Get the condensed talk from Amsterdam: Deep Learning Application for 4D Pressure Saturation Inversion Compared to Bayesian Inversion on North Sea Data

——————————————————————————————————————
Join the community and support these videos:
🎁 www.patreon.com/thegeophysicist
——————————————————————————————————————

Presented in Amsterdam during the Practical Reservoir Monitoring Workshop in Amsterdam.

📝 Preprint: doi.org/10.31223/osf.io/zytp2
📝 Paper: doi.org/10.3997/2214-4609.201900028
📝 Presentation: doi.org/10.6084/m9.figshare.7963775

——————————————————————————————————————
Authors:
Jesper Dramsch, Gustavo Corte, Hamed Amini, Mikael Lüthje, Colin MacBeth

Abstract:
In this work we present a deep neural network inversion on map-based 4D seismic data for pressure and saturation. We present a novel neural network architecture that trains on synthetic data and provides insights into observed field seismic. The network explicitly includes AVO gradient calculation within the network as physical knowledge to stabilize pressure and saturation changes separation. We apply the method to Schiehallion field data and go on to compare the results to Bayesian inversion results. Despite not using convolutional neural networks for spatial information, we produce maps with good signal to noise ratio and coherency.
——————————————————————————————————————
Chapters:
0:00 Vlog
1:25 Preamble
2:13 Outline
2:38 Data
3:41 Neural Networks
5:43 Training Schema for Transfer Learning
6:23 Physics-based Neural Network Architecture
9:08 Results & Discussion
15:05 Conclusion
16:55 Acknowledgements

——————————————————————————————————————
👋 Social

💙 Linkedin: www.linkedin.com/in/thegeophy...
🖤 Github: github.com/JesperDramsch
💚 ORCID: orcid.org/0000-0001-8273-905X
🧡 Google Scholar: scholar.google.de/citations?user=2nrI28QAAAAJ

✒️ Professional Blog: the-geophysics.net/
🌍 Main Website: dramsch.net/
🎁 Community: www.patreon.com/thegeophysicist ——————————————————————————————————————
🎥 My Camera Gear
www.amazon.com/shop/jesperdramsch ——————————————————————————————————————
📝 Disclaimer
Jesper Dramsch is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for us to earn fees by linking to Amazon.com and affiliated sites.

Opinions my own. Not financial advice. Sponsors are acknowledged. For entertainment p