A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

DOI10.1016/J.JCP.2020.109456zbMath1436.76058arXiv1908.05823OpenAlexW3016309349MaRDI QIDQ776737

Meng Tang, Louis J. Durlofsky, Yi-min Liu

Publication date: 13 July 2020

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.05823

zbMATH Keywords

reservoir simulationhistory matchingsurrogate modeldeep learninginverse modeling

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Liquid-liquid two component flows (76T06)

Related Items (18)

Accelerated reactive transport simulations in heterogeneous porous media using Reaktoro and Firedrake ⋮ Mesh-Conv: convolution operator with mesh resolution independence for flow field modeling ⋮ Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems ⋮ Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network ⋮ A gradient-based deep neural network model for simulating multiphase flow in porous media ⋮ Transformers for modeling physical systems ⋮ Convolutional -- recurrent neural network proxy for robust optimization and closed-loop reservoir management ⋮ Deep reinforcement learning for optimal well control in subsurface systems with uncertain geology ⋮ Solute transport prediction in heterogeneous porous media using random walks and machine learning ⋮ Physics-informed machine learning method with space-time Karhunen-Loève expansions for forward and inverse partial differential equations ⋮ Efficient deep data assimilation with sparse observations and time-varying sensors ⋮ Theory-guided auto-encoder for surrogate construction and inverse modeling ⋮ Efficient uncertainty quantification for dynamic subsurface flow with surrogate by theory-guided neural network ⋮ Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow ⋮ Variational data assimilation and its decoupled iterative numerical algorithms for Stokes-Darcy model ⋮ An encoder-decoder deep surrogate for reverse time migration in seismic imaging under uncertainty ⋮ A nonintrusive hybrid neural-physics modeling of incomplete dynamical systems: Lorenz equations ⋮ Use of multifidelity training data and transfer learning for efficient construction of subsurface flow surrogate models

Uses Software

• SGeMS
• Adam
• GNMT
• CycleGAN
• pix2pix
• BERT
• U-Net

Cites Work

• Unnamed Item
• Unnamed Item
• Data assimilation and uncertainty assessment for complex geological models using a new PCA-based parameterization
• Gaussian processes for history-matching: application to an unconventional gas reservoir
• Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
• Non-intrusive subdomain POD-TPWL for reservoir history matching
• A deep-learning-based geological parameterization for history matching complex models
• Reduced-order optimal control of water flooding using proper orthogonal decomposition
• Development and application of reduced-order modeling procedures for subsurface flow simulation
• Mesh Adaptive Direct Search Algorithms for Constrained Optimization

This page was built for publication: A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems