Predicting CO₂ Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network

Abstract

Numerical simulation of flow and transport in heterogeneous formations has long been studied, especially for uncertainty quantification and risk assessment. The high computational cost associated with running large‐scale numerical simulations in a Monte Carlo sense has motivated the development of surrogate models, which aim to capture the important input‐output relations of physics‐based models but require only a fraction of the cost of full model runs. In this work, we formulate a conditional deep convolutional generative adversarial network (cDC‐GAN) surrogate model to learn the dynamic functional mappings in multiphase models. The cDC‐GAN belongs to a class of semisupervised learning methods that can be used to learn the data generation processes. Like the original GAN, a main strength of the cDC‐GAN is that it includes a self‐training scheme for improving the quality of generative modeling in a game theoretic framework, without requiring extensive statistical knowledge and assumptions on input data distributions. In particular, our cDC‐GAN model is designed to learn cross‐domain mappings between high‐dimensional input (e.g., permeability) and output (e.g., phase saturations) pairs, with the ability to incorporate conditioning information (e.g., prediction time). As a use case, we demonstrate the performance of cDC‐GAN for predicting the migration of carbon dioxide (CO2) plume in heterogeneous carbon storage reservoirs, which has both numerical and practical significance because of the safe storage requirements now mandated in many countries. Results show that cDC‐GAN achieves high accuracy in predicting the spatial and temporal evolution patterns of the injected CO2 plume, as compared to the original results obtained using a compositional reservoir simulator. The performance of cDC‐GAN models, trained using the same number of training samples, stays relatively robust when the level of spatial heterogeneity is increased. Our cDC‐GAN is pattern based and is not limited by the underlying physics. Thus, it provides a general framework for developing surrogate models, and for conducting uncertainty analyses for a wide range of physics‐based models used in both groundwater and subsurface energy exploration applications.

Downscaling Satellite and Reanalysis Precipitation Products Using Attention-Based Deep Convolutional Neural Nets

“…Mao et al (2016) showed that the use of skip connections helps the training process to converge much faster and attain a higher-quality local optimum. So far, U-Net and its variants have been used in a large number of DL applications in geosciences (Sun, 2018;Arge et al, 2019;Karimpouli and Tahmasebi, 2019;Mo et al, 2019;Zhong et al, 2019;Zhu et al, 2019).…”

Inversion of Time‐Lapse Seismic Reservoir Monitoring Data Using CycleGAN: A Deep Learning‐Based Approach for Estimating Dynamic Reservoir Property Changes

“…For this study, CycleGAN is implemented by using deep convolutional neural networks, as shown in Zhong, Sun, and Jeong () (Figure ). Similar to the original CycleGAN design presented in Zhu et al (), the two generative models share the same end‐to‐end deep learning neural network architecture, which includes a series of convolutional layers to extract fine‐scale features from the input data, followed by a series of deconvolutional layers to learn coarse‐scale features and to generate a target image that has the same sizes as the input data (i.e., ).…”

Integration of Adversarial Autoencoders With Residual Dense Convolutional Networks for Estimation of Non‐Gaussian Hydraulic Conductivities

“…The two factors together make the commonly used surrogate methods, such as Gaussian processes (Rasmussen & Williams, ) and polynomial chaos expansion (Xiu & Karniadakis, ), difficult to work. Deep neural networks have already exhibited a promising and impressive performance for surrogate modeling of forward models with high‐dimensional input and output fields (Kani & Elsheikh, ; Mo, Zabaras, et al, ; Mo, Zhu, et al ; Sun, ; Tripathy & Bilionis, ; Zhong et al, ; Zhu & Zabaras, ; Zhu et al, ). For example, in Tripathy and Bilionis () a deep neural network was proposed to build a surrogate model for a single‐phase flow forward model.…”