PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media
PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media
复制标题
DOI：
10.1016/j.advwatres.2020.103539
复制
发表时间：
2020-04
影响因子：
4.7
通讯作者：
Javier E. Santos;Duo Xu;H. Jo;C. Landry;M. Prodanović;M. Pyrcz
中科院分区：
文献类型：
--
作者：
Javier E. Santos;Duo Xu;H. Jo;C. Landry;M. Prodanović;M. Pyrcz
我们提出了PoreFlow-Net，这是一种3D卷积神经网络架构，可为3D数字岩石图像提供快速准确的流体流动预测。我们训练我们的网络来提取多孔介质形态和流体速度场之间的空间关系。我们的工作流程从3D二进制图像中计算简单的几何信息，以训练深度神经网络（PoreFlow-Net），该网络经过优化，可概括多孔材料的流动问题。我们的研究结果表明，提取的信息是足够的，以获得准确的流场预测在不到一秒钟，而不进行昂贵的数值模拟提供了几个数量级的速度。我们还证明，我们的模型，训练与简单的合成几何形状，能够提供准确的结果，在真实的样本跨越粒状岩石，碳酸盐岩，轻微固结介质从各种地下地层，突出了模型的能力，概括多孔介质流动问题。这里介绍的工作流程展示了颠覆性技术（基于物理的机器学习模型训练）在数字岩石物理学社区的成功应用。
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.