Machine learning for accelerating effective property prediction for poroelasticity problem in stochastic media
This work addresses the computational bottleneck of property prediction in stochastic poroelasticity, which is important for applications like geophysics or materials science, but it appears incremental as it applies existing deep learning techniques to this specific domain.
The paper tackles the problem of predicting effective properties for poroelasticity in stochastic media by developing a deep neural network method that maps stochastic fields to effective properties, achieving fast and accurate predictions in 2D and 3D model problems.
In this paper, we consider a numerical homogenization of the poroelasticity problem with stochastic properties. The proposed method based on the construction of the deep neural network (DNN) for fast calculation of the effective properties for a coarse grid approximation of the problem. We train neural networks on the set of the selected realizations of the local microscale stochastic fields and macroscale characteristics (permeability and elasticity tensors). We construct a deep learning method through convolutional neural network (CNN) to learn a map between stochastic fields and effective properties. Numerical results are presented for two and three-dimensional model problems and show that proposed method provide fast and accurate effective property predictions.