part fields). Neftyanoe Khozyaystvo– Oil Industry, 2015, 12: 38-40. (in Russian).
Hall, P., Park, B. U., Samworth, R. J. Choice of neighbor order in nearest-neighbor classification. The Annals of Statistics, 2008, 36(5): 2135-2152.
Hantschel, T., Kauerauf, A. I. Fundamentals of Basin and Petroleum Systems Modeling. Springer, Berlin, Germany, 2009.
Hastie, T., Tibshirani, R., Friedman, J. H. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, New York, USA, 2009.
Horai, K.-i. Thermal conductivity of rock-forming minerals. Journal of Geophysical Research, 1971, 76(5): 1278-1308.
Hu, K., Liu, X., Chen, Z., et al. Mineralogical characterization from geophysical well logs using a machine learning approach: Case study for the Horn River Basin, Canada. Earth and Space Science, 2023, 10: e2023EA003084.
Khan, S. Q., Kirmani, F. Applicability of deep neural networks for lithofacies classification from conventional well logs: An integrated approach. Petroleum Research, 2024, 9: 393-408.
Kim, D., Choi, J., Kim, D., et al. Predicting mineralogy by integrating core and well log data using a deep neural network. Journal of Petroleum Science and Engineering, 2020, 195: 107838.
Kodikara, G. R. L., McHenry, L. J., Stanistreet, I. G., et al. Wide and deep learning for predicting relative mineral compositions of sediment cores solely based on xrf scans: A case study from pleistocene paleolake olduvai, tanzania. Artificial Intelligence in Geosciences, 2024, 5: 100088.
Kozlov, E. N., Fomina, E. N. The use of factor analysis for express diagnostics of the mineral composition of geologically complex objects based on X-ray diffraction data. Paper Presented at Proceedings of the Geological Institute of the Russian Academy of Sciences, Moscow, Russia, 20-23 November, 2018. (in Russian).
Kumar, T., Seelam, N. K., Rao, G. S. Lithology prediction from well log data using machine learning techniques: A case study from talcher coalfield, eastern india. Journal of Applied Geophysics, 2022, 199: 104605.
Martin, T., Meyer, R., Jobe, Z. Centimeter-scale lithology and facies prediction in cored wells using machine learning. Frontiers in Earth Science, 2021, 9: 659611.
Meshalkin, Y., Shakirov, A., Orlov, D., et al. Well-logging based lithology prediction using machine learning. Paper Prsented at Proceedings of the EAGE Conference on Data Science in Oil and Gas, Vienna, Austria, 19-20 October, 2020.
Nawal, M., Shekar, B., Jaiswal, P. Integration of sparse and continuous data sets using machine learning for core mineralogy interpretation. The Leading Edge, 2023, 42: 421-432.
Park, S., Son, B.-K., Choi, J., et al. Application of machine learning to quantification of mineral composition on gas hydrate-bearing sediments, ulleung basin, korea. Journal of Petroleum Science and Engineering, 2021, 209: 109840.
Popov, Y., Beardsmore, G., Clauser, C., et al. ISRM suggested methods for determining thermal properties of rocks from laboratory tests at atmospheric pressure. Rock Mechanics and Rock Engineering, 2016, 49(10): 4179-4207.
Popov, Y., Berezin, V., Soloviov, V., et al. Thermal conductivity of minerals. Izvestia, Physics of Solid Earth, 1987, 23(3): 245-253.
Postnikova, O. V., Postnikov, A. V., Zueva, O. A., et al. Types of void space in the bazhenov reservoir rocks. Geosciences, 2021, 11(7): 269.
Rodriguez-Galiano, V., Sánchez-Castillo, M., Chica-Olmo, M., et al. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geology Reviews, 2015, 71: 804-818.
Sass, J. H. The thermal conductivity of fifteen feldspar spe imens. Journal of Geophysical Research, 1965, 70(16): 4064-4065.
Serra, O. Fundamentals of Well-Log Interpretation. Elsevier, Amsterdam, Netherlands, 1983.
Temnikova, E. Y., Fedoseev, A. A., Kazanenkov, V. A., et al. Lithological characteristic of bazhenov formation sections in central and southeastern regions of western siberia according to logging data set. Russian Geology and Geophysics, 2022, 63(9): 1050-1060.
Tucker, M. Techniques in Sedimentology. Blackwell Science, Oxford, UK, 1988.
Tóth, C., Harangi, S., Károlyi, A., et al. Method development for the elemental analysis of organic rich soil samples by microwave plasma atomic emission spectrometry. Studia Universitatis Babes-Bolyai Chemia, 2017, 62: 483-494.
Wang, W., Carreira-Perpinan, M. A. Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application. ArXiv Preprint ArXiv: 1309.1541, 2013.
Yang, Z., Ghanizadeh, A., Younis, A., et al. Prediction of mineralogical composition in heterogeneous unconventional reservoirs: Comparisons between data-driven and chemistry-based models. Paper SPE 218116 D011S004R001 Prsented at Proceedings of the SPE Canadian Energy Technology Conference, Calgary, Canada, 13-14 March, 2024.
Zhou, B., Luo, R., Li, N., et al. Predicting mineralogy of the salt-gypsum layer by drilling cuttings and conventional well logging data using a multilayer perceptron neural network (MLPNN): A case study in kuqa depression, tarim basin. Paper ARMA 2021-1418 Prsented at 55th U.S. Rock Mechanics/Geomechanics Symposium, Virtual, 18-25 June, 2021.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.