← Back to all news
arXiv Machine Learning By Chunyang Wang, Mingrui Zhang, Yuyan Zhang, Linqi Zhu, Xin Ju, Edo Sicco Boek, Martin J. Blunt, Gege Wen

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

Read the original on arXiv Machine Learning →

PoreML is an open‑source, GPU‑native framework that unifies data generation, model training, and evaluation for multiphase flow in porous media. It includes a validated lattice Boltzmann solver, a 3.3 TB dataset of 560 simulation runs with 158,546 time steps covering synthetic and micro‑CT derived structures, and a learning framework that assesses one‑step prediction and autoregressive rollouts with domain‑specific protocols. Five diverse models were evaluated, and two challenges test transfer to larger domains and to real‑material geometries.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 28

Physics-Guided Generative AI for Property-Targeted 3D Porous Media Design

arXiv:2607. 24274v1 Announce Type: cross Abstract: Inverse design of three-dimensional porous media is central to applications in filtration, catalysis, energy storage, fuel cells, thermal management, and biomedical scaffolds, but remains challenging because many distinct pore geometries can share similar porosity or permeability while small structural changes can strongly affect transport behaviour.

By Peng Wang
diffusion
More like this →
arXiv Machine Learning
Sep 24

An Adaptive Machine Learning Framework for Fluid Flow in Dual-Network Porous Media

The paper introduces a physics-informed neural network (PINN) framework for modeling fluid flow in dual‑network porous media, specifically addressing double porosity/permeability (DPP) systems. The framework embeds governing equations and boundary conditions into the loss function with adaptive weighting, employs dynamic collocation point selection, and uses shared trunk architectures to efficiently capture coupled pore‑network behavior. It is mesh‑free, accurately handles discontinuities across layered domains, and supports robust inverse analysis for parameter identification, with a systematic convergence study validating its stability and accuracy.

By V. S. Maduri, K. B. Nakshatrala
More like this →
arXiv Machine Learning
Jun 25

Surrogate models for Rock-Fluid Interaction: A Grid-Size-Invariant Approach

arXiv:2602. 22188v2 Announce Type: replace Abstract: Modelling rock-fluid interaction requires solving a set of partial differential equations (PDEs) to predict the flow behaviour and the reactions of the fluid with the rock on the interfaces.

By Nathalie C. Pinheiro, Donghu Guo, Hannah P. Menke, Aniket C. Joshi, Claire E. Heaney, Ahmed H. ElSheikh, Christopher C. Pain
More like this →