The course is ideal for geoscientists, engineers, and data analysts at all experience levels. Concepts are supported with ample illustrations and case studies, complemented by mathematical rigor benefitting the subject. Aspects of supervised learning, unsupervised learning, classification, and reclassification are introduced to illustrate how these methods apply to seismic data. The course is presented in English only. The video recording was originally produced as part of a GSH webinar.
The 24 high-quality videos present over 11 hours of material on the application of machine learning to seismic Interpretation. Your purchase of this course provides access for 1 year. Return to view the videos as often as you like. Please let us know if you find a graphic or two that you would like and we’ll be glad to share it. The course is offered with and without certification, as described below.
What you will learn:
What is machine learning and how does it apply to seismic exploration and unconventional resource development?
What is the difference between supervised and unsupervised machine learning?
When is an analysis statistical and when is it machine learning?
What is attribute space and what is the mathematical foundation of this technology?
How do you know if the results are any good?
What are some case histories that illustrate machine learning principals?
What are some practical tips?
Each of these topics includes one or more examples and simple exercises to illustrate a principal where appropriate.
- Supervised and Unsupervised Learning
- MLP; CNN; FCN; k-means; SOM
- Attribute space classification
- Seismic Processing for Machine Learning
- Attribute Selection List Objectives
- Principal Component Analysis (PCA)
- Geobody Classification
- Fluid Contacts
- Geobody Seismic Facies
- Making Predictions
- The Best Well
- The Best Seismic Processing
- Who Makes the Best Predictions?
Click on a unit below to view lessons
- Machine Learning Operation
- Machine Learning Foundation
- Machine Learning Practice
- Machine Learning Prediction