A review on optimization algorithms and surrogate models for reservoir automatic history matching

Y Zhao, R Luo, L Li, R Zhang, D Zhang, T Zhang… - Geoenergy Science and …, 2024 - Elsevier
Reservoir history matching represents a crucial stage in the reservoir development process
and purposes to match model predictions with various observed field data, including …

A dual-porosity flow-net model for simulating water-flooding in low-permeability fractured reservoirs

X Yan, GY Qin, LM Zhang, K Zhang, YF Yang… - Geoenergy Science and …, 2024 - Elsevier
The physics-based data-driven flow-network models with high computational efficiency have
received great attention as the promising surrogate models for reservoir numerical …

Extension of fourier neural operator from three-dimensional (x, y, t) to four-dimensional (x, y, z, t) subsurface flow simulation

J Liu, H Pan, W Sun, H **g, B Gong - Mathematical Geosciences, 2024 - Springer
Numerical simulation of subsurface flow in porous media is crucial for various geoscience
applications. However, conducting numerical simulations for such problems, particularly in …

A Physics-Informed Spatial-Temporal Neural Network for Reservoir Simulation and Uncertainty Quantification

J Bi, J Li, K Wu, Z Chen, S Chen, L Jiang, D Feng… - SPE J., 2024 - onepetro.org
Surrogate models play a vital role in reducing computational complexity and time burden for
reservoir simulations. However, traditional surrogate models suffer from limitations in …

A maximum entropy deep reinforcement learning method for sequential well placement optimization using multi-discrete action spaces

K Zhang, Z Sun, L Zhang, G **n, Z Wang… - Geoenergy Science and …, 2024 - Elsevier
Well placement optimization is a crucial method to solve the planar conflicts in reservoir
development, mainly to determine the optimal well locations and drilling sequence to …

Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning

Z Wang, Y Chen, G Chen, D Zhang - Geoenergy Science and Engineering, 2025 - Elsevier
Identifying the time-varying control schemes that maximize storage performance is critical to
the commercial deployment of geological carbon storage (GCS) projects. However, the …

Transfer Learning in Subsurface Flow Surrogate Model with Physics-Guided Neural Network

HB Cheng, JH Qiao, YC Wei, SC Li, P Zeng… - SPE Annual Technical …, 2024 - onepetro.org
It is a great challenge for reservoir engineers to accurately and quickly model the subsurface
flow surrogate for oil and gas reservoirs. The traditional numerical simulation methods are …

Deep Learning Surrogate Model Based on Residual Bottleneck Block for History Matching

T Gao, J Zang, L Zhang, X Wang… - … Conference on New …, 2024 - ieeexplore.ieee.org
History matching is a key link to predict the development performance of oil field by using
reservoir numerical simulation, which directly determines the reliability of numerical …

ConvNeXt Block-Based Deep Learning Surrogate Model for Polymer-Flooding Reservoir Simulation

X Liu, T Gaol, L Li, C **ao, X Lv, B Yuan… - … Conference on New …, 2023 - ieeexplore.ieee.org
Surrogate modeling has emerged as a crucial strategy for time and cost savings in reservoir
development. However, the majority of research on surrogate modeling has been …

Multimodal Surrogate-Enhanced Deep Reinforcement Learning for Policy Optimization of Subsurface Energy Systems

Z Wang, Y Chen, D Zhang, G Chen - Available at SSRN 4552911 - papers.ssrn.com
Efficient optimization of subsurface energy production and carbon storage is crucial for
environmental, energy, and economic security. However, it is confronted with huge …