Deep Learning Framework for History Matching CO2 Storage with 4D Seismic and Monitoring Well Data

2024-08-02

arXiv.org

AI Summary

High uncertainty in reservoir parameters severely limits the accuracy of long-term CO₂ containment prediction in geological carbon storage. Method: This study proposes a coupled deep surrogate modeling and hierarchical MCMC history-matching framework: (i) a decoupled dual-branch CNN/MLP surrogate model, separately trained to accurately emulate time-lapse 4D seismic saturation responses and monitoring-well data; and (ii) a hierarchical MCMC scheme integrating multi-source observations to enable early dynamic calibration and quantify the individual uncertainty-reduction contribution of each data type. Results: In synthetic case studies, joint assimilation of both data types reduces uncertainty in key reservoir parameters by over 60% and confines CO₂ plume location prediction error within 50 m—substantially improving early-stage risk assessment reliability. This work introduces the first decoupled surrogate modeling paradigm tailored to well-seismic multi-scale observations, establishing a new data-driven paradigm for dynamic storage management.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Geological carbon storage entails the injection of megatonnes of supercritical CO2 into subsurface formations. The properties of these formations are usually highly uncertain, which makes design and optimization of large-scale storage operations challenging. In this paper we introduce a history matching strategy that enables the calibration of formation properties based on early-time observations. Early-time assessments are essential to assure the operation is performing as planned. Our framework involves two fit-for-purpose deep learning surrogate models that provide predictions for in-situ monitoring well data and interpreted time-lapse (4D) seismic saturation data. These two types of data are at very different scales of resolution, so it is appropriate to construct separate, specialized deep learning networks for their prediction. This approach results in a workflow that is more straightforward to design and more efficient to train than a single surrogate that provides global high-fidelity predictions. The deep learning models are integrated into a hierarchical Markov chain Monte Carlo (MCMC) history matching procedure. History matching is performed on a synthetic case with and without 4D seismic data, which allows us to quantify the impact of 4D seismic on uncertainty reduction. The use of both data types is shown to provide substantial uncertainty reduction in key geomodel parameters and to enable accurate predictions of CO2 plume dynamics. The overall history matching framework developed in this study represents an efficient way to integrate multiple data types and to assess the impact of each on uncertainty reduction and performance predictions.

Problem

• Geological Carbon Storage
• Subsurface Uncertainty Reduction
• CO2 Storage Planning

Innovation

• Deep Learning
• Markov Chain Monte Carlo
• Geological Carbon Storage