Brownian Bridge Augmented Surrogate Simulation and Injection Planning for Geological CO$_2$ Storage

2025-05-21

AI Summary

Geological CO₂ sequestration (GCS) demands efficient, dynamic injection control under stringent safety constraints; however, existing numerical and surrogate-based optimization approaches struggle to simultaneously ensure state smoothness, goal-directedness, and computational timeliness. This paper proposes a Brownian bridge–enhanced surrogate simulation and goal-oriented injection planning framework. We introduce the Brownian bridge as a novel smoothness regularizer for latent state trajectories and as a conditional planner that enforces target-state constraints at specified time horizons. A deep Brownian bridge representation is developed via contrastive learning coupled with reconstruction loss. Furthermore, we establish a Brownian bridge–driven surrogate model regularization mechanism and a utility-conditioned trajectory planning strategy. Evaluated on multi-source GCS datasets, our method significantly improves simulation fidelity and planning efficacy while maintaining real-time performance and low computational overhead—enabling industrial-scale adaptive injection control.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Geological CO2 storage (GCS) involves injecting captured CO2 into deep subsurface formations to support climate goals. The effective management of GCS relies on adaptive injection planning to dynamically control injection rates and well pressures to balance both storage safety and efficiency. Prior literature, including numerical optimization methods and surrogate-optimization methods, is limited by real-world GCS requirements of smooth state transitions and goal-directed planning within limited time. To address these limitations, we propose a Brownian Bridge-augmented framework for surrogate simulation and injection planning in GCS and develop two insights: (i) Brownian bridge as a smooth state regularizer for better surrogate simulation; (ii) Brownian bridge as goal-time-conditioned planning guidance for improved injection planning. Our method has three stages: (i) learning deep Brownian bridge representations with contrastive and reconstructive losses from historical reservoir and utility trajectories, (ii) incorporating Brownian bridge-based next state interpolation for simulator regularization, and (iii) guiding injection planning with Brownian utility-conditioned trajectories to generate high-quality injection plans. Experimental results across multiple datasets collected from diverse GCS settings demonstrate that our framework consistently improves simulation fidelity and planning effectiveness while maintaining low computational overhead.

Problem

• Enhancing CO2 storage safety and efficiency via adaptive injection planning
• Overcoming limitations of smooth state transitions in GCS optimization
• Improving simulation fidelity with Brownian Bridge-augmented surrogate models

Innovation

• Brownian Bridge-augmented surrogate simulation framework
• Deep Brownian bridge representations with contrastive losses
• Goal-time-conditioned Brownian bridge planning guidance