Reconstruction of 3D Porous Media From 2D Slices
This addresses the challenge of obtaining representative rock samples in earth sciences, offering a method to generate similar 3D structures from partial 2D data, which is incremental as it builds on existing deep learning techniques for reconstruction.
The paper tackles the problem of generating 3D porous media samples from limited 2D slices, proposing a deep learning architecture that reconstructs 3D structures as the most probable based on a fitted distribution, with numerical experiments showing good reconstruction in terms of Minkowski functionals.
In many branches of earth sciences, the problem of rock study on the micro-level arises. However, a significant number of representative samples is not always feasible. Thus the problem of the generation of samples with similar properties becomes actual. In this paper, we propose a novel deep learning architecture for three-dimensional porous media reconstruction from two-dimensional slices. We fit a distribution on all possible three-dimensional structures of a specific type based on the given dataset of samples. Then, given partial information (central slices), we recover the three-dimensional structure around such slices as the most probable one according to that constructed distribution. Technically, we implement this in the form of a deep neural network with encoder, generator and discriminator modules. Numerical experiments show that this method provides a good reconstruction in terms of Minkowski functionals.