The description of rocks is one of the most time-consuming tasks in the everyday work of a geologist, especially when very accurate description is required. We here present a method that reduces the time needed for accurate description of rocks, enabling the geologist to work more efficiently. We describe the application of methods based on color distribution analysis and feature extraction. Then we focus on a new approach, used by us, which is based on convolutional neural networks. We used several well-known neural network architectures (AlexNet, VGG, GoogLeNet, ResNet) and made a comparison of their performance. The precision of the algorithms is up to 95% on the validation set with GoogLeNet architecture. The best of the proposed algorithms can describe 50 m of full-size core in one minute.
With the rapid progress of imaging methods it is now possible to obtain detailed rock structure information on different scales, ranging from nanometers to micrometers. Such knowledge facilitates use of pore-scale modeling approaches to predict numerous physical properties based on three dimensional structural data. Pore-scale modeling approaches can simulate different processes in the rock under natural conditions (pressure, temperature, etc.), which are more difficult to simulate in the laboratory. This is especially important for unconventional reservoir rocks such as the Bazhen formation siliceous rocks (black shales) used in this study. Based on X-ray microtomography and SEM imaging we develop a detailed categorization of different types of porosities (including micro, i.e. larger than µm size, and nano, i.e. sub-micron size, porosities) for samples of Bazhen siliceous rocks. Standard pore-scale modeling techniques do not account for different flow regimes within different pore sizes. Thus, we develop a pore-network model with different physics of gas flow for micro- and nanoporosity. High-resolution images are used for stochastic reconstructions of 3D structure and subsequently used for modeling of gas permeability. Resulting permeability values are in a good agreement with gas permeabilities measured for Bazhenov siliceous rocks. Finally, we present a framework to model gas permeability of unconventional reservoir rocks using multi-scale 3D structure information based on microCT scans and high resolution SEM/FIB-SEM imaging techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.