RockGPT: reconstructing three-dimensional digital rocks from single two-dimensional slice with deep learning
Authors:
Open Access
- 11 April 2022
- journal article
- research article
- Published by Springer Nature in Computational Geosciences
- Vol. 26 (3) , 677-696
Abstract
Random reconstruction of three-dimensional (3D) digital rocks from two-dimensional (2D) slices is crucial for elucidating the microstructure of rocks and its effects on pore-scale flow in terms of numerical modeling, since massive samples are usually required to handle intrinsic uncertainties. Despite remarkable advances achieved by traditional process-based methods, statistical approaches and recently famous deep learning-based models, few works have focused on producing several kinds of rocks with one trained model and allowing the reconstructed samples to approximately satisfy certain given properties, such as porosity. To fill this gap, we propose a new framework with deep learning, named RockGPT, which is composed of VQ-VAE and conditional GPT, to synthesize 3D samples based on a single 2D slice from the perspective of video generation. The VQ-VAE is utilized to compress high-dimensional input video, i.e., the sequence of continuous rock slices, to discrete latent codes and reconstruct them. In order to obtain diverse reconstructions, the discrete latent codes are modeled using conditional GPT in an autoregressive manner, while incorporating conditional information from a given slice, rock type, and porosity. We conduct two experiments on five kinds of rocks, and the results demonstrate that RockGPT can produce different kinds of rocks with a single model, and the porosities of reconstructed samples can distribute around specified targets with a narrow range. In a broader sense, through leveraging the proposed conditioning scheme, RockGPT constitutes an effective way to build a general model to produce multiple kinds of rocks simultaneously that also satisfy user-defined properties.Keywords
All Related Versions
Funding Information
- Shenzhen Key Laboratory of Natural Gas Hydrates (ZDSYS20200421111201738)
- Postdoctoral Research Foundation of China (2020M682830)
This publication has 35 references indexed in Scilit:
- MS-CCSIM: Accelerating pattern-based geostatistical simulation of categorical variables using a multi-scale search in Fourier spaceComputers & Geosciences, 2014
- Nanometer‐scale characterization of microscopic pores in shale kerogen by image analysis and pore‐scale modelingGeochemistry, Geophysics, Geosystems, 2013
- Fiji: an open-source platform for biological-image analysisNature Methods, 2012
- Multiple-point geostatistical modeling based on the cross-correlation functionsComputational Geosciences, 2012
- A multiple-point statistics algorithm for 3D pore space reconstruction from 2D imagesAdvances in Water Resources, 2011
- Continuum reconstruction of the pore scale microstructure for Fontainebleau sandstonePhysica A: Statistical Mechanics and its Applications, 2010
- 3-D Pore-Scale Modelling of Sandstones and Flow Simulations in the Pore NetworksSPE Journal, 1997
- Multivariate Geostatistics: Beyond Bivariate Moments1993
- Flow in simulated porous mediaInternational Journal of Multiphase Flow, 1990
- A new three-dimensional modeling technique for studying porous mediaJournal of Colloid and Interface Science, 1984