PoreML: A Data-Driven Framework for Learning Multiphase Flow in Porous Media
Abstract
Multiphase flow in porous microstructures is central to CO2 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.
Related
- Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
- Scalable machine learning framework for multiphase identification from powder X-ray diffraction
- Solute dispersion in magnetically influenced multiphase flow through a porous tube: axial transport and microrotational effects
- Formulations of elastodynamic equations for anisotropic multiphase porous piezoelectric media based on global energy conservation
- PolyGraphPy: A unified Python framework for atomistic simulation and machine learning-driven polymer design
BibTeX
@misc{wang2026poreml,
title = {{PoreML: A Data-Driven Framework for Learning Multiphase Flow in Porous Media}},
author = {Chunyang Wang and Mingrui Zhang and Yuyan Zhang and Linqi Zhu and Xin Ju and Edo Sicco Boek and Martin J. Blunt and Gege Wen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10314},
eprint = {2610.10314},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.10314},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - PoreML: A Data-Driven Framework for Learning Multiphase Flow in Porous Media
AU - Chunyang Wang
AU - Mingrui Zhang
AU - Yuyan Zhang
AU - Linqi Zhu
AU - Xin Ju
AU - Edo Sicco Boek
AU - Martin J. Blunt
AU - Gege Wen
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.10314
UR - https://arxiv.org/abs/2610.10314
AB - 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.
ER -