Learning Pore-scale Multiphase Flow from 4D Velocimetry

2026-03-12

AI Summary

Accurately characterizing pore-scale multiphase flow dynamics in real three-dimensional porous media remains challenging, hindering applications such as carbon sequestration and underground hydrogen storage. This work proposes a multimodal learning framework that integrates graph neural networks—simulating Lagrangian tracer particle motion—with a 3D U-Net for interface evolution prediction, using imaged pore geometry as boundary constraints. The two components are iteratively coupled to jointly update velocity fields and fluid interfaces. This approach achieves the first end-to-end digital twin of multiphase flow grounded in experimental four-dimensional micro-velocity data, efficiently capturing transient, non-local phenomena like Haines jumps. Under capillary-dominated conditions (Ca ≈ 10⁻⁶), it accelerates simulations that traditionally require hours to days down to second-scale inference, offering a high-fidelity, high-efficiency digital experimentation platform for investigating the effects of injection protocols and pore structure.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Multiphase flow in porous media underpins subsurface energy and environmental technologies, including geological CO$_2$ storage and underground hydrogen storage, yet pore-scale dynamics in realistic three-dimensional materials remain difficult to characterize and predict. Here we introduce a multimodal learning framework that infers multiphase pore-scale flow directly from time-resolved four-dimensional (4D) micro-velocimetry measurements. The model couples a graph network simulator for Lagrangian tracer-particle motion with a 3D U-Net for voxelized interface evolution. The imaged pore geometry serves as a boundary constraint to the flow velocity and the multiphase interface predictions, which are coupled and updated iteratively at each time step. Trained autoregressively on experimental sequences in capillary-dominated conditions ($Ca\approx10^{-6}$), the learned surrogate captures transient, nonlocal flow perturbations and abrupt interface rearrangements (Haines jumps) over rollouts spanning seconds of physical time, while reducing hour-to-day--scale direct numerical simulations to seconds of inference. By providing rapid, experimentally informed predictions, the framework opens a route to ''digital experiments'' to replicate pore-scale physics observed in multiphase flow experiments, offering an efficient tool for exploring injection conditions and pore-geometry effects relevant to subsurface carbon and hydrogen storage.

Problem

• multiphase flow
• porous media
• pore-scale dynamics
• 4D velocimetry
• subsurface storage

Innovation

• multiphase flow
• 4D micro-velocimetry
• graph neural network
• 3D U-Net
• digital experiments