Micro-CT sub-volume dataset for pore-scale rock property prediction using 3D CNNs
Abstract
This dataset contains 9261 3D micro-CT image sub-volumes extracted from carbonate rock samples. The data were used to train and evaluate 3D convolutional neural network models for predicting pore-scale rock properties, including porosity, pore size, throat size, coordination number, and pore shape factor.
Fields of Study & Subjects
Enhanced Oil Recovery Techniques
Hydrocarbon exploration and reservoir analysis
Seismic Imaging and Inversion Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 5 February 2026
- Document type
- Dataset