Image Processing and Machine Learning Approaches for Petrographic Thin Section Analysis (Russian)
- Semen Budennyy (Center for Engineering and Technology of Moscow Institute of Physics and Technology) | Alexey Pachezhertsev (Center for Engineering and Technology of Moscow Institute of Physics and Technology) | Alexander Bukharev (Center for Engineering and Technology of Moscow Institute of Physics and Technology) | Artem Erofeev (Center for Engineering and Technology of Moscow Institute of Physics and Technology) | Dmitry Mitrushkin (Center for Engineering and Technology of Moscow Institute of Physics and Technology) | Boris Belozerov (NTC Gazpromneft)
- Document ID
- Society of Petroleum Engineers
- SPE Russian Petroleum Technology Conference, 16-18 October, Moscow, Russia
- Publication Date
- Document Type
- Conference Paper
- 2017. Society of Petroleum Engineers
- 6.1.5 Human Resources, Competence and Training, 6.1 HSSE & Social Responsibility Management, 6 Health, Safety, Security, Environment and Social Responsibility, 1.2.3 Rock properties, 5.5.2 Core Analysis, 7.6.6 Artificial Intelligence
- 2 in the last 30 days
- 139 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 9.50|
|SPE Non-Member Price:||USD 28.00|
The PDF file of this paper is in Russian.
The article presents the methodology of petrographic thin section analysis, combining the algorithms of image processing and statistical learning. The methodology includes the structural description of thin sections and rock classification based on images obtained from polarized optical microscope. To evaluate the properties of structural objects in thin section (grain, cement, voids, cleavage), first they are segmented by watershed method with advanced noise reduction, preserving the boundaries of grains.
Analysis of segmentation for test thin sections showed a fairly accurate contouring of mineral grains which makes possible automatically carry out the calculation of their key features (size, perimeter, contour features, elongation, orientation, etc.). The paper presents an example of particle size analysis – definition of grains size class. The roundness and rugosity coefficients of grains are estimated also. Statistical analysis of templates for manual determination of roundness and rugosity coefficients revealed drawback of examined templates in terms statistical accuracy (high dispersion of coefficient for all grain within one template, outliers presence).
In the frame of classification problem the feature importance analysis and clustering of non-correctly segmented grains are handled. The classifier for rock type definition (sandstone, limestone, dolomite) is trained with decision tree method, while the classifier of mineral composition of sandstones (greywackes, arkose) is learnt with "random forest" method. Both classifiers are learnt in the feature space generated from segmented grains and their evaluated properties.
As a result, we proved the possibility to conduct automatic quantitative and qualitative analysis of thin sections applying image processing and statistical learning methods.
|File Size||1 MB||Number of Pages||13|
Varfolomeev I.A., Yakimchuk I.V., Denisenko A.S. 2016. Integrated Study of Thin Sections: Optical Petrography and Electron Microscopy. SPE Russian Petroleum Technology Conference and Exhibition, 24-26 October, Moscow, Russia. SPE-182071-RU. https://doi.org/10.2118/182071-RU.
Al-Bazzaz W.H., Al-Mehanna Y.W. 2007. Porosity, Permeability, and MHR Calculations Using SEM and Thin-section Images for Characterizing Complex Mauddud-Burgan Carbonate Reservoir. SPE Asia Pacific Oil & Gas Conference and Exhibition, Indonesia, 30 October-1 November. SPE-110730. https://doi.org/10.2118/110730-MS
Bennetzen M.V., Marquez X, Mogensen K. 2014. Automatic High-Throughput Detection of Fluid Inclusions in Thin-Section Images using a Novel Algorithm. International Petroleum Technology Conference, Qatar, 19-22 January. IPTC-17680-MS. https://doi.org/10.2523/IPTC-17680-MS
Wardaya P.D., Khairy H., Sum C.W. 2013. Extracting Physical Properties from Thin Section: Another Neural Network Contribution in Rock Physics. International Petroleum Technology Conference. China, 26-28 March. IPTC-16977-MS. https://doi.org/10.2523/IPTC-16977-MS.
Wardaya P.D., Khairy H., Sum C.W. 2013. Integrating digital image processing and artificial neural network for estimating porosity from thin section. International Petroleum Technology Conference.- China. 26-28 March. IPTC-16959-MS. https://doi.org/10.2523/IPTC-16959-MS.