Gaussian mixture model fitting method for uncertainty quantification by conditioning to production data

DOI10.1007/S10596-019-9823-3zbMath1434.86038OpenAlexW2954528614WikidataQ127751206 ScholiaQ127751206MaRDI QIDQ2185981

Jeroen C. Vink, Hao Jiang, Joel J. Ita, Yaakoub El Khamra, Chaohui Chen, Guohua Gao

Publication date: 8 June 2020

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

Full work available at URL: https://doi.org/10.1007/s10596-019-9823-3

zbMATH Keywords

Bayesian inferenceGaussian mixture modeluncertainty quantificationhistory matchingdistributed Gauss-Newton optimization method

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Bayesian inference (62F15) Inverse problems in geophysics (86A22) Geostatistics (86A32)

Related Items (4)

Conditioning generative adversarial networks on nonlinear data for subsurface flow model calibration and uncertainty quantification ⋮ A machine-learning-accelerated distributed LBFGS method for field development optimization: algorithm, validation, and applications ⋮ A residual-driven adaptive Gaussian mixture approximation for Bayesian inverse problems ⋮ Distributed quasi-Newton derivative-free optimization method for optimization problems with multiple local optima

Uses Software

• Unnamed Item

Cites Work

• Markov chains and stochastic stability
• Iterative Bayesian inversion with Gaussian mixtures: finite sample implementation and large sample asymptotics
• Levenberg-Marquardt forms of the iterative ensemble smoother for efficient history matching and uncertainty quantification
• Calibration of imperfect models to biased observations
• Distributed Gauss-Newton optimization method for history matching problems with multiple best matches
• Bayesian Gaussian mixture linear inversion for geophysical inverse problems
• Recent progress on reservoir history matching: a review
• Finite Mixture Modeling with Mixture Outcomes Using the EM Algorithm
• Inverse Problem Theory and Methods for Model Parameter Estimation
• Metropolized Randomized Maximum Likelihood for Improved Sampling from Multimodal Distributions
• Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity
• Data Assimilation

This page was built for publication: Gaussian mixture model fitting method for uncertainty quantification by conditioning to production data