Integration of Adversarial Autoencoders With Residual Dense Convolutional Networks for Estimation of Non‐Gaussian Hydraulic Conductivities. Issue 2 (3rd February 2020)

• Record Type: Journal Article
• Authors: Mo, Shaoxing; Zabaras, Nicholas; Shi, Xiaoqing; Wu, Jichun
• Is Part Of: Water resources research. Volume 56:Issue 2(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-02-03
• Subjects: Hydrology -- Periodicals; 333.91
• DOI: 10.1029/2019WR026082
• Languages: English
• ISSNs: 0043-1397

Abstract

Abstract: Inverse modeling for the estimation of non‐Gaussian hydraulic conductivity fields in subsurface flow and solute transport models remains a challenging problem. This is mainly due to the non‐Gaussian property, the nonlinear physics, and the fact that many repeated evaluations of the forward model are often required. In this study, we develop a convolutional adversarial autoencoder (CAAE) to parameterize non‐Gaussian conductivity fields with heterogeneous conductivity within each facies using a low‐dimensional latent representation. In addition, a deep residual dense convolutional network (DRDCN) is proposed for surrogate modeling of forward models with high‐dimensional and highly complex mappings. The two networks are both based on a multilevel residual learning architecture called residual‐in‐residual dense block. The multilevel residual learning strategy and the dense connection structure ease the training of deep networks, enabling us to efficiently build deeper networks that have an essentially increased capacity for approximating mappings of very high complexity. The CAAE and DRDCN networks are incorporated into an iterative ensemble smoother to formulate an inversion framework. The numerical experiments performed using 2‐D and 3‐D solute transport models illustrate the performance of the integrated method. The obtained results indicate that the CAAE is a robust parameterization method for non‐Gaussian conductivity fields with different heterogeneity patterns. The DRDCN is able to obtain accurate approximations of the forward models with high‐dimensional and highly complex mappings using relatively limited training data. The CAAE and DRDCN methods together significantly reduce the computation time required to achieve accurate inversion results. Key Points: A convolutional adversarial autoencoder is developed to parameterize non‐Gaussian conductivity fields with multimodal distributions A deep residual dense convolutional network is introduced as a surrogate of the forward physics‐based model The integrated method is tested with inverse problems for the estimation of non‐Gaussian conductivities in solute transport modeling