Deep learning surrogate for predicting hydraulic conductivity tensors from stochastic discrete fracture-matrix models

DOI10.1007/S10596-024-10324-8MaRDI QIDQ6662489FDOQ6662489

Authors: Martin Špetlík, Jan Březina, Eric Laloy 

Publication date: 14 January 2025

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

Recommendations

• Surrogate permeability modelling of low-permeable rocks using convolutional neural networks
• A Bayesian multiscale deep learning framework for flows in random media
• A gradient-based deep neural network model for simulating multiphase flow in porous media
• Data-driven uncertainty quantification for predictive flow and transport modeling using support vector machines
• Prediction of numerical homogenization using deep learning for the Richards equation

zbMATH Keywords

numerical homogenizationdeep learning surrogate2D DFM modelsequivalent hydraulic conductivity tensor

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Theories of fracture and damage (74A45) Finite element methods applied to problems in fluid mechanics (76M10) Flows in porous media; filtration; seepage (76S05)

Cites Work

• Deep learning
• Flow and transport in porous media and fractured rock. From classical methods to modern approaches.
• An efficient multi-point flux approximation method for discrete fracture-matrix simulations
• On Simulations of Discrete Fracture Network Flows with an Optimization-Based Extended Finite Element Method
• Upscaling: a review
• Machine learning for accelerating macroscopic parameters prediction for poroelasticity problem in stochastic media
• Analysis of Model Error for a Continuum-Fracture Model of Porous Media Flow
• Upscaling of two-phase discrete fracture simulations using a convolutional neural network
• Rapid estimation of permeability from digital rock using 3D convolutional neural network
• Prediction of numerical homogenization using deep learning for the Richards equation
• Effective permeability of fractured porous media with fracture density near the percolation threshold
• Deep-learning-based upscaling method for geologic models via theory-guided convolutional neural network

Cited In (1)

• Solute transport prediction in heterogeneous porous media using random walks and machine learning

This page was built for publication: Deep learning surrogate for predicting hydraulic conductivity tensors from stochastic discrete fracture-matrix models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6662489)