Porous media, found in both natural forms (e.g., sand, oil-bearing rocks, honeycombs) and synthetic forms (e.g., lattice materials, metallic fibers, metal foams), play crucial roles in numerous natural and industrial processes. In nature, porous media are vital for soil formation, groundwater flow, and the movement of nutrients and pollutants. Industrial applications include filtration, fuel cells, energy storage, and biomedical devices.

The characteristics of porous media, such as pore size, grain size, and connectivity, significantly influence their physical and chemical properties like permeability, porosity, and surface area. Determining permeability typically involves resource-intensive experiments, as it varies widely among different porous media structures. Computational Fluid Dynamics (CFD) has become essential in studying fluid flow in complex geometries, providing valuable insights into behaviors such as multiphase flow and chemical reactions. However, CFD simulations can be computationally demanding, often requiring high computing power and extensive mesh elements.

To address these challenges, Artificial Intelligence (AI) techniques, including machine learning and deep learning, offer efficient and accurate methods to predict fluid flow behavior in porous media. This competition aims to leverage AI to enhance the understanding and prediction of fluid dynamics within porous structures, providing a cost-effective and scalable solution to traditional methods.

This competition is a part of DLAI8.