Deep Learning-Accelerated Surrogate Optimization for High-Dimensional Well Control in Stress-Sensitive Reservoirs

TL;DR

This paper introduces a deep learning surrogate model for high-dimensional well control optimization in stress-sensitive reservoirs, significantly reducing computational costs while maintaining accuracy.

Contribution

It presents a novel problem-informed sampling strategy and neural network proxy for efficient, scalable optimization in complex reservoir management scenarios.

Findings

Surrogate achieves 2-5% accuracy compared to full-physics solutions.

Reduces computational cost by up to three orders of magnitude.

Effective for high-dimensional, PDE-constrained optimization problems.

Abstract

Production optimization in stress-sensitive unconventional reservoirs is governed by a nonlinear trade-off between pressure-driven flow and stress-induced degradation of fracture conductivity and matrix permeability. While higher drawdown improves short-term production, it accelerates permeability loss and reduces long-term recovery. Identifying optimal, time-varying control strategies requires repeated evaluations of fully coupled flow-geomechanics simulators, making conventional optimization computationally expensive. We propose a deep learning-based surrogate optimization framework for high-dimensional well control. Unlike prior approaches that rely on predefined control parameterizations or generic sampling, our method treats well control as a continuous, high-dimensional problem and introduces a problem-informed sampling strategy that aligns training data with trajectories encountered during optimization. A neural network proxy is trained to approximate the mapping between bottomhole pressure trajectories and cumulative production using data from a coupled flow-geomechanics model. The proxy is embedded within a constrained optimization workflow, enabling rapid evaluation of control strategies. Across multiple initializations, the surrogate achieves agreement with full-physics solutions within 2-5 percent, while reducing computational cost by up to three orders of magnitude. Discrepancies are mainly associated with trajectories near the boundary of the training distribution and local optimization effects. This framework shows that combining surrogate modeling with problem-informed sampling enables scalable and reliable optimization for high-dimensional, simulator-based problems, with broader applicability to PDE-constrained systems.