Machine Learning & Deep Learning for Geophysical Applications (GEO 124)
COURSE SCHEDULE
| Code | Date | Location | price (€)* |
|---|---|---|---|
| GEO 124 | 2 - 6 Mar 2026 | Online | 3300 |
| GEO 124 | 6 - 10 Jul 2026 | Online | 3300 |
| GEO 124 | 9 - 13 Feb 2026 | Istanbul | 4400 |
| GEO 124 | 20- 24 Apr 2026 | Oslo | 4400 |
COURSE OVERVIEW
The aim of the course is to introduce how Artificial Intelligence (Machine & Deep Learning) can be applied in geophysics. In the course you will acquaint yourself with the workflows and algorithms used in Machine and Deep Learning. Use will be made of open-source software: Weka and TensorFlow. Power-point presentations and videos will introduce various aspects of AI, but the emphasis is on computer-based exercises. We will apply methods to classify the data: Multilayer Perceptron, Support Vector, Nearest Neighbour, AdaBoost, Trees. Non-linear Regression is used to predict porosity. Quizzes will enhance the learning.
COURSE OUTLINE
5 days
Day 1:
o Machine learning
o Supervised Learning
o Classification
o Unsupervised Learning
o Clustering
o Attribute Selection
Day 2:
o Artificial Neural Networks
o Facies Classification,
o Semi-supervised Learning
o Deep Neural Nets
o Ensemble, Trees
Day 3:
o Lithology Segmentation
o Porosity Regression
o Activation Functions
o Deep Learning Networks
Day 4:
o Use of ChatGPT for DL
o CNN, SVM, GAN, U-net
o Hyper parameters
o Training Deep Learning Strategies
o Deep Learning for 4D
o GAN vs CNN
Day 5:
o ML Models
o Porosity prediction from Seismic
o CNN Salt Segmentation
o Boolean Logics
o DL for Geothermal & CO2
o AI for Inversion
o U-net Salt Segmentation
INSTRUCTOR
Instructor Profile
Instructor has a PhD from Utrecht University on “Full wave theory and the structure of the lower mantle” and joined Shell Research to develop methods to predict lithology and pore-fluid based on seismic, petrophysical and geological data. Subsequently worked for Shell in London to interpret seismic data from the Central North Sea Graben.
As part of a Quantitative Interpretation assignment, he was actively involved in managing, processing and interpreting Well Seismic Profiling data, while heading a team for the development of 3D interpretation methods using multi-attribute statistical and pattern recognition analysis. Subsequently he was responsible for Geophysics in the Shell Learning Centre and at the same time part-time professor in Applied Geophysics at the University of Utrecht. From 2001 till 2005 he worked on the development of Potential Field Methods (Gravity, Magnetics) for detecting oil and gas. From 2008 til 2013 he was visiting professor at the German Technical University in Muscat. Finally, he became a champion on the use of EM methods and involved in designing acquisition, processing and interpretation for Marine Controlled Source EM (CSEM) methods.
FAQ
DESIGNED FOR
All those interested in understanding the impact Artificial Intelligence will have on the Geosciences. Hence, Geologist and Geophysicists, involved in exploration and development of hydrocarbons or mineral resources, and those involved in geothermal and CO2 storage can benefit from the course.
LEARNING OBJECTIVES
The course's primary learning objectives are:
o Familiarization with Machine & Deep Learning
o Geophysical Applications of Artificial Intelligence
o Supervised, Unsupervised, Semi-Supervised Methods
o Classification, Clustering, Regression Applications
o Physics-involved Deep Learning
REGISTER
Registration is now OPEN!
Ph.D. students, group and early bird registrants are eligible to DISCOUNT!
For more details and registration please send email to: register@petro-teach.com
REQUEST IN HOUSE
Would you like a PetroTeach training course delivered at a time or location to suit you?
click for request in house