Skip to content

Neural style transfer applied to elastic subsurface models [SEG19]. Visualized and explained.

License

Notifications You must be signed in to change notification settings

ovcharenkoo/geo-style-keras

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Style transfer for generation of realistically textured subsurface models. Visualized and explained.

Ovcharenko Oleg, Vladimir Kazei, Daniel Peter, and Tariq Alkhalifah. "Style transfer for generation of realistically textured subsurface models." In SEG Technical Program Expanded Abstracts 2019, pp. 2393-2397. Society of Exploration Geophysicists, 2019.

The notebook in this repository reproduces the workflow for texture-transfer from an elastic isotropic subsurface model to a prior synthetic distribution. We follow the (Gatys et al., 2015) to transfer texture from a Marmousi II benchmark geological model to a background distribution generated using a random Gaussian field.


Example

Make a random Gaussian field resamble the Marmousi II layered features.

result

Workfolw

We apply the iterative optimization approach which benefits from higher control at cost of longer generation times. To accelerate the texture transfer one would use a GAN-based approach as proposed by (Johnson et al., 2016) and (Ulyanov et al., 2016).

roadmap

Visualizations

Seeing the outputs from intermediate layers in the network leads to better understaing of what is going on at each step of the algorithm.

visualizations

Well-log constrains

Enforcing the optimization to match certain areas from the style model ultimately leads to a controlled texture generation. output

How to run

In the terminal, go to the folder with the notebook and run the command

jupyter notebook geo_style.ipynb

Resources used:

https://github.com/kevinzakka/style-transfer

https://github.com/rrmina/neural-style-pytorch

https://www.tensorflow.org/beta/tutorials/generative/style_transfer


Dependencies

Jupyter    4.4.0

Keras    2.2.4

Numpy    1.15.4

Pillow    5.3.0

Scipy    1.1.0


BibTeX

@incollection{ovcharenko2019style,
title={Style transfer for generation of realistically textured subsurface models},
author={Ovcharenko, Oleg and Kazei, Vladimir and Peter, Daniel and Alkhalifah, Tariq},
booktitle={SEG Technical Program Expanded Abstracts 2019},
pages={2393--2397},
year={2019},
publisher={Society of Exploration Geophysicists}
}