georesГеоресурсыGeoresources1608-50431608-5078Georesursy LLC10.18599/grs.2025.3.22geores-526Research ArticleПОИСК, РАЗВЕДКА И РАЗРАБОТКА МЕСТОРОЖДЕНИЙ УГЛЕВОДОРОДОВ, ИССЛЕДОВАНИЕ КОЛЛЕКТОРОВPROSPECTING, EXPLORATION AND DEVELOPMENT OF HYDROCARBON DEPOSITS, RESERVOIR PROPERTIES STUDYНовая методика текстурно-структурного анализа имиджей с помощью алгоритмов глубокого обученияA new state-of-the-art technique for textural and structural microimager data analysis using deep learning algorithmsКоссовГ. А.KossovG. A.

Георгий Андреевич Коссов – научный сотрудник

125171, Москва, Ленинградское ш., д. 16а, стр. 3

Georgy A. Kossov – Researcher

Build. 3, 16a, Leningradskoe shosse, Moscow, 125171

gkossov@slb.ruАбашкинВ. В.AbashkinV. V.

Владимир Викторович Абашкин – кандидат физ.-мат. наук, руководитель проектов

125171, Москва, Ленинградское ш., д. 16а, стр. 3

Vladimir V. Abashkin – Cand. Sci. (Physics and Mathematics), Project Manager

Build. 3, 16a, Leningradskoe shosse, Moscow, 125171

vabashkin@slb.ruЕгоровС. С.EgorovS. S.

Сергей Сергеевич Егоров – технический руководитель группы геологической интерпретации данных

125171, Москва, Ленинградское ш., д. 16а, стр. 3

Sergey S. Egorov – Technical Team Leader of GWL data interpretation group

Build. 3, 16a, Leningradskoe shosse, Moscow, 125171

segorov3@slb.ruМакиенкоД. О.MakienkoD. O.

Дарья Олеговна Макиенко – научный сотрудник

125171, Москва, Ленинградское ш., д. 16а, стр. 3

Daria O. Makienko – Researcher

Build. 3, 16a, Leningradskoe shosse, Moscow, 125171

dmakienko@slb.ruГаеваВ. А.GaevaV. A.

Валерия Александровна Гаева – стажёр-исследователь

125171, Москва, Ленинградское ш., д. 16а, стр. 3

Valeria A. Gaeva – Student intern

Build. 3, 16a, Leningradskoe shosse, Moscow, 125171

ООО "СТИБШ"РоссияLLC "STISS"Russian Federation202527092025273209220Copyright © Коссов Г.А., Абашкин В.В., Егоров С.С., Макиенко Д.О., Гаева В.А., 20252025Коссов Г.А., Абашкин В.В., Егоров С.С., Макиенко Д.О., Гаева В.А.Kossov G.A., Abashkin V.V., Egorov S.S., Makienko D.O., Gaeva V.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.geors.ru/jour/article/view/526

Скважинные имиджеры являются мощным инструментом для исследования сложнопостроенных коллекторов, предоставляя уникальную информацию о структурных и текстурных особенностях изучаемых пластов, в том числе информацию в масштабе кернового материала. Развитие методов обработки и интерпретации позволяет оптимизировать существующие подходы к оценке имиджей на качественном и количественном уровнях. Они также способствуют повышению эффективности и качества работы с имиджами за счёт новой пообъектной информации. В данной работе предлагается современная методика анализа имиджей, основанная на результатах обработки большого и уникального объёма накопленных данных с применением технологий машинного обучения. Разработанные алгоритмы позволяют автоматизировать процесс предобработки имиджей, а также процесс структурно-текстурной декомпозиции. Применение глубоких нейронных сетей обеспечило выделение целевых объектов с точностью более 90%, а алгоритмы компьютерного зрения позволили получить их количественную характеристику в виде оценки размеров, форм, ориентаций и топологий. Области применения предлагаемой методики включают в себя: седиментологический анализ (в частности, обнаружение тонких пропластков); дополнение к программам исследований сплошного и бокового керна; дополнение к программам исследований с помощью пластоиспытателя на кабеле (детальное описание особенностей коллекторов в интервалах, не охарактеризованных керном); дополнительная информация для обработки и интерпретации комплекса геологических и геофизических данных (моделирование пласта с использованием детерминированного подхода, критерии распределения для стохастического моделирования, определение петрофизических параметров с высокой степенью достоверности).

