Predicting Effective Diffusivity of Porous Media from Images by Deep Learning
Abstract
Abstract We report the application of machine learning methods for predicting the effective diffusivity ( D e ) 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 ≲ D e < 1), e.g., >95% of predicted D e have truncated relative error of <10% when the true D e 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 D e < 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.,more »
- Authors:
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1619666
- Alternate Identifier(s):
- OSTI ID: 1599031
- Report Number(s):
- LA-UR-19-23183
Journal ID: ISSN 2045-2322; 20387; PII: 56309
- Grant/Contract Number:
- 89233218CNA000001
- Resource Type:
- Published Article
- Journal Name:
- Scientific Reports
- Additional Journal Information:
- Journal Name: Scientific Reports Journal Volume: 9 Journal Issue: 1; Journal ID: ISSN 2045-2322
- Publisher:
- Nature Publishing Group
- Country of Publication:
- United Kingdom
- Language:
- English
- Subject:
- 42 ENGINEERING; Earth Sciences; Material Science
Citation Formats
Wu, Haiyi, Fang, Wen-Zhen, Kang, Qinjun, Tao, Wen-Quan, and Qiao, Rui. Predicting Effective Diffusivity of Porous Media from Images by Deep Learning. United Kingdom: N. p., 2019.
Web. doi:10.1038/s41598-019-56309-x.
Wu, Haiyi, Fang, Wen-Zhen, Kang, Qinjun, Tao, Wen-Quan, & Qiao, Rui. Predicting Effective Diffusivity of Porous Media from Images by Deep Learning. United Kingdom. https://doi.org/10.1038/s41598-019-56309-x
Wu, Haiyi, Fang, Wen-Zhen, Kang, Qinjun, Tao, Wen-Quan, and Qiao, Rui. Tue .
"Predicting Effective Diffusivity of Porous Media from Images by Deep Learning". United Kingdom. https://doi.org/10.1038/s41598-019-56309-x.
@article{osti_1619666,
title = {Predicting Effective Diffusivity of Porous Media from Images by Deep Learning},
author = {Wu, Haiyi and Fang, Wen-Zhen and Kang, Qinjun and Tao, Wen-Quan and Qiao, Rui},
abstractNote = {Abstract We report the application of machine learning methods for predicting the effective diffusivity ( D e ) 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 ≲ D e < 1), e.g., >95% of predicted D e have truncated relative error of <10% when the true D e 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 D e < 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 D e < 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.},
doi = {10.1038/s41598-019-56309-x},
journal = {Scientific Reports},
number = 1,
volume = 9,
place = {United Kingdom},
year = {2019},
month = {12}
}
https://doi.org/10.1038/s41598-019-56309-x
Web of Science
Works referenced in this record:
Morphology, propagation dynamics and scaling characteristics of drying fronts in porous media: PROPAGATION DYNAMICS OF DRYING FRONTS
journal, May 2012
- Shokri, N.; Sahimi, Muhammad; Or, D.
- Geophysical Research Letters, Vol. 39, Issue 9
Seeing permeability from images: fast prediction with convolutional neural networks
journal, September 2018
- Wu, Jinlong; Yin, Xiaolong; Xiao, Heng
- Science Bulletin, Vol. 63, Issue 18
Mesoscopic predictions of the effective thermal conductivity for microscale random porous media
journal, March 2007
- Wang, Moran; Wang, Jinku; Pan, Ning
- Physical Review E, Vol. 75, Issue 3
Pore Scale Simulation of Transport and Electrochemical Reactions in Reconstructed PEMFC Catalyst Layers
journal, January 2010
- Lange, Kyle J.; Sui, Pang-Chieh; Djilali, Ned
- Journal of The Electrochemical Society, Vol. 157, Issue 10
3D Convolutional Neural Networks for Human Action Recognition
journal, January 2013
- Ji, Shuiwang; Xu, Wei; Yang, Ming
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, Issue 1
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Fast connected-component labeling
journal, September 2009
- He, Lifeng; Chao, Yuyan; Suzuki, Kenji
- Pattern Recognition, Vol. 42, Issue 9
Permeability prediction of shale matrix reconstructed using the elementary building block model
journal, November 2015
- Chen, Li; Kang, Qinjun; Dai, Zhenxue
- Fuel, Vol. 160
X-ray imaging and analysis techniques for quantifying pore-scale structure and processes in subsurface porous medium systems
journal, January 2013
- Wildenschild, Dorthe; Sheppard, Adrian P.
- Advances in Water Resources, Vol. 51
Improving direct physical properties prediction of heterogeneous materials from imaging data via convolutional neural network and a morphology-aware generative model
journal, July 2018
- Cang, Ruijin; Li, Hechao; Yao, Hope
- Computational Materials Science, Vol. 150
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
A multi-block lattice Boltzmann method for the thermal contact resistance at the interface of two solids
journal, June 2018
- Fang, Wen-Zhen; Gou, Jian-Jun; Chen, Li
- Applied Thermal Engineering, Vol. 138
Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets
journal, August 2018
- Yang, Zijiang; Yabansu, Yuksel C.; Al-Bahrani, Reda
- Computational Materials Science, Vol. 151
Material structure-property linkages using three-dimensional convolutional neural networks
journal, March 2018
- Cecen, Ahmet; Dai, Hanjun; Yabansu, Yuksel C.
- Acta Materialia, Vol. 146
Pore Architecture and Connectivity in Gas Shale
journal, February 2015
- King, Hubert E.; Eberle, Aaron P. R.; Walters, Clifford C.
- Energy & Fuels, Vol. 29, Issue 3
Generalized lattice Boltzmann model for flow through tight porous media with Klinkenberg's effect
journal, March 2015
- Chen, Li; Fang, Wenzhen; Kang, Qinjun
- Physical Review E, Vol. 91, Issue 3
The permeability of fibrous porous media
journal, June 1986
- Jackson, Graham W.; James, David F.
- The Canadian Journal of Chemical Engineering, Vol. 64, Issue 3
Nanoscale simulation of shale transport properties using the lattice Boltzmann method: permeability and diffusivity
journal, January 2015
- Chen, Li; Zhang, Lei; Kang, Qinjun
- Scientific Reports, Vol. 5, Issue 1
A dual-tube model for gas dynamics in fractured nanoporous shale formations
journal, October 2014
- Lunati, I.; Lee, S. H.
- Journal of Fluid Mechanics, Vol. 757
Fast Feature Pyramids for Object Detection
journal, August 2014
- Dollar, Piotr; Appel, Ron; Belongie, Serge
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, Issue 8