Published on Wed Jan 08 2020

Bayesian Inversion Of Generative Models For Geologic Storage Of Carbon Dioxide

Gavin H. Graham, Yan Chen

Carbon capture and storage (CCS) can aid decarbonization of the atmosphere. A framework utilizing unsupervised learning is used to generate a range of subsurface geologic volumes.

0
0
0
Abstract

Carbon capture and storage (CCS) can aid decarbonization of the atmosphere to limit further global temperature increases. A framework utilizing unsupervised learning is used to generate a range of subsurface geologic volumes to investigate potential sites for long-term storage of carbon dioxide. Generative adversarial networks are used to create geologic volumes, with a further neural network used to sample the posterior distribution of a trained Generator conditional to sparsely sampled physical measurements. These generative models are further conditioned to historic dynamic fluid flow data through Bayesian inversion to improve the resolution of the forecast of the storage capacity of injected carbon dioxide.

Thu Feb 15 2018
Machine Learning
Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models
Generative adversarial Networks (GANs) have been shown to be a successful method for generating unconditional simulations of pore- and reservoir-scale models. This contribution leverages the differentiable nature of neural networks to extend GANs to the conditional simulation of three-dimensional
0
0
0
Sun Apr 07 2019
Machine Learning
Parametrization of stochastic inputs using generative adversarial networks with application in geology
This is done by training a neural network to generate samples from the data. By emulating the data generating process, the relevant statistics of the data are replicated. The method is assessed in subsurface flow problems, where effective parametrization is important.
0
0
0
Thu Apr 29 2021
Neural Networks
Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks
0
0
0
Fri Jul 13 2018
Machine Learning
Parametric generation of conditional geological realizations using generative neural networks
Deep learning techniques are increasingly being considered for geological applications. The challenges are dominated by high-dimensional spatial data dominated by multipoint statistics. The method obtains a neural network capable of producing very complex geological patterns.
0
0
0
Wed Aug 16 2017
Machine Learning
Training-image based geostatistical inversion using a spatial generative adversarial neural network
Probabilistic inversion within a multiple-point statistics framework is oftencomputationally prohibitive for high-dimensional problems. We introduce and evaluate a new training-image based inversion approach for complex geologic media. Our approach relies on a deep neural network of the generative adversarial network (GAN) type.
0
0
0
Tue Sep 10 2019
Machine Learning
Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
Stochastic parameterizations account for uncertainty in the representation of sub-grid processes by sampling from the distribution of possible sub-grid forcings. The GAN stochastic parameterization is trained and evaluated on output from the Lorenz '96 model.
0
0
0