Borehole formation microimagers are a powerful tool for analyzing complex reservoirs, providing detailed information about the structural and textural features of formations. The development of state-of-the-art interpretation techniques can optimize existing approaches to microimager data analysis, enable the extraction of new object-level information, and significantly enhance the efficiency and quality of data interpretation. This study proposes a novel workflow for fullbore formation microimager data analysis based on processing a large and unique dataset using machine learning and computer vision techniques. The developed algorithms facilitate the automatic preprocessing of borehole microimager data and their automated structural and textural decomposition. The accuracy of object segmentation by convolutional deep neural networks exceeds 90%, while computer vision algorithms enable the analysis of the sizes, shapes, orientations, and topology of detected objects. The application areas of the proposed methodology include sedimentological analysis (thin-bed analysis); enhancement of core study workflow and formation tester evaluations (detailed characterization of reservoirs in intervals not covered by core samples); and advanced information for processing geological and geophysical data (reservoir modeling using deterministic approaches, distribution criteria for stochastic modeling and determining petrophysical parameters with high reliability).

скважинные имиджерыимиджимикроимиджерысвёрточные нейронные сетиавтоматическая интерпретациякомпьютерное зрениеколичественная геологическая интерпретация данныхborehole formation microimagerconvolution neural networksautomated interpretationcomputer visionquantitative geological interpretationReferencesAgarap A.F. (2019). Deep Learning using Rectified Linear Units (ReLU). ArXiv preprint arXiv:1803.08375. https://doi.org/10.48550/arXiv.1803.08375Agarap A.F. (2019). Deep Learning using Rectified Linear Units (ReLU). ArXiv preprint arXiv:1803.08375. https://doi.org/10.48550/arXiv.1803.08375Azim R.A. (2021). Estimation of fracture network properties from FMI and conventional well logs data using artificial neural network. Upstream Oil and Gas Technology, 7, 100044. https://doi.org/10.1016/j.upstre.2021.100044Azim R.A. (2021). Estimation of fracture network properties from FMI and conventional well logs data using artificial neural network. Upstream Oil and Gas Technology, 7, 100044. https://doi.org/10.1016/j.upstre.2021.100044Bradski G. (2000). The opencv library. Dr. Dobb’s Journal: Software Tools for the Professional Programmer, 25, pp. 120–123.Bradski G. (2000). The opencv library. Dr. Dobb’s Journal: Software Tools for the Professional Programmer, 25, pp. 120–123.Canny J. (1986). A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence, pp. 679–698. https://doi.org/10.1109/TPAMI.1986.4767851Canny J. (1986). A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence, pp. 679–698. https://doi.org/10.1109/TPAMI.1986.4767851Chang Li, Liqiang Sima, Guoqiong Che, Wang Liang, Anjiang Shen, Qingxin Guo, Bing Xie (2020). Vug and fracture characterization and gas production prediction by fractals: Carbonate reservoir of the Longwangmiao Formation in the Moxi-Gaoshiti area, Sichuan Basin. Interpretation, 8(3), pp. 159–171. https://doi.org/10.1190/INT-2019-0260.1Chang Li, Liqiang Sima, Guoqiong Che, Wang Liang, Anjiang Shen, Qingxin Guo, Bing Xie (2020). Vug and fracture characterization and gas production prediction by fractals: Carbonate reservoir of the Longwangmiao Formation in the Moxi-Gaoshiti area, Sichuan Basin. Interpretation, 8(3), pp. 159–171. https://doi.org/10.1190/INT-2019-0260.1Chen T., Guestrin C. (2016). XGBoost: A Scalable Tree Boosting System. The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, San Francisco California USA, pp. 785–794. https://doi.org/10.1145/2939672.2939785Chen T., Guestrin C. (2016). XGBoost: A Scalable Tree Boosting System. The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, San Francisco California USA, pp. 785–794. https://doi.org/10.1145/2939672.2939785Chollet F. (2021). Deep learning with Python. Simon and Schuster, 478 