Browsing by Author "Kang, Qinjun"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Predicting Effective Diffusivity of Porous Media from Images by Deep Learning
    Wu, Haiyi; Fang, Wen-Zhen; Kang, Qinjun; Tao, Wen-Quan; Qiao, Rui (Nature, 2019-12-31)
    We report the application of machine learning methods for predicting the effective diffusivity (De) of two-dimensional porous media from images of their structures. Pore structures are built using reconstruction methods and represented as images, and their effective diffusivity is computed by lattice Boltzmann (LBM) simulations. The datasets thus generated are used to train convolutional neural network (CNN) models and evaluate their performance. The trained model predicts the effective diffusivity of porous structures with computational cost orders of magnitude lower than LBM simulations. The optimized model performs well on porous media with realistic topology, large variation of porosity (0.28–0.98), and effective diffusivity spanning more than one order of magnitude (0.1 ≲ De < 1), e.g., >95% of predicted De have truncated relative error of <10% when the true De is larger than 0.2. The CNN model provides better prediction than the empirical Bruggeman equation, especially for porous structure with small diffusivity. The relative error of CNN predictions, however, is rather high for structures with De < 0.1. To address this issue, the porosity of porous structures is encoded directly into the neural network but the performance is enhanced marginally. Further improvement, i.e., 70% of the CNN predictions for structures with true De < 0.1 have relative error <30%, is achieved by removing trapped regions and dead-end pathways using a simple algorithm. These results suggest that deep learning augmented by field knowledge can be a powerful technique for predicting the transport properties of porous media. Directions for future research of machine learning in porous media are discussed based on detailed analysis of the performance of CNN models in the present work.
  • Thumbnail Image
    The Role of Disjoining Pressure and Thermal Activation in the Invasion of Droplets into Nanopores
    Fang, Chao; Kang, Qinjun; Qiao, Rui (2019-03-21)
    Multiphase transport at a nanoscale level plays a key role in applications including drying of nanoporous materials and gas/oil recovery from low permeability rocks. A frequently encountered scenario in multiphase transport is the presence of droplets near nanopores. Whether droplets invade the nanopores or become trapped at their entrance greatly affects the operation of engineered systems. Here we analyze the free energy profile of nanometer-sized droplets entering the nanopore and how the profile is affected by the pressure difference and the size of the droplet and the nanopore. We show that, for nanopores whose surface is fully wetted by water but not the droplet, a droplet larger than the pore diameter must overcome a higher free energy barrier than that predicted by classical theories due to the large disjoining pressure. For smaller nanodroplets, the threshold pressure for their invasion into a given nanopore can be lowered by thermal activation. When a droplet is slightly narrower than a pore, and thus is often assumed to enter the pore freely, a large energy barrier for droplet entry can actually exist. The droplet cannot easily enter the pore even with hydrodynamic drag by moving fluids. Entering the pore through Brownian motion is possible, and the mean entry time depends sensitively on the pore size and can reach seconds or even longer. These findings provide molecular insights on the invasion of droplets into nanopores and lay foundations for large-scale modeling of multiphase nanofluidic transport.