PoreFlow-Net

Implementation of PoreFlow-Net: a 3D convolutional neural network to predict fluid flow through porous media

Instructions

1. Download the desired data from the digital rock portal (or create your own via your preferred simulation method)
2. Use the train.py script to train a model

Model architecture

This is how our network looks like:

Methodology

Pre-requisites

To train/test the model we used tensorflow 1.12, newer versions should work

The rest of the necessary packages should be available via pip

Data

All the training/testing data can be found here: gdrive link

Room for improvement

The keras tunner could be used to optimize the number of filters on each encoding branch

Collaborations

We welcome collaborations

Citation

If you use our code for your own research, we would be grateful if you cite our publication AWR

@article{PFN2020,
title = "PoreFlow-Net: a 3D convolutional neural network to predict fluid flow through porous media",
journal = "Advances in Water Resources",
pages = "103539",
year = "2020",
issn = "0309-1708",
doi = "https://doi.org/10.1016/j.advwatres.2020.103539",
url = "http://www.sciencedirect.com/science/article/pii/S0309170819311145",
author = "Javier E. Santos and Duo Xu and Honggeun Jo and Christopher J. Landry and Maša Prodanović and Michael J. Pyrcz",
}