• Corpus ID: 231924593

Multi-Scale Neural Networks for to Fluid Flow in 3D Porous Media

@article{Santos2021MultiScaleNN,
  title={Multi-Scale Neural Networks for to Fluid Flow in 3D Porous Media},
  author={Javier E. Santos and Ying Yin and Honggeun Jo and Wen Pan and Qinjun Kang and Hari S. Viswanathan and Ma{\vs}a Prodanovi{\'c} and Michael J. Pyrcz and Nick Lubbers},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.07625}
}
The permeability of complex porous materials can be obtained via direct flow simulation, which provides the most accurate results, but is very computationally expensive. In particular, the simulation convergence time scales poorly as simulation domains become tighter or more heterogeneous. Semi-analytical models that rely on averaged structural properties (i.e. porosity and tortuosity) have been proposed, but these features only summarize the domain, resulting in limited applicability. On the…