EQUIVARIANT GEOMETRIC LEARNING FOR DIGITAL ROCK PHYSICS: ESTIMATING FORMATION FACTOR AND EFFECTIVE PERMEABILITY TENSORS FROM MORSE GRAPH

We present a SE(3)-equivariant graph neural network (GNN) approach that directly predicts the formation factor and effective permeability from micro-CT images. Fast Fourier Transform (FFT) solvers are established to compute both the formation factor and effective permeability, while the topology and geometry of the pore space are represented by a persistence-based Morse graph. Together, they constitute the database for training, validating, and testing the neural networks. While the graph and Euclidean convolutional approaches both employ neural networks to generate low -dimensional latent space to represent the features of the microstructures for forward predictions, the SE(3) equivariant neural network is found to generate more accurate predictions, especially when the training data are limited. Numerical experiments have also shown that the new SE(3) approach leads to predictions that fulfill the material frame indifference whereas the predictions from classical convolutional neural networks (CNNs) may suffer from spurious dependence on the coordinate system of the training data. Comparisons among predictions inferred from training the CNN and those from graph convolutional neural networks with and without the equivariant constraint indicate that the equivariant graph neural network seems to perform better than the CNN and GNN without enforcing equivariant constraints.

Automated summary

We propose a SE(3)-equivariant graph neural network (GNN) approach to predict the formation factor and effective permeability from micro-CT images. The method uses FFT solvers to compute the formation factor and effective permeability, and represents the pore space topology and geometry using a persistence-based Morse graph. Experimental results show that the SE(3) approach generates more accurate predictions, especially with limited training data, and fulfills material frame indifference.