Benchmarking deep CNN architectures for micro-CT rock image classification
Authors:
- Daniel Milian PérezDPDaniel Milian Pérez
- Daniel MilianDMDaniel Milian
- Abel Gámez RodríguezARAbel Gámez Rodríguez
- Abel GámezAGAbel Gámez
- Yaicel Ge ProenzaYPYaicel Ge Proenza
- Daniel Amancio DuarteDDDaniel Amancio Duarte
- da SilvaDSda Silva
- Mário Augusto BezerraMBMário Augusto Bezerra
- de la NovalDNde la Noval
- Fabián Luis MenaFMFabián Luis Mena
- Jose Antonio BarbosaJBJose Antonio Barbosa
- Dmitriy A. MartyushevDmitriy A. Martyushev
Open Access
- 27 October 2026
- journal article
- research article
- Published by Springer Nature in Earth Science Informatics
- Vol. 19 (12) , 229
Abstract
This study presents a benchmark analysis of deep convolutional neural network (CNN) architectures for rock type classification using high-resolution two-dimensional grayscale slices extracted from 3D micro-computed tomography (µCT) datasets. The main contribution of this work is the development of a controlled and systematic benchmarking framework for CNN architectures under standardized µCT imaging conditions, rather than expanding the number of lithological classes or facies. A dataset comprising 52,706 two-dimensional grayscale µCT slices derived from 11 sandstone samples, 16 limestone samples, and eight shale plugs extracted from a single core was used as a three-class geological classification problem. Seventeen pretrained CNN architectures were evaluated under a standardized workflow incorporating data augmentation, area-like image downsampling, and specimen-level grouped three-fold cross-validation to reduce data leakage and account for the physical sampling structure. Model performance was assessed using accuracy, loss, weighted precision and weighted recall, weighted F1-score, mean per-class accuracy (MPCA), confusion matrices, specimen-level majority-vote metrics, and learning curves. Several architectures, including DenseNet169, DenseNet121, DenseNet201, and InceptionV3, achieved reliable classification performance across all metrics with stable convergence behavior. Sandstone and limestone samples were the most frequently confused classes, whereas shale samples were classified more consistently within the available dataset. Comparison with previous studies highlights recurring challenges such as intra-class variability, overfitting in small datasets, and the influence of image modality on model performance. Overall, the results provide a reproducible Earth science informatics framework for evaluating deep learning models in micro-CT-based rock image classification and digital rock analysis.Keywords
Funding Information
- Universidade Federal de Pernambuco
This publication has 32 references indexed in Scilit:
- Reservoir heterogeneity analysis using multi-directional textural attributes from deep learning-based enhanced acoustic impedance inversion: A study from Poseidon, NW shelf AustraliaEnergy Geoscience, 2023
- A critical review on intelligent optimization algorithms and surrogate models for conventional and unconventional reservoir production optimizationFuel, 2023
- Quantitative evaluation of fracture porosity from dual laterlog based on deep learning methodEnergy Geoscience, 2023
- Correction to: Estimating permeability of 3D micro-CT images by physics-informed CNNs based on DNSComputational Geosciences, 2023
- Impact of dataset size and convolutional neural network architecture on transfer learning for carbonate rock classificationComputers & Geosciences, 2022
- Micro-computed tomography of sandstone rocks: Raw, filtered and segmented datasetsData in Brief, 2022
- Petrographic microfacies classification with deep convolutional neural networksComputers & Geosciences, 2020
- An Introduction to Enhanced Oil Recovery2018
- Reservoirs and Reservoir Fluids2017
- Petroleum System: Nature's Distribution System for Oil and Gas2004