Lithology classification of whole core CT scans using convolutional neural networks

Abstract

X-ray computerized tomography (CT) images as digital representations of whole cores can provide valuable information on the composition and internal structure of cores extracted from wells. Incorporation of millimeter-scale core CT data into lithology classification workflows can result in high-resolution lithology description. In this study, we use 2D core CT scan image slices to train a convolutional neural network (CNN) whose purpose is to automatically predict the lithology of a well on the Norwegian continental shelf. The images are preprocessed prior to training, i.e., undesired artefacts are automatically flagged and removed from further analysis. The training data include expert-derived lithofacies classes obtained by manual core description. The trained classifier is used to predict lithofacies on a set of test images that are unseen by the classifier. The prediction results reveal that distinct classes are predicted with high recall (up to 92%). However, there are misclassification rates associated with similarities in gray-scale values and transport properties. To postprocess the acquired results, we identified and merged similar lithofacies classes through ad hoc analysis considering the degree of confusion from the prediction confusion matrix and aided by porosity–permeability cross-plot relationships. Based on this analysis, the lithofacies classes are merged into four rock classes. Another CNN classifier trained on the resulting rock classes generalize well, with higher pixel-wise precision when detecting thin layers and bed boundaries compared to the manual core description. Thus, the classifier provides additional and complementing information to the already existing rock type description. Article Highlights A workflow for automatic lithofacies classification using whole core 2D image slices and CNN is introduced. The proposed classifier shows lithology-dependent accuracies. The prediction confusion matrix is exploited as a tool to identify lithofacies classes with similar transport properties and to automatically generate lithofacies hierarchies.

Impact of dataset size and convolutional neural network architecture on transfer learning for carbonate rock classification

“…The results from this study show great potential for the use of deep learning in carbonate classification from digital images. Several studies now have applied CNN models to broad lithofacies classifications in both core and thin section images (Baraboshkin et al, 2020;Pires de Lima et al, 2020;Koeshidayatullah et al, 2020;Chawshin et al, 2021). However, it remains to be determined which of the available CNN architectures performs best for the classification of carbonate core images.…”

“…Current deep learning applications within the geoscientific community include, but are not limited to, seismic facies classification (e.g. West et al, 2002;Chevitarese et al, 2018), lithofacies classification from wireline logs (e.g. Bestagini et al, 2017;Halotel et al, 2020), volcanic ash detection (e.g.…”

Mechanistic analysis of matrix-acid treatment of carbonate formations: An experimental core flooding study

“…The CT imaging is one of the most current nondestructive methods for examining the whole cores at a submillimeter resolution. The digital images of the core can aid toward the automation of the core classification process [ 75 ]. Whole core CT scanning has a long history in helping the engineers and/or geologists to study the cores [ 76 ].…”

Machine learning-based classification of petrofacies in fine laminated limestones

“…Furthermore, the manual labeling of properties of interest, either lithofacies (groups of rocks that share similar lithologic or physical characteristics), or petrofacies (groups of rocks that share similar petrographic or mineralogical characteristics) regarding variations found from site to site over the borehole data can also be ambiguous, expensive, and time-consuming (Edwards et al 2017, Lineman et al 1987. This challenge has led to the development of automated identification and classification computation tools that process well log observations (Hall 2016, Halotel et al 2019, Merembayev et al 2021, Silva et al 2020) and core images (Chawshin et al 2021, Lima et al 2019, Thomas et al 2011). These approaches allow fast and reliable identification/correlation of geological properties from well logs (Wu et al 2018), to build sophisticated models (Ertekin & Sun 2019, Othman et al 2021.…”