A review of proxy modeling highlighting applications for reservoir engineering

P Bahrami, F Sahari Moghaddam, LA James - Energies, 2022 - mdpi.com
Numerical models can be used for many purposes in oil and gas engineering, such as
production optimization and forecasting, uncertainty analysis, history matching, and risk …

Deep autoregressive neural networks for high‐dimensional inverse problems in groundwater contaminant source identification

S Mo, N Zabaras, X Shi, J Wu - Water Resources Research, 2019 - Wiley Online Library
Identification of a groundwater contaminant source simultaneously with the hydraulic
conductivity in highly heterogeneous media often results in a high‐dimensional inverse …

Fundamental controls on fluid flow in carbonates: current workflows to emerging technologies

SM Agar, S Geiger - Geological Society, London, Special …, 2015 - lyellcollection.org
The introduction reviews topics relevant to the fundamental controls on fluid flow in
carbonate reservoirs and to the prediction of reservoir performance. The review provides …

Probabilistic model updating via variational Bayesian inference and adaptive Gaussian process modeling

P Ni, J Li, H Hao, Q Han, X Du - Computer Methods in Applied Mechanics …, 2021 - Elsevier
The estimation of the posterior probability distribution of unknown parameters remains a
challenging issue for model updating with uncertainties. Most current studies are based on …

Predicting field production rates for waterflooding using a machine learning-based proxy model

Z Zhong, AY Sun, Y Wang, B Ren - Journal of Petroleum Science and …, 2020 - Elsevier
Waterflooding, during which water is injected in the reservoir to increase pressure and
therefore boost oil production, is extensively used as a secondary oil recovery technology …

Deep residual U-net convolution neural networks with autoregressive strategy for fluid flow predictions in large-scale geosystems

Z Jiang, P Tahmasebi, Z Mao - Advances in Water Resources, 2021 - Elsevier
The inherent complexity of the fluid flow in subsurface systems brings potential inevitable
uncertainty in their characterization. Computationally intensive high-dimensional inversion …

Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non‐Gaussian hydraulic conductivities

S Mo, N Zabaras, X Shi, J Wu - Water Resources Research, 2020 - Wiley Online Library
Inverse modeling for the estimation of non‐Gaussian hydraulic conductivity fields in
subsurface flow and solute transport models remains a challenging problem. This is mainly …

Reduced-order modeling of subsurface multi-phase flow models using deep residual recurrent neural networks

JN Kani, AH Elsheikh - Transport in Porous Media, 2019 - Springer
We present a reduced-order modeling technique for subsurface multi-phase flow problems
building on the recently introduced deep residual recurrent neural network (DR …

A novel hybrid recurrent convolutional network for surrogate modeling of history matching and uncertainty quantification

X Ma, K Zhang, J Zhang, Y Wang, L Zhang, P Liu… - Journal of Petroleum …, 2022 - Elsevier
Automatic history matching (AHM) has been widely studied in petroleum engineering due to
it can provide reliable numerical models for reservoir development and management …

Probabilistic-learning-based stochastic surrogate model from small incomplete datasets for nonlinear dynamical systems

C Soize, R Ghanem - Computer Methods in Applied Mechanics and …, 2024 - Elsevier
We consider a high-dimensional nonlinear computational model of a dynamical system,
parameterized by a vector-valued control parameter, in the presence of uncertainties …