Subsurface Characterization using Deep Learning Approaches

Estimation of unknown subsurface parameters from indirect hydrogeological and geophysical measurements is usually an ill-posed inverse problem and can be computationally challenging for high-dimensional and big data applications as most of the inversion techniques require iterative calls to complex multiphysics models to compute Jacobians and subsequent inversion of large dense matrices. In this presentation, deep learning approaches are utilized to accelerate inverse modeling, data assimilation, and uncertainty quantification for geoscience parameter estimation and subsequent forecast. Reduced order models of PDEs are constructed on a nonlinear manifold of low dimensionality through deep generative models so that uncertainty quantification can be performed on the low dimensional latent space in a Bayesian framework. Combined with automatic differentiation and stochastic Newton-type MCMC methods, it is shown that deep learning-based methods can perform the inversion operation much faster than traditional inversion methods, which offers great promise in various subsurface applications. The improvement and performance of these methodologies are illustrated by applying them to subsurface permeability characterization examples. SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525.