Direct mineral content prediction from drill core images via transfer learning

TL;DR

This work demonstrates that convolutional neural networks with transfer learning can predict lithology and mineral content directly from drill-core images. By preprocessing core photographs and applying pretrained backbones (e.g., ResNet152) for six-formation classification, the model achieves $96.7\%$ test accuracy, and the embedded regression head—trained via transfer learning on a limited mineral-content dataset—yields $R^2$ values up to $0.811$ for total clay and strong per-formation performance. Comparisons with MultiMin log analyses and bulk XRD measurements show good agreement, confirming the viability of image-based mineral-content estimation at 1 cm resolution. The results indicate a promising path toward reducing lab work and accelerating subsurface characterization, while highlighting the need for more data and exploration of alternative backbones and data-augmentation strategies to improve generalizability.

Abstract

Deep subsurface exploration is important for mining, oil and gas industries, as well as in the assessment of geological units for the disposal of chemical or nuclear waste, or the viability of geothermal energy systems. Typically, detailed examinations of subsurface formations or units are performed on cuttings or core materials extracted during drilling campaigns, as well as on geophysical borehole data, which provide detailed information about the petrophysical properties of the rocks. Depending on the volume of rock samples and the analytical program, the laboratory analysis and diagnostics can be very time-consuming. This study investigates the potential of utilizing machine learning, specifically convolutional neural networks (CNN), to assess the lithology and mineral content solely from analysis of drill core images, aiming to support and expedite the subsurface geological exploration. The paper outlines a comprehensive methodology, encompassing data preprocessing, machine learning methods, and transfer learning techniques. The outcome reveals a remarkable 96.7% accuracy in the classification of drill core segments into distinct formation classes. Furthermore, a CNN model was trained for the evaluation of mineral content using a learning data set from multidimensional log analysis data (silicate, total clay, carbonate). When benchmarked against laboratory XRD measurements on samples from the cores, both the advanced multidimensional log analysis model and the neural network approach developed here provide equally good performance. This work demonstrates that deep learning and particularly transfer learning can support extracting petrophysical properties, including mineral content and formation classification, from drill core images, thus offering a road map for enhancing model performance and data set quality in image-based analysis of drill cores.

Figures (12)

• Figure 1: Left: Cartographic representation illustrating the geographical region of northern Switzerland. The map specifically features the borehole site of Trüllikon 1-1 which is selected for the data analysis of this study. Background: ©Data:swisstopo and hillshading from NASA SRTM. Right: Abstracted lithological profile of the section Trüllikon 1-1 showing the interval between 770.35m and 939m depth. The blue bars denote the available data segments.
• Figure 2: Preprocessing pipeline, consisting of five distinct steps, from the original image (a) to the final 1cm image segments (e). The 1cm segments with the red cross next to the image are excluded from the analysis, since the cracked area size is bigger than 5000 pixels.
• Figure 3: Architecture of the neural network for the mineral content regression with three formation models as a backbone architecture
• Figure 4: Left: Formation classification results for the test data set for different backbone architectures with 14 different seeds each. Right: Confusion matrix for the formation classification model based on ResNet152 with artefact threshold T=5000 pixels for the test data set.
• Figure 5: Counts of true and false predicted classes for each formation. In the x-axis, the classes are numbered; C0 corresponds to Park.Wuertt.Schichten, C1 to Humphr. Formation, ..., C5 to Staffelegg Formation. For a better understanding of the figure, consider e.g. the Park. Wuertt.Schichten, here the first 6 x-labels are relevant, the number of counts, 366 for True C0 means that 366 images were correctly classified as Park. Wuertt.Schichten, so class C0; no image was classified as class C1, C2, C3, or C5 and only one image that should have been a Park. Wuertt.Schicht was classified as class C4 (Opalinus clay), so this was misclassified.