Search

Understanding the spatial variation in lithology is crucial for characterizing reservoirs, as it governs the distribution of petrophysical characteristics. This study focuses on predicting the lithology of carbonate rocks (limestone, argillaceous limestone, marly limestone, and marl) within the Kometan Formation, Khabbaz Oil Field, Northern Iraq, using well logs. Precise lithology prediction was achieved by applying multivariate regression method on neutron, sonic, and density logs. Gamma-ray and elemental concentrations from bulk-rock X-ray fluorescence spectroscopy were employed to identify clay minerals, paleoenvironments, and quantify the shale content. The results indicate that the Kometan Formation predominantly comprises limestone, marl, marly limestone, and argillaceous limestone in the middle section. The middle part exhibits a higher shale content compared to the lower and upper parts. A statistically significant correlation (R 2  = 0.83-0.85) between described and predicted lithology was established. The model with a higher coefficient of determination (0.85) was tested for further predictions in other wells in the Kirkuk Oil Field. This research can be valuable for lithological and petrophysical characterization of carbonate reservoirs and electrofacies analysis, particularly in situations where core data is unavailable., Competing Interests: The author whose name is listed immediately below certifies that they have no affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent-licensing arrangements), or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript., (© 2024 The Authors.)

In this paper, we considered one of the problems that arise during drilling automation, namely the automation of lithology identification from drill cuttings images. Usually, this work is performed by experienced geologists, but this is a tedious and subjective process. Drill cuttings are the cheapest source of rock formation samples; therefore, reliable lithology prediction can greatly reduce the cost of analysis during drilling. To predict the lithology content from images of cuttings samples, we used a convolutional neural network (CNN). For training a model with an acceptable generalization ability, we applied dataset-cleaning techniques, which help to reveal bad samples, as well as samples with uncertain labels. It was shown that the model trained on a cleaned dataset performs better in terms of accuracy. Data cleaning was performed using a cross-validation technique, as well as a clustering analysis of embeddings, where it is possible to identify clusters with distinctive visual characteristics and clusters where visually similar samples of rocks are attributed to different lithologies during the labeling process.