Introduction to Machine Learning in Geotechnics (pilot course, March 2025)

Curious about machine learning and prefer an applied approach? Join our 4-session course, learn the basics of machine learning and explore the breadth of opportunities for using machine learning in geotechnics. You need no prior knowledge of machine learning, but basic experience in Python programming is required. We go through theory for each topic, followed by a Python coding example, which you will run along with us. We will give you an overview of the main branches of machine learning - supervised, unsupervised, and reinforcement learning – and describe how different datasets direct the use of different models. The last part of the course focuses on demonstrating how you, with just a few lines of code, can carry out the basics of advanced tasks such as image classification, time series forecasting and data clustering. You will apply your new skills through several smaller tasks during the course.

Content

  The course guides you through central topics such as; 

• When to consider machine learning and when not to
• The principles and inner workings of machine learning
• Branches of machine learning
• Key issues encountered (overfitting/underfitting, complexity/interpretability trade-off, data-splitting, performance metrics, bias and balance).
• Considerations for geotechnical data and required properties of datasets for machine learning.