May 15, 2024 - 17:00
Den Haag

Monthly Lecture

Jaap C. Mondt (Breakaway) will talk about:

Machine Learning for Geophysical Applications?

Abstract
More and more Deep Learning will play a role not only in society in general but also in the geosciences. Machine & Deep Learning resorts under the overall heading of Artificial Intelligence. In these domains often the word “Algorithms” is used to indicate that computer algorithms are used to obtain results. Also, “Big Data” is mentioned, indicating that these algorithms need a fast amount of training data to produce useful results.

Many scientists mention “Let the data speak for itself” when referring to Machine/Deep Learning, indicating that hidden or latent relationships between observations and classes of (desired) outcomes can be derived using these algorithms. Many applications are in seismic acquisition, processing, and interpretation, but also in the non-seismic domain.

In the presentation, the basic building blocks of a Deep Learning algorithm will be discussed and an interesting network to predict porosity directly from seismic will be shown, called by me “You ain’t seen nothing yet”., as it demonstrates the beginning of a revolutionary change in the geosciences.

About the presenter
A Bachelor in Geology (Leiden), a Master in Geophysics (Utrecht) and a PhD (Utrecht) on “Full wave theory and the structure of the lower mantle”. After his PhD he joined Shell Research to develop methods to predict lithology and pore-fluid based on seismic, petrophysical and geological data. Subsequently, he worked for Shell in London to interpret seismic data from the Central North Sea Graben. After his return to The Netherlands, he worked on 3D interpretation methods using multi-attribute statistical and pattern recognition methods, followed by quality Assurance of “Contractor” software for seismic processing. He became responsible for Geophysics in the Shell Learning Centre. During that time he was also a part-time professor in Applied Geophysics (Utrecht). Finally, he worked on the development of Potential Field Methods (Gravity, Magnetics) and became a champion on the use of EM methods. After his retirement he founded Breakaway, specialised in courses on acquisition, processing, and interpretation of geophysical data. Lately, he became keenly interested in the use of Machine/Deep Learning for Geophysical Applications.

Teams meeting link: Will be published closer to the event.

 

Venue:
Millers, Plein 10, Den Haag