Machine learning enhanced data assimilation framework for multiscale carbonate rock characterization

2026-01-27

arXiv.org

AI Summary

This study addresses the limitations of conventional X-ray CT imaging in characterizing multiscale carbonate rocks—specifically, the trade-off between field of view and resolution—and the prohibitive computational cost of multiphysics numerical simulations. To overcome these challenges, we propose a machine learning–enhanced data assimilation framework that, for the first time, couples a deep neural network (DNN) with the ensemble smoother with multiple data assimilation (ESMDA) algorithm. Using experimental relative permeability data as constraints, the framework efficiently inverts micropore structures and constructs high-fidelity digital rock models. The DNN acts as a surrogate for multiscale pore-network models, reducing inference time from thousands of hours to seconds while preserving accuracy. Furthermore, the method quantifies the relative permeability of microporous phases along with associated uncertainties and identifies key petrophysical contributors, offering a general and efficient solution for multiscale carbonate rock characterization.

Abstract

Carbonate reservoirs offer significant capacity for subsurface carbon storage, oil production, and underground hydrogen storage. X-ray computed tomography (X-ray CT) coupled with numerical simulations is commonly used to investigate the multiphase flow behaviors in carbonate rocks. Carbonates exhibit pore size distribution across scales, hindering the comprehensive investigation with conventional X-ray CT images. Imaging samples at both macro and micro-scales (multi-scale imaging) proved to be a viable option in this context. However, multi-scale imaging faces two key limitations: the trade-off between field of view and voxel size necessitates resource-intensive imaging, while multi-scale multi-physics numerical simulations on resulting digital models incur prohibitive computational costs. To address these challenges, we propose a machine learning-enhanced data assimilation framework that leverages experimental drainage relative permeability measurements to achieve efficient characterization of micro-scale structures, delivering a data-driven solution toward a high-fidelity multiscale digital rock modeling. We train a dense neural network (DNN) as a proxy to a multi-scale pore network simulator and couple it with an ensemble smoother with multiple data assimilation (ESMDA) algorithm. DNN-ESMDA framework simultaneously infers the CO2-brine drainage relative permeability of microporosity phases with associated uncertainty estimation, revealing the relative importance of each rock phase and guiding future characterization. Our DNN-ESMDA framework achieves a computational speedup, reducing inference time from thousands of hours to seconds compared with the usage of conventional multiscale numerical simulation. Given this computational efficiency and applicability, the machine learning-enhanced ESMDA framework presents a generalizable approach for characterizing multiscale carbonate rocks.

Problem

• multiscale imaging
• carbonate rock characterization
• computational cost
• pore structure
• data assimilation

Innovation

• machine learning
• data assimilation
• multiscale characterization
• digital rock modeling
• dense neural network