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

TL;DR

This paper introduces a deep reinforcement learning agent that rapidly generates optimized oilfield development plans based on reservoir data, significantly reducing computational effort compared to traditional methods.

Contribution

The study develops a convolutional neural network-based reinforcement learning framework capable of generalizing field development decisions across various reservoir scenarios.

Findings

The AI agent provides instant optimized development plans after training.

Training involved millions of flow simulations with diverse reservoir parameters.

The approach outperforms traditional optimization algorithms in speed and adaptability.

Abstract

We present a deep reinforcement learning-based artificial intelligence agent that could provide optimized development plans given a basic description of the reservoir and rock/fluid properties with minimal computational cost. This artificial intelligence agent, comprising of a convolutional neural network, provides a mapping from a given state of the reservoir model, constraints, and economic condition to the optimal decision (drill/do not drill and well location) to be taken in the next stage of the defined sequential field development planning process. The state of the reservoir model is defined using parameters that appear in the governing equations of the two-phase flow. A feedback loop training process referred to as deep reinforcement learning is used to train an artificial intelligence agent with such a capability. The training entails millions of flow simulations with varying reservoir model descriptions (structural, rock and fluid properties), operational constraints, and economic conditions. The parameters that define the reservoir model, operational constraints, and economic conditions are randomly sampled from a defined range of applicability. Several algorithmic treatments are introduced to enhance the training of the artificial intelligence agent. After appropriate training, the artificial intelligence agent provides an optimized field development plan instantly for new scenarios within the defined range of applicability. This approach has advantages over traditional optimization algorithms (e.g., particle swarm optimization, genetic algorithm) that are generally used to find a solution for a specific field development scenario and typically not generalizable to different scenarios.