Deep Neural Networks for Map-Based 4D Seismic Pressure-Saturation Inversion

This repository reproduces the results in the following publications:

Dramsch, J. S., Corte, G., Amini, H., Lüthje, M., & MacBeth, C.. (2019, April). Deep Learning Application for 4D Pressure Saturation Inversion Compared to Bayesian Inversion on North Sea Data. In Second EAGE Workshop Practical Reservoir Monitoring 2019.

Dramsch, J. S., Corte, G., Amini, H., MacBeth, C., & Lüthje, M.. (2019). Including Physics in Deep Learning--An example from 4D seismic pressure saturation inversion. arXiv preprint arXiv:1904.02254.

Architecture

The network architecture includes basic physics (AVO) on the input data to learn noisy gradients and learn the residual.

Results