气候变化领域集成服务门户(CCPortal): PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media

CCPortal

DOI	10.1016/j.advwatres.2020.103539
	PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media
	Santos J.E.; Xu D.; Jo H.; Landry C.J.; Prodanović M.; Pyrcz M.J.
发表日期	2020
ISSN	0309-1708
卷号	138
英文摘要	We present the PoreFlow-Net, a 3D convolutional neural network architecture that provides fast and accurate fluid flow predictions for 3D digital rock images. We trained our network to extract spatial relationships between the porous medium morphology and the fluid velocity field. Our workflow computes simple geometrical information from 3D binary images to train a deep neural network (the PoreFlow-Net) optimized to generalize the problem of flow through porous materials. Our results show that the extracted information is sufficient to obtain accurate flow field predictions in less than a second, without performing expensive numerical simulations providing a speed-up of several orders of magnitude. We also demonstrate that our model, trained with simple synthetic geometries, is able to provide accurate results in real samples spanning granular rocks, carbonates, and slightly consolidated media from a variety of subsurface formations, which highlights the ability of the model to generalize the porous media flow problem. The workflow presented here shows the successful application of a disruptive technology (physics-based training of machine learning models) to the digital rock physics community. © 2020 Elsevier Ltd
关键词	Binary images Convolution Deep learning Deep neural networks Flow fields Flow of fluids Forecasting Learning systems Mechanical permeability Network architecture Porous materials Velocity Disruptive technology Fluid velocity field Geometrical informations Machine learning models Orders of magnitude Spatial relationships Subsurface formations Surrogate model Convolutional neural networks artificial neural network digital image flow modeling fluid flow permeability porous medium prediction rock mechanics surrogate method three-dimensional modeling
语种	英语
来源机构	Advances in Water Resources
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/131824
推荐引用方式 GB/T 7714	Santos J.E.,Xu D.,Jo H.,et al. PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media[J]. Advances in Water Resources,2020,138.
APA	Santos J.E.,Xu D.,Jo H.,Landry C.J.,Prodanović M.,&Pyrcz M.J..(2020).PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media.,138.
MLA	Santos J.E.,et al."PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media".138(2020).