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.

No abstract

No abstract

No abstract

The paper describes the principal possibility of using machine learning methods for verifying and restoring the quality of oilfield measurements. Basic methods for screening incorrect values have been given and approaches for solving three problems have been recommended: Correctness analysis of well logging data Quality control of physical and chemical fluid properties (PVT-studies) Separation between the base production and effect from well interventions (WI) to predict the performance of hydraulic fracturing (frac). The main deliverable is a set of algorithms based on machine learning methods, which allows to automatically process large volumes of field data. A number of approaches is proposed, including using modern methods of machine learning, to restore the missing values and the quality of algorithms operation.