p. Cortes C. (1995). Support-Vector Networks. Machine Learning, 20, pp. 273–297. https://doi.org/10.1023/A:1022627411411Chollet F. (2021). Deep learning with Python. Simon and Schuster, 478 p. Cortes C. (1995). Support-Vector Networks. Machine Learning, 20, pp. 273–297. https://doi.org/10.1023/A:1022627411411De Ville B. (2013). Decision trees. WIREs Computational Stats, 5, pp. 448–455. https://doi.org/10.1002/wics.1278De Ville B. (2013). Decision trees. WIREs Computational Stats, 5, pp. 448–455. https://doi.org/10.1002/wics.1278Fathi, E., Carr, T.R., Faiq, M.A., Panetta, B., Kumar, A., Carney, B.J. (2022). High-quality fracture network mapping using high frequency logging while drilling (LWD) data: MSEEL case study. Machine Learning with Applications, 10, pp. 100421. https://doi.org/10.1016/j.mlwa.2022.100421Fathi, E., Carr, T.R., Faiq, M.A., Panetta, B., Kumar, A., Carney, B.J. (2022). High-quality fracture network mapping using high frequency logging while drilling (LWD) data: MSEEL case study. Machine Learning with Applications, 10, pp. 100421. https://doi.org/10.1016/j.mlwa.2022.100421Fix E. (1985). Discriminatory analysis: nonparametric discrimination, consistency properties. USAF school of Aviation Medicine.Fix E. (1985). Discriminatory analysis: nonparametric discrimination, consistency properties. USAF school of Aviation Medicine.Freund Y., Schapire R.E. (1995). A desicion-theoretic generalization of on-line learning and an application to boosting, in: Vitányi, P. (Ed.), Computational Learning Theory, Lecture Notes in Computer Science. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 23–37. https://doi.org/10.1007/3-540-59119-2_166Freund Y., Schapire R.E. (1995). A desicion-theoretic generalization of on-line learning and an application to boosting, in: Vitányi, P. (Ed.), Computational Learning Theory, Lecture Notes in Computer Science. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 23–37. https://doi.org/10.1007/3-540-59119-2_166Friedman J.H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, pp. 1189–1232. https://doi.org/10.1214/aos/1013203451Friedman J.H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, pp. 1189–1232. https://doi.org/10.1214/aos/1013203451Gabor D. (1946). Theory of communication. Part 1: The analysis of information. Journal of the Institution of Electrical Engineers - Part III: Radio and Communication Engineering, 93, pp. 429–441. https://doi.org/10.1049/ji-3-2.1946.0074Gabor D. (1946). Theory of communication. Part 1: The analysis of information. Journal of the Institution of Electrical Engineers - Part III: Radio and Communication Engineering, 93, pp. 429–441. https://doi.org/10.1049/ji-3-2.1946.0074Geurts P., Ernst D., Wehenkel L. (2006). Extremely randomized trees. Mach Learn, 63, pp. 3–42. https://doi.org/10.1007/s10994-006-6226-1Geurts P., Ernst D., Wehenkel L. (2006). Extremely randomized trees. Mach Learn, 63, pp. 3–42. https://doi.org/10.1007/s10994-006-6226-1Hilt D.E., Seegrist D.W. (1977). Ridge, a computer program for calculating ridge regression estimates. Department of Agriculture, Forest Service, Northeastern Forest Experiment. https://doi.org/10.5962/bhl.title.68934Hilt D.E., Seegrist D.W. (1977). Ridge, a computer program for calculating ridge regression estimates. Department of Agriculture, Forest Service, Northeastern Forest Experiment. https://doi.org/10.5962/bhl.title.68934John G.H., Langley P. (2013). Estimating Continuous Distributions in Bayesian Classifiers. arXiv preprint arXiv:1302.4964. https://doi.org/10.48550/arXiv.1302.4964John G.H., Langley P. (2013). Estimating Continuous Distributions in Bayesian Classifiers. arXiv preprint arXiv:1302.4964. https://doi.org/10.48550/arXiv.1302.4964Kharitontseva P., Gardiner A., Tugarova M., Chernov D., Maksimova E., Churochkin C., Rukavishnikov V. (2021). An Integrated Approach for Formation Micro-Image Rock Typing Based on Petrography Data: A Case Study in Shallow Marine Carbonates. Geosciences, 11(6), pp. 235. https://doi.org/10.3390/geosciences11060235Kharitontseva P., Gardiner A., Tugarova M., Chernov D., Maksimova E., Churochkin C., Rukavishnikov V. (2021). An Integrated Approach for Formation Micro-Image