A fundamental challenge in the research of geologic subsurface flow is to upscale laboratory-measured, core-scale rock and flow properties to the field scale. We aim to combine physics with data analytics to address this fundamental challenge by developing novel machine-learning and data-assimilation based frameworks.
Super-resolution-assisted pore flow field prediction using neural networks
Predicting the permeability from porous media images with convolutional neural networks
Projects
Recent neural-network-based pore flow prediction using only porous media geometry can cause ill-posedness and has poor extrapolation capability. We proposed incorporating a coarse velocity field in the input to effectively improve the prediction performance, especially for those with a large degree of heterogeneity.
Calculating the permeability of porous media using direct pore-scale simulation is often expensive for realistic systems. We proposed using a physics-informed convolutional neural network to predict the permeability directly from porous media images.
Selected Publications
- Zhou, X.-H., McClure, J. E., Chen, C., and Xiao, H. Neural network–based pore flow field prediction in porous media using super-resolution. Physical Review Fluids, 7, 074302, 2022. DOI: https://doi.org/10.1103/PhysRevFluids.7.074302
- Wu, J., Yin, X., and Xiao, H. Seeing permeability from images: Fast prediction with convolutional neural networks. Science Bulletin, 63, 1215–1222, 2018. DOI: https://doi.org/10.1016/j.scib.2018.07.015
Funding and Acknowledgement
These Projects are funded by Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy - EXC 2075 - 390740016. We acknowledge the support by the Stuttgart Center for Simulation Science (SC SimTech). Funding and support is highly acknowledged.
Contacts
Qingqi Zhao
Dr.Wissenschaftlicher Mitarbeiter
Heng Xiao
Univ.-Prof. Dr.Professor für Daten-getriebene Simulation von Strömungen auf Höchstleistungsrechnern