Multiphase flow in porous media involves a variety of natural and industrial processes.
However, the microscopic description of multiphase flow is challenging due to fluid-fluid and …

This paper presents a hybrid deep learning framework that combines graph neural networks
with convolutional neural networks to predict porous media properties. This approach …

Efficient, economical, and environmentally friendly development of oil-gas reservoirs is
essential for mitigating the energy crisis. Notably, in oil reservoirs exhibiting pronounced …

Coupling CFD and DEM is commonly used to study particle-fluid flow in sand retention
systems for oil and gas wells, addressing the limitations of laboratory experiments and …

The success of CO2 storage projects largely depends on addressing formation damage,
such as salt precipitation, hydrate formation, and fines migration. While analytical models for …

The occurrence of multi-phase flows in porous media is a complex phenomenon that
involves multiple scales, ranging from individual pores to larger continuum scales …

While petroleum scientists and engineers have increasingly acknowledged the significance
of integrating geology with engineering for efficient petroleum development, the precise …

The objective of screen testing and selection is to minimise sand production while
maintaining acceptable filter permeability, however, screen failures during operation are …

The main contribution of this study is to present Pore-GNN, a novel GNN-based framework
for predicting the properties of porous media. The proposed architectures demonstrate that …

In porous media flow, conventional methods struggle to determine a reliable representative
elementary volume (REV), particularly in highly heterogeneous samples or dynamic …