Robust Optimal Well Control using an Adaptive Multigrid Reinforcement Learning Framework

Article Automation & Control Systems

Stochastic optimal well control in subsurface reservoirs using reinforcement learning

Atish Dixit et al.

Summary: This study introduces a model-free reinforcement learning framework to address the robust optimal well control problem, utilizing deep RL algorithms to learn optimal action policies based on saturation, pressure values, and valve openings. By introducing a domain randomization scheme to handle model parameter uncertainties, numerical results are presented on two subsurface flow test cases with distinct uncertainty distributions, demonstrating the robustness of the proposed RL approach when applied to unseen samples.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2022)

Add to Collection

Article Mathematics, Interdisciplinary Applications

Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flow

Yusuf Nasir et al.

Summary: The research introduces a deep-reinforcement-learning-based artificial intelligence agent for optimizing oil and gas field development plans, utilizing a convolutional neural network to map the reservoir model state, constraints, and economic conditions to optimal decisions. The agent is trained through a feedback loop process with millions of flow simulations, providing instant optimized plans for new scenarios within a defined range of applicability.

FRONTIERS IN APPLIED MATHEMATICS AND STATISTICS (2021)

Add to Collection

Article Automation & Control Systems