A deep-learning-based geological parameterization for history matching complex models

DOI10.1007/s11004-019-09794-9zbMath1421.86004arXiv1807.02716OpenAlexW2963162215WikidataQ128173315 ScholiaQ128173315MaRDI QIDQ2323494

Louis J. Durlofsky, Wenyue Sun, Yi-min Liu

Publication date: 3 September 2019

Published in: Mathematical Geosciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.02716

zbMATH Keywords

principal component analysishistory matchingdeep learninggeological parameterization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Inverse problems in geophysics (86A22) General questions in geophysics (86A04)

Related Items (11)

Extended dynamic mode decomposition for inhomogeneous problems ⋮ Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems ⋮ Application of Bayesian generative adversarial networks to geological facies modeling ⋮ Bridging deep convolutional autoencoders and ensemble smoothers for improved estimation of channelized reservoirs ⋮ Deep reinforcement learning for optimal well control in subsurface systems with uncertain geology ⋮ Data-space inversion using a recurrent autoencoder for time-series parameterization ⋮ Recent developments combining ensemble smoother and deep generative networks for facies history matching ⋮ Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow ⋮ Objective-sensitive principal component analysis for high-dimensional inverse problems ⋮ A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems ⋮ An intelligent multi-fidelity surrogate-assisted multi-objective reservoir production optimization method based on transfer stacking

Uses Software

• SGeMS
• PyTorch
• ImageNet
• Adam
• GitHub
• Wasserstein GAN

Cites Work

• Unnamed Item
• Data assimilation and uncertainty assessment for complex geological models using a new PCA-based parameterization
• Regularized kernel PCA for the efficient parameterization of complex geological models
• Compressed history matching: Exploiting transform-domain sparsity for regularization of nonlinear dynamic data integration problems
• High-order statistics of spatial random fields: Exploring spatial cumulants for modeling complex non-Gaussian and non-linear phenomena
• Filter-based classification of training image patterns for spatial simulation
• A new differentiable parameterization based on principal component analysis for the low-dimensional representation of complex geological models
• Conditioning truncated pluri-Gaussian models to facies observations in ensemble-Kalman-based data assimilation
• Kernel principal component analysis for efficient, differentiable parametrization of multipoint geostatistics
• Porous structure reconstruction using convolutional neural networks
• Investigation on principal component analysis parameterizations for history matching channelized facies models with ensemble-based data assimilation
• Conditional simulation of complex geological structures using multiple-point statistics
• Parametric generation of conditional geological realizations using generative neural networks
• Stochastic seismic waveform inversion using generative adversarial networks as a geological prior
• Efficient real-time reservoir management using adjoint-based optimal control and model updating
• History matching of facies distribution with the EnKF and level set parameterization

This page was built for publication: A deep-learning-based geological parameterization for history matching complex models