PoreML: A Data-Driven Framework for Learning Multiphase Flow in Porous Media

2026-10-07

AI Summary

This study addresses the challenges of data scarcity and the absence of standardized evaluation criteria in predicting multiphase flow through porous media by proposing a unified, open-source framework. Methodologically, a GPU-native lattice Boltzmann method is employed to generate a 3.3 TB high-quality spatiotemporal dataset, which is integrated with deep learning training and autoregressive prediction pipelines. Furthermore, a domain-specific, physics-consistent evaluation protocol is designed. Experiments systematically validate the performance of five representative models. By providing an end-to-end workflow encompassing data generation, model training, and scientific evaluation, this project facilitates intelligent prediction of multiphase flow and effectively advances standardized research and collaborative community development in the field.

Abstract

Multiphase flow in porous microstructures is central to CO$_2$ storage, fuel-cell operation, and flip-chip packaging. Predicting these flows remains challenging because wettability and complex pore geometry govern the nonlinear evolution of fluid interfaces. Machine learning holds substantial promise for advancing the field, but progress is constrained by scarce time-resolved 3D datasets and a lack of a unified workflow for training and evaluating models. To fill this critical gap, we introduce PoreML, an open-source framework unifying data generation, model training, and evaluation grounded in pore-scale physics. The framework comprises three core components. (a) A modern GPU-native lattice Boltzmann solver, validated against analytical solutions and published experiments, enables reproducible data generation. (b) A 3.3 TB dataset contains 560 simulation runs and 158,546 stored time steps across four application-driven scenarios. These trajectories span synthetic structures and geometries derived from micro-CT scans of real materials, covering diverse wetting conditions and viscosity ratios. (c) A unified learning framework evaluates one-step prediction and autoregressive rollouts. Its domain-specific evaluation protocols assess predictive accuracy and physical consistency. We evaluate five models of diverse architecture under these protocols. Two complementary challenges assess transfer to larger domains and from synthetic to micro-CT-derived structures. PoreML provides a shared foundation for machine-learning research on multiphase flow in porous media, with the aim of empowering the community to develop reliable predictive models and advance the field.

Problem

• multiphase flow
• porous media
• machine learning
• 3D datasets
• pore-scale physics

Innovation

• Multiphase Flow
• Porous Media
• Lattice Boltzmann Method
• Machine Learning
• Data-Driven Framework