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

TL;DR

This paper presents a deep learning-based framework called the multimodal latent dynamic model combined with reinforcement learning to optimize geological carbon storage operations efficiently, significantly reducing computational costs and improving decision quality.

Contribution

The study introduces the MLD model supporting diverse data inputs and integrates it with deep reinforcement learning, enabling faster and more effective GCS optimization compared to traditional simulation-based methods.

Findings

Achieves over 60% reduction in computational resources.

Outperforms traditional methods in maximizing net present value.

Demonstrates strong generalization to new scenarios.

Abstract

Maximizing storage performance in geological carbon storage (GCS) is crucial for commercial deployment, but traditional optimization demands resource-intensive simulations, posing computational challenges. This study introduces the multimodal latent dynamic (MLD) model, a deep learning framework for fast flow prediction and well control optimization in GCS. The MLD model includes a representation module for compressed latent representations, a transition module for system state evolution, and a prediction module for flow responses. A novel training strategy combining regression loss and joint-embedding consistency loss enhances temporal consistency and multi-step prediction accuracy. Unlike existing models, the MLD supports diverse input modalities, allowing comprehensive data interactions. The MLD model, resembling a Markov decision process (MDP), can train deep reinforcement learning agents, specifically using the soft actor-critic (SAC) algorithm, to maximize net present value (NPV) through continuous interactions. The approach outperforms traditional methods, achieving the highest NPV while reducing computational resources by over 60%. It also demonstrates strong generalization performance, providing improved decisions for new scenarios based on knowledge from previous ones.