Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks

Abstract

An important problem in geostatistics is to build models of the subsurface of the Earth given physical measurements at sparse spatial locations. Typically, this is done using spatial interpolation methods or by reproducing patterns from a reference image. However, these algorithms fail to produce realistic patterns and do not exhibit the wide range of uncertainty inherent in the prediction of geology. In this paper, we show how semantic inpainting with Generative Adversarial Networks can be used to generate varied realizations of geology which honor physical measurements while matching the expected geological patterns. In contrast to other algorithms, our method scales well with the number of data points and mimics a distribution of patterns as opposed to a single pattern or image. The generated conditional samples are state of the art.

arXiv commentAdded ICML workshop info, more specific training details and more details on how images are chosen

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• Parametrization and generation of geological models with generative adversarial networks
• Context-Aware Semantic Inpainting

Cited by in corpus (12)

• Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother
• Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
• 3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels
• Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matching
• Latent Diffusion Model for Conditional Reservoir Facies Generation
• DeepFlow: History Matching in the Space of Deep Generative Models
• Generative Models as Distributions of Functions
• Deep Learning of Dynamic Subsurface Flow via Theory-guided Generative Adversarial Network
• Generating unrepresented proportions of geological facies using Generative Adversarial Networks
• Parametrization of stochastic inputs using generative adversarial networks with application in geology
• Exemplar-based synthesis of geology using kernel discrepancies and generative neural networks
• Generation of non-stationary stochastic fields using Generative Adversarial Networks