Standard

A machine learning framework for mineralogical composition assessment in unconventional formations. / Gainitdinov, B.; Meshalkin, Y.; Orlov, D.; Chekhonin, E.; Zagranovskaya, J.; Koroteev, D.; Popov, Y.

в: Advances in Geo-Energy Research, Том 19, № 1, 25.01.2026, стр. 14-29.

Результаты исследований: Научные публикации в периодических изданияхстатьяРецензирование

Harvard

Gainitdinov, B, Meshalkin, Y, Orlov, D, Chekhonin, E, Zagranovskaya, J, Koroteev, D & Popov, Y 2026, 'A machine learning framework for mineralogical composition assessment in unconventional formations', Advances in Geo-Energy Research, Том. 19, № 1, стр. 14-29. https://doi.org/10.46690/ager.2026.01.02

APA

Gainitdinov, B., Meshalkin, Y., Orlov, D., Chekhonin, E., Zagranovskaya, J., Koroteev, D., & Popov, Y. (2026). A machine learning framework for mineralogical composition assessment in unconventional formations. Advances in Geo-Energy Research, 19(1), 14-29. https://doi.org/10.46690/ager.2026.01.02

Vancouver

Gainitdinov B, Meshalkin Y, Orlov D, Chekhonin E, Zagranovskaya J, Koroteev D и пр. A machine learning framework for mineralogical composition assessment in unconventional formations. Advances in Geo-Energy Research. 2026 Янв. 25;19(1):14-29. https://doi.org/10.46690/ager.2026.01.02

Author

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. в: Advances in Geo-Energy Research. 2026 ; Том 19, № 1. стр. 14-29.

BibTeX

@article{d9cfcf64081a4180aeaee9f39cbcf400,
title = "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, hetero-geneity, 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. {\textcopyright} The Author(s) 2025.",
keywords = "gradient boosting, Machine learning, mineral composition prediction, subsurface characterization, thermal profiling, unconventional reservoir, well logs, Adaptive boosting, Chains, Experimental mineralogy, Learning systems, Organic carbon, Organic minerals, Rocks, Thermal conductivity, Thermal logging, Gradient boosting, Machine-learning, Mineral composition, Mineral composition prediction, Subsurface characterizations, Thermal, Thermal core, Thermal profiling, Unconventional reservoirs, Well logs, chemical composition, core logging, machine learning, optimization, prediction, pyrite, quartz, thermal conductivity, total organic carbon, volume, weight, well logging, Mean square error, Volume fraction",
author = "B. Gainitdinov and Y. Meshalkin and D. Orlov and E. Chekhonin and J. Zagranovskaya and D. Koroteev and Y. Popov",
note = "Export Date: 29 March 2026; Cited By: 0",
year = "2026",
month = jan,
day = "25",
doi = "10.46690/ager.2026.01.02",
language = "Английский",
volume = "19",
pages = "14--29",
journal = "Advances in Geo-Energy Research",
issn = "2207-9963",
publisher = "Yandy Scientific Press",
number = "1",

}

RIS

TY - JOUR

T1 - A machine learning framework for mineralogical composition assessment in unconventional formations

AU - Gainitdinov, B.

AU - Meshalkin, Y.

AU - Orlov, D.

AU - Chekhonin, E.

AU - Zagranovskaya, J.

AU - Koroteev, D.

AU - Popov, Y.

N1 - Export Date: 29 March 2026; Cited By: 0

PY - 2026/1/25

Y1 - 2026/1/25

N2 - 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, hetero-geneity, 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. © The Author(s) 2025.

AB - 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, hetero-geneity, 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. © The Author(s) 2025.

KW - gradient boosting

KW - Machine learning

KW - mineral composition prediction

KW - subsurface characterization

KW - thermal profiling

KW - unconventional reservoir

KW - well logs

KW - Adaptive boosting

KW - Chains

KW - Experimental mineralogy

KW - Learning systems

KW - Organic carbon

KW - Organic minerals

KW - Rocks

KW - Thermal conductivity

KW - Thermal logging

KW - Gradient boosting

KW - Machine-learning

KW - Mineral composition

KW - Mineral composition prediction

KW - Subsurface characterizations

KW - Thermal

KW - Thermal core

KW - Thermal profiling

KW - Unconventional reservoirs

KW - Well logs

KW - chemical composition

KW - core logging

KW - machine learning

KW - optimization

KW - prediction

KW - pyrite

KW - quartz

KW - thermal conductivity

KW - total organic carbon

KW - volume

KW - weight

KW - well logging

KW - Mean square error

KW - Volume fraction

UR - https://www.mendeley.com/catalogue/a50d5b08-a284-307c-9e98-4a8ca69daf33/

U2 - 10.46690/ager.2026.01.02

DO - 10.46690/ager.2026.01.02

M3 - статья

VL - 19

SP - 14

EP - 29

JO - Advances in Geo-Energy Research

JF - Advances in Geo-Energy Research

SN - 2207-9963

IS - 1

ER -

ID: 151309001