OEKB301579 Advanced methods in remote sensing: Machine learning and cloud computing

Type
Lecture and exercise
Semester hours
2
Lecturer (assistant)
Faßnacht, Fabian
Organisation
Geomatics
Offered in
Wintersemester 2026/27
Languages of instruction
Englisch
Content

This semester, this course will focus on a specific subfield of machine learning: “deep learning.” This subfield is currently revolutionizing remote sensing across all areas (classification, regression, simulation) and is increasingly replacing conventional machine learning methods (such as random forests, support vector machines, etc.).

The course aims to teach students with no prior experience in AI and deep learning the fundamental principles in an accessible way, covering both theory and practice. In the final third of the course, we will apply the knowledge gained through a small research project.

The course will cover the following topics (each consisting of a theoretical section and a corresponding exercise):

1. Introduction to Artificial Intelligence and Deep Learning in the context of remote sensing
2. Introduction to supervised learning
3. Shallow neural networks
4. Deep neural networks
5. Loss functions
6. Training Deep Learning Models
7. Deep Learning Models for Images
8. Deep Learning for Time Series

After covering this material, we will conduct a small research project in groups during the final part of the course, where we will creatively apply the fundamental principles we have learned and also discuss principles of cloud computing.
Previous knowledge expected

Basic programming skills, basic knowledge of remote sensing and classification methods.
Objective (expected results of study and acquired competences)

Students will understand the basic principles of AI and deep learning methods. During the course, students will learn to design and implement neural networks and apply them to remote sensing data.
You can find more details like the schedule or information about exams on the course-page in BOKUonline.