Rock Typing Based on Petrography Data: A Case Study in Shallow Marine Carbonates. Geosciences, 11(6), pp. 235. https://doi.org/10.3390/geosciences11060235Kingma D.P., Ba J. (2017). Adam: A Method for Stochastic Optimization. https://doi.org/10.48550/arXiv.1412.6980Kingma D.P., Ba J. (2017). Adam: A Method for Stochastic Optimization. https://doi.org/10.48550/arXiv.1412.6980Kohonen T. (2013). Essentials of the self-organizing map. Neural Networks, 37, pp. 52–65. https://doi.org/10.1016/j.neunet.2012.09.018Kohonen T. (2013). Essentials of the self-organizing map. Neural Networks, 37, pp. 52–65. https://doi.org/10.1016/j.neunet.2012.09.018Köpüklü O., Babaee M., Hörmann S., Rigoll G. (2019). Convolutional Neural Networks with Layer Reuse. https://doi.org/10.48550/arXiv.1901.09615Köpüklü O., Babaee M., Hörmann S., Rigoll G. (2019). Convolutional Neural Networks with Layer Reuse. https://doi.org/10.48550/arXiv.1901.09615Li, X., Shen, J., Zhu, Z., Wang, L., Li, Z. (2016). Fracture extraction from FMI based on multiscale mathematical morphology. SEG International Exposition and Annual Meeting, SEG-2016. https://doi.org/10.1190/segam2016-13880859.1Li, X., Shen, J., Zhu, Z., Wang, L., Li, Z. (2016). Fracture extraction from FMI based on multiscale mathematical morphology. SEG International Exposition and Annual Meeting, SEG-2016. https://doi.org/10.1190/segam2016-13880859.1McCallum A., Nigam K. (1998). A comparison of event models for naive bayes text classification. AAAI-98 Workshop on Learning for Text Categorization. Madison, WI, pp. 41–48.McCallum A., Nigam K. (1998). A comparison of event models for naive bayes text classification. AAAI-98 Workshop on Learning for Text Categorization. Madison, WI, pp. 41–48.Mohammad Faiq Adenan, Fathi E., Carr T., Panetta B. (2023). Machine learning-based workflow for identifying fractures and baffles from Formation Micro Imager (FMI) log: A practical application in Illinois Basin Decatur Project (IBDP). SEG/AAPG International Meeting for Applied Geoscience & Energy. https://doi.org/10.1190/image2023-3916031.1Mohammad Faiq Adenan, Fathi E., Carr T., Panetta B. (2023). Machine learning-based workflow for identifying fractures and baffles from Formation Micro Imager (FMI) log: A practical application in Illinois Basin Decatur Project (IBDP). SEG/AAPG International Meeting for Applied Geoscience & Energy. https://doi.org/10.1190/image2023-3916031.1Otsu N. (1975). A threshold selection method from gray-level histograms. Automatica, 11, pp. 23–27.Otsu N. (1975). A threshold selection method from gray-level histograms. Automatica, 11, pp. 23–27.Ponziani M., Slob E., Luthi, S., Bloemenkamp R., Le Nir, I. (2013). Fracture characterization from Formation MicroImager data. 75th EAGE Conference & Exhibition incorporating SPE EUROPEC 2013, European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.20130805Ponziani M., Slob E., Luthi, S., Bloemenkamp R., Le Nir, I. (2013). Fracture characterization from Formation MicroImager data. 75th EAGE Conference & Exhibition incorporating SPE EUROPEC 2013, European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.20130805Qifeng Sun, Naiyuan Su, Faming Gong, Qizhen Du. (2023). Blank Strip Filling for Logging Electrical Imaging Based on Multiscale Generative Adversarial Network. Processes, 11(6), 1709. https://doi.org/10.3390/pr11061709Qifeng Sun, Naiyuan Su, Faming Gong, Qizhen Du. (2023). Blank Strip Filling for Logging Electrical Imaging Based on Multiscale Generative Adversarial Network. Processes, 11(6), 1709. https://doi.org/10.3390/pr11061709Rahman M.A., Wang Y. (2016). Optimizing intersection-over-union in deep neural networks for image segmentation. The International symposium on visual computing. Springer, pp. 234–244. https://doi.org/10.1007/978-3-319-50835-1_22Rahman M.A., Wang Y. (2016). Optimizing intersection-over-union in deep neural networks for image segmentation. The International symposium on visual computing. Springer, pp. 234–244. https://doi.org/10.1007/978-3-319-50835-1_22Rennie J.D., Shih L., Teevan J., Karger D.R. (2003). Tackling the poor assumptions of naive bayes text classifiers. Proceedings of the 20th International Conference on Machine Learning (ICML-03), pp. 616–623.Rennie J.D., Shih L., Teevan J., Karger D.R. (2003). Tackling the poor assumptions of naive bayes text classifiers. Proceedings of the 20th International Conference on Machine Learning (ICML-03), pp. 616–623.Rigatti, S.J. (2017). Random forest. Journal of Insurance Medicine, 47, pp. 31–39. https://doi.org/10.17849/insm-47-01-31-39.1Rigatti, S.J. (2017). Random forest. Journal of Insurance Medicine, 47, pp. 31–39. https://doi.org/10.17849/insm-47-01-31-39.1Ronneberger O., Fischer P., Brox T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (Eds.). Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28Ronneberger O., Fischer P., Brox T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (Eds.). Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28Rosenblatt F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65, 386. https://doi.org/10.1037/h0042519Rosenblatt F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65, 386. https://doi.org/10.1037/h0042519Sara U., Akter M., Uddin M.S. (2019). Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. Journal of Computer and Communications, 7, pp. 8–18. https://doi.org/10.4236/jcc.2019.73002Sara U., Akter M., Uddin M.S. (2019). Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. Journal of Computer and Communications, 7, pp. 8–18. https://doi.org/10.4236/jcc.2019.73002Shafiabadi M., Kamkar-Rouhani A., Riabi S.R.G., Kahoo A.R., Tokhmechi B. (2021). Identification of reservoir fractures on FMI image logs using Canny and Sobel edge detection algorithms. Oil & Gas Science and Technology–Revue d’IFP Energies nouvelles, 76, 10. https://doi.org/10.2516/ogst/2020086Shafiabadi M., Kamkar-Rouhani A., Riabi S.R.G., Kahoo A.R., Tokhmechi B. (2021). Identification of reservoir fractures on FMI image logs using Canny and Sobel edge detection algorithms. Oil & Gas Science and Technology–Revue d’IFP Energies nouvelles, 76, 10. https://doi.org/10.2516/ogst/2020086Tahmasebi P. (2018). Multiple point statistics: a review. Handbook of mathematical geosciences: Fifty years of IAMG, pp. 613–643. https://doi.org/10.1007/978-3-319-78999-6_30Tahmasebi P. (2018). Multiple point statistics: a review. Handbook of mathematical geosciences: Fifty years of IAMG, pp. 613–643. https://doi.org/10.1007/978-3-319-78999-6_30Tibshirani R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B: Statistical Methodology, 58, pp. 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.xTibshirani R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B: Statistical Methodology, 58, pp. 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.xWalker, S.H., Duncan, D.B. (1967). Estimation of the probability of an event as a function of several independent variables. Biometrika, 54, pp. 167–179. https://doi.org/10.1093/biomet/54.1-2.167Walker, S.H., Duncan, D.B. (1967). Estimation of the probability of an event as a function of several independent variables. Biometrika, 54, pp. 167–179. https://doi.org/10.1093/biomet/54.1-2.167Ye S.-J., Rabiller P. (2000). A new tool for electro-facies analysis: multiresolution graph-based clustering. The SPWLA Annual Logging Symposium, SPWLA, SPWLA-2000.Ye S.-J., Rabiller P. (2000). A new tool for electro-facies analysis: multiresolution graph-based clustering. The SPWLA Annual Logging Symposium, SPWLA, SPWLA-2000.Yu L., Li Z., Xu M., Gao Y., Luo J., Zhang J. (2022). Distribution-Aware Margin Calibration for Semantic Segmentation in Images. Int J Comput Vis, 130, pp. 95–110. https://doi.org/10.1007/s11263-021-01533-0Yu L., Li Z., Xu M., Gao Y., Luo J., Zhang J. (2022). Distribution-Aware Margin Calibration for Semantic Segmentation in Images. Int J Comput Vis, 130, pp. 95–110. https://doi.org/10.1007/s11263-021-01533-0Zou H., Hastie T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society Series B: Statistical Methodology, 67, pp. 301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.xZou H., Hastie T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society Series B: Statistical Methodology, 67, pp. 301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x

The authors declare that there are no conflicts of interest present.