Discovering state-parameter mappings in subsurface models using generative adversarial networks

Abstract

A fundamental problem in geophysical modeling is related to the identification and approximation of causal structures among physical processes. However, resolving the bidirectional mappings between physical parameters and model state variables (i.e., solving the forward and inverse problems) is challenging, especially when parameter dimensionality is high. Deep learning has opened a new door toward knowledge representation and complex pattern identification. In particular, the recently introduced generative adversarial networks (GANs) hold strong promises in learning cross-domain mappings for image translation. This study presents a state-parameter identification GAN (SPID-GAN) for simultaneously learning bidirectional mappings between a high-dimensional parameter space and the corresponding model state space. SPID-GAN is demonstrated using a series of representative problems from subsurface flow modeling. Results show that SPID-GAN achieves satisfactory performance in identifying the bidirectional state-parameter mappings, providing a new deep-learning-based, knowledge representation paradigm for a wide array of complex geophysical problems.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Instance Normalization: The Missing Ingredient for Fast Stylization
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Land Use Classification in Remote Sensing Images by Convolutional Neural Networks
• Estimating ground-level PM2.5 by fusing satellite and station observations: A geo-intelligent deep learning approach
• Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets
• Prolongation of SMAP to Spatio-temporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
• Coupled Generative Adversarial Networks

Cited by in corpus (8)

• Deep Learning of Subsurface Flow via Theory-guided Neural Network
• Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identification
• Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities
• Using Deep Learning to Improve Ensemble Smoother: Applications to Subsurface Characterization
• Attention U-Net as a surrogate model for groundwater prediction
• Deep Learning to Estimate Permeability using Geophysical Data
• Physics-informed semantic inpainting: Application to geostatistical modeling
• Generation of non-stationary stochastic fields using Generative Adversarial Networks