Uncertainty quantification in Bayesian inverse problems with model and data dimension reduction

D Grana, L Passos de Figueiredo, L Azevedo - Geophysics, 2019 - library.seg.org
The prediction of rock properties in the subsurface from geophysical data generally requires
the solution of a mathematical inverse problem. Because of the large size of geophysical …

Robust optimization of geoenergy production using data-driven deep recurrent auto-encoder and fully-connected neural network proxy

C Xiao, S Zhang, Y Hu, X Gu, X Ma, T Zhou… - Expert Systems with …, 2024 - Elsevier
Robust and efficient optimization of post-history well production schedule under history-
matched geomodel known as closed-loop production management is crucial to achieve …

Machine-learning-based well production prediction under geological and hydraulic fracture parameters uncertainty for unconventional shale gas reservoirs

C Xiao, G Wang, Y Zhang, Y Deng - Journal of Natural Gas Science and …, 2022 - Elsevier
Shale gas production prediction under history-matching-based geomodel is crucial to
achieve reliable assessment and economic management of unconventional shale …

History matching for geological carbon storage using data-space inversion with spatio-temporal data parameterization

S Jiang, LJ Durlofsky - International Journal of Greenhouse Gas Control, 2024 - Elsevier
History matching based on monitoring data will enable uncertainty reduction, and thus
improved aquifer management, in industrial-scale carbon storage operations. In traditional …

Efficient surrogate modeling based on improved vision transformer neural network for history matching

D Zhang, H Li - SPE Journal, 2023 - onepetro.org
For history-matching problems, simulations of reservoir models usually involve high
computational costs. Surrogate modeling based on deep learning has proved to be an …

A data-space inversion procedure for well control optimization and closed-loop reservoir management

S Jiang, W Sun, LJ Durlofsky - Computational Geosciences, 2020 - Springer
Data-space inversion (DSI) methods provide posterior (history-matched) predictions for
quantities of interest, along with uncertainty quantification, without constructing posterior …

[HTML][HTML] Data space inversion for efficient uncertainty quantification using an integrated surface and sub-surface hydrologic model

H Delottier, J Doherty, P Brunner - Geoscientific Model …, 2023 - gmd.copernicus.org
It is incumbent on decision-support hydrological modelling to make predictions of uncertain
quantities in a decision-support context. In implementing decision-support modelling, data …

Deep-learning-generalized data-space inversion and uncertainty quantification framework for accelerating geological CO2 plume migration monitoring

C Xiao, S Zhang, X Ma, T Zhou, T Hou… - Geoenergy Science and …, 2023 - Elsevier
Efficient coupling of high-fidelity simulation models and history-monitored data to predict
future migration behavior of CO 2 plume is crucial for leakage risk management and …

[HTML][HTML] An improved data space inversion method to predict reservoir state fields via observed production data

D Liu, X Rao, H Zhao, YF Xu, RX Gong - Petroleum Science, 2021 - Elsevier
A data-space inversion (DSI) method has been recently proposed and successfully applied
to the history matching and production prediction of reservoirs. Based on Bayesian theory …

Data-space inversion using a recurrent autoencoder for time-series parameterization

S Jiang, LJ Durlofsky - Computational Geosciences, 2021 - Springer
Data-space inversion (DSI) and related procedures represent a family of methods applicable
for data assimilation in subsurface flow settings. These methods differ from usual model …