Machine Learning in Geoscience - PhD Defence of Jesper Dramsch

Machine Learning in Geoscience - Applications of Deep Neural Networks in 4D Seismic Data Analysis
Closed Captions [CC] available.

PhD Defence presentation at the Technical University of Denmark.
Thanks to everyone that attended!

——————————————————————————————————————
Get my filming and presentation equipment here:
https://www.amazon.com/shop/jesperdra...
——————————————————————————————————————

Get the presentation here: https://10.6084/m9.figshare.13634045
Get the thesis and all code openly here: https://dramsch.net/phd

——————————————————————————————————————
Timestamps
——————————————————————————————————————
0:00 Prelude
0:24 Motivation
2:20 Outline
2:58 What's Seismic
7:47 What are Neural Networks
11:59 Transfer Learning Seismic Interpretation (Chapter 5)
16:50 Complex-Valued Neural Networks on Physical Data (Chapter 6)
26:32 4D Inversion with Neural Networks (Chapter 7)
39:47 3D Warping for 4D Seismic (Chapter 8)
47:47 Conclusion

——————————————————————————————————————
Publications in this Defence
——————————————————————————————————————
Journal Articles
=============
Dramsch, J. S., A. N. Christensen, C. MacBeth, and M. Lüthje (2019b). “Deep Unsupervised 4D Seismic 3D Time-Shift Estimation with Convolutional Neural Networks”. In: IEEE Transactions in Geoscience and Remote Sensing.

Dramsch, J. S., M. Lüthje, and A. N. Christensen (2019h). “Complex-valued neural networks for machine learning on non-stationary physical data”. In: Computers & Geoscience.


Peer-Reviewed Conference Proceedings
================================
Dramsch, J. S. and M. Lüthje (2018d). “Deep-learning seismic facies on state-of-the-art CNN architectures”. In: SEG Technical Program Expanded Abstracts 2018. Published, Chapter 4. Society of Exploration Geophysicists.


Peer-Reviewed Workshop Proceedings
===============================
Dramsch, J. S., G. Corte, H. Amini, M. Lüthje, and C. MacBeth (2019d). “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., G. Corte, H. Amini, C. MacBeth, and M. Lüthje (2019g). “Including Physics in Deep Learning – An Example from 4D Seismic Pressure Saturation Inversion”. In: 81st EAGE Conference and Exhibition 2019 Workshop Programme.

——————————————————————————————————————
Additional publications in the thesis
——————————————————————————————————————
Peer-Reviewed Workshop Proceedings
===============================
Dramsch, J. S., F. Amour, and M. Lüthje (2018a). “Gaussian Mixture Models For Robust Unsupervised Scanning-Electron Microscopy Image Segmentation Of North Sea Chalk”. In: First EAGE/PESGB Workshop Machine Learning.

Book Chapters
============
Dramsch, J. S. (Sept. 2020a). “70 years of machine learning in geoscience in review”. In: Advances in Geophysics. Ed. by B. Moseley and L. Krischer. Academic Press.

——————————————————————————————————————
Other work that resulted from this PhD
——————————————————————————————————————
Journal Articles
=============
Aabø, T. M., J. S. Dramsch, C. L. Würtzen, S. Seyum, F. Amour, M. Welch, and M. Lüthje (2020). “An integrated workflow for fracture characterization in chalk reservoirs, applied to the Kraka Field”. In: Marine and Petroleum Geology.

Côrte, G., J. S. Dramsch, H. Amini, and C. MacBeth (2020). “Deep neural network application for 4D seismic inversion to changes in pressure and saturation: Optimizing the use of synthetic training datasets”. In: Geophysical Prospecting.


Peer-Reviewed Conference Proceedings
===============================
Corte, G., Dramsch, J., MacBeth, C., & Amini, H. (December 2020). Deep Neural Network Application for 4D Seismic Inversion to Pressure and Saturation: Enhancing Training Data Sets. EAGE Conference & Exhibition 2020.

Mosser, L., W. Kimman, J. S. Dramsch, S. Purves, A. De la Fuente Briceño, and G. Ganssle (June 2018a). “Rapid seismic domain transfer: Seismic velocity inversion and modeling using deep generative neural networks”. In: 80th EAGE Conference & Exhibition.

Aabø, T. M., J. S. Dramsch, M. Welch, and M. Lüthje (June 2017a). “Correlation of Fractures From Core, Borehole Images and Seismic Data in a Chalk Reservoir in the Danish North Sea”. In: 79th EAGE Conference & Exhibition 2017.

Peer-Reviewed Workshop Proceedings
===============================
Dramsch, J. S. and M. Lüthje (2018e). “Information Theory Considerations In PatchBased Training Of Deep Neural Networks On Seismic Time-Series”. In: First EAGE/PESGB Workshop Machine Learning.

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

💙 Linkedin:   / mlds  
💜 Twitter:   / jesperdramsch  
🖤 Github: https://github.com/JesperDramsch
💚 ORCID: http://orcid.org/0000-0001-8273-905X
🧡 Google Scholar: https://scholar.google.de/citations?u...

🌍 Main Website: https://dramsch.net
🎁 Community:   / thegeophysicist