Skip to content

Geophysics-AI/EikoNet

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 

Repository files navigation

EikoNet: A deep neural networking approach for seismic ray tracing

EikoNet is a software package that allows the training of a neural network that satisfies the Factored Eikonal for the computation of travel-time from any source-reciever pair in a user defined velocity model.

This approach is outline in greater detail in the publication: Smith et al. (2020) - EikoNet:A deep neural networking approach for seismic ray tracing.

Any additional question please contact: jsmith@caltech.edu

Notebooks

The folder Notebook gives a series of Notebooks that allow you to run the code for the 3D problems as outlined in the publication.

The code is commented to allow the user to understand the processing procedures. A full python package is currently being developed and we hope to release this in the coming weeks.

Developers

Jonathan Smith - California Institute of Technology
Jack Muir - California Institute of Technology
Kamyar Azizzadenesheli - California Institute of Technology
Zachary Ross - California Institute of Technology

About

Machine learning formulation for the Factored Eikonal Equation

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors