Integrating Score-Based Diffusion Models with Machine Learning-Enhanced Localization for Advanced Data Assimilation in Geological Carbon Storage

TL;DR

This paper presents a novel framework combining score-based diffusion models with machine learning-enhanced localization to improve data assimilation and uncertainty quantification in geological carbon storage, especially in channelized reservoirs.

Contribution

It introduces an integrated approach that leverages diffusion models and machine learning for better covariance estimation in GCS data assimilation.

Findings

ML-based localization maintains more ensemble variance.

Achieves comparable data-matching quality with improved uncertainty quantification.

Framework applicable to real GCS scenarios for risk assessment.

Abstract

Accurate characterization of subsurface heterogeneity is important for the safe and effective implementation of geological carbon storage (GCS) projects. This paper explores how machine learning methods can enhance data assimilation for GCS with a framework that integrates score-based diffusion models with machine learning-enhanced localization in channelized reservoirs during CO$_2$ injection. We employ a machine learning-enhanced localization framework that uses large ensembles ($N_s = 5000$) with permeabilities generated by the diffusion model and states computed by simple ML algorithms to improve covariance estimation for the Ensemble Smoother with Multiple Data Assimilation (ESMDA). We apply ML algorithms to a prior ensemble of channelized permeability fields, generated with the geostatistical model FLUVSIM. Our approach is applied on a CO$_2$ injection scenario simulated using the Delft Advanced Research Terra Simulator (DARTS). Our ML-based localization maintains significantly more ensemble variance than when localization is not applied, while achieving comparable data-matching quality. This framework has practical implications for GCS projects, helping improve the reliability of uncertainty quantification for risk assessment.