Predicting porosity, permeability, and tortuosity of porous media from images by deep learning.

Predicting porosity, permeability, and tortuosity of porous media from images by deep learning.
复制标题

DOI:
10.1038/s41598-020-78415-x
复制
发表时间:
2020-12-08
期刊:
影响因子:
4.6
通讯作者:
Matyka M
Matyka M
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Graczyk KM;Matyka M

文献摘要

参考文献

被引文献

相似文献

卷积神经网络(CNN)被用来编码的初始配置的障碍物和多孔介质中的三个基本量之间的关系:孔隙度(),渗透率(k),和曲折度(T)。考虑了具有障碍物的二维系统。用格子Boltzmann方法模拟了多孔介质中的流体流动。已进行了分析的系统,其中涵盖了五个数量级的渗透率和曲折的跨度。结果表明,神经网络可以用来预测孔隙度,渗透率和弯曲度具有良好的精度。利用CNN模型,得到了T和之间的关系,并与经验估计进行了比较。
Convolutional neural networks (CNN) are utilized to encode the relation between initial configurations of obstacles and three fundamental quantities in porous media: porosity (), permeability (k), and tortuosity (T). The two-dimensional systems with obstacles are considered. The fluid flow through a porous medium is simulated with the lattice Boltzmann method. The analysis has been performed for the systems with which covers five orders of magnitude a span for permeability and tortuosity . It is shown that the CNNs can be used to predict the porosity, permeability, and tortuosity with good accuracy. With the usage of the CNN models, the relation between T and has been obtained and compared with the empirical estimate.
DOI: 10.1016/j.advwatres.2018.04.009
发表时间: 2018-06-01
影响因子: 4.7
作者:
Li, Zi;Galindo-Torres, Sergio;Li, Ling
通讯作者: Li, Ling
DOI: 10.1016/s0010-4655(97)00054-4
发表时间: 1997-08-01
影响因子: 6.3
作者:
Lagaris, IE;Likas, A;Fotiadis, DI
通讯作者: Fotiadis, DI
DOI: 10.1103/physreve.78.026306
发表时间: 2008-08-01
期刊: PHYSICAL REVIEW E
影响因子: 2.4
作者:
Matyka, Maciej;Khalili, Arzhang;Koza, Zbigniew
通讯作者: Koza, Zbigniew
DOI: 10.1038/s41598-019-39741-x
发表时间: 2019-03-04
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Bakhshian, Sahar;Hosseini, Seyyed A.;Shokri, Nima
通讯作者: Shokri, Nima
DOI: 10.1038/s41598-017-14810-1
发表时间: 2017-11-01
期刊: Scientific reports
影响因子: 4.6
作者:
Backeberg NR;Iacoviello F;Rittner M;Mitchell TM;Jones AP;Day R;Wheeler J;Shearing PR;Vermeesch P;Striolo A
通讯作者: Striolo A