Machine-learning-based modeling of coarse-scale error, with application to uncertainty quantification

DOI10.1007/S10596-018-9740-XzbMath1443.86002OpenAlexW2802741293WikidataQ129836238 ScholiaQ129836238MaRDI QIDQ1787655

Louis J. Durlofsky, Sumeet Trehan

Publication date: 5 October 2018

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

Full work available at URL: https://doi.org/10.1007/s10596-018-9740-x

zbMATH Keywords

classificationreservoir simulationmachine learningupscalinguncertainty quantificationrandom forestsurrogate modelerror modeling

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Flows in porous media; filtration; seepage (76S05) Computational methods for problems pertaining to geophysics (86-08)

Related Items (6)

Multiscale uncertainty quantification with arbitrary polynomial chaos ⋮ A data-space inversion procedure for well control optimization and closed-loop reservoir management ⋮ Multifidelity framework for uncertainty quantification with multiple quantities of interest ⋮ Prediction of permeability of porous media using optimized convolutional neural networks ⋮ The use of flow diagnostics to rank model ensembles ⋮ Use of low-fidelity models with machine-learning error correction for well placement optimization

Uses Software

• MRST
• randomForest
• ElemStatLearn
• SGeMS
• MRST-AD

Cites Work

• Unnamed Item
• A multi-resolution workflow to generate high-resolution models constrained to dynamic data
• Open-source MATLAB implementation of consistent discretisations on complex grids
• Ensemble level upscaling for compositional flow simulation
• Reservoir management optimization using well-specific upscaling and control switching
• Data assimilation and uncertainty assessment for complex geological models using a new PCA-based parameterization
• Nonlinear two-point flux approximation for modeling full-tensor effects in subsurface flow simulations
• Representing spatial uncertainty using distances and kernels
• Coarse scale models of two-phase flow in heterogeneous reservoirs: Volume averaged equations and their relationship to existing upscaling techniques
• Conditional simulation of complex geological structures using multiple-point statistics
• Statistical assignment of upscaled flow functions for an ensemble of geological models
• Linearized reduced-order models for subsurface flow simulation
• Uncertainty Quantification for Subsurface Flow Problems Using Coarse-Scale Models
• The ROMES Method for Statistical Modeling of Reduced-Order-Model Error
• Constraint reduction procedures for reduced-order subsurface flow models based on POD-TPWL
• A Generalized Convection-Diffusion Model for Subgrid Transport in Porous Media
• 10.1162/153244303322753616
• An Introduction to Statistical Learning
• Assessment of Uncertainty in Reservoir Production Forecasts Using Upscaled Flow Models
• Random forests

This page was built for publication: Machine-learning-based modeling of coarse-scale error, with application to uncertainty quantification