Read the course online — lecture notes, exercises, and links to slides.
This repository contains resources accompanying the course Machine Learning in Fluid Mechanics offered by the Institute of Fluid Mechanics at TU Dresden. Note that slides, Python chapters, and other resources will be regularly updated throughout the term.
This course previously received funding from the Foundation for Innovation in Higher Education.
| # | Topic | Lecture | Exercise | Slides |
|---|---|---|---|---|
| 0 | How to learn with generative AI | Read | — | — |
| 1 | Course overview and motivation | Read | Exercises | Slides |
| 2 | Introduction to machine learning | Read | Exercises | Slides |
| 3 | Surrogate models for discrete predictions | |||
| 4 | Surrogate models for continuous predictions | |||
| 5 | Analysis of coherent structures | |||
| 6 | Reduced-order modeling | |||
| 7 | Bayesian optimization and exploration | |||
| 8 | Data assimilation | |||
| 9 | Active flow control |
Later lecture and exercise materials will be revised before they are linked.
The course datasets are currently being revised. A download link will be published here soon.
- Books on computational fluid dynamics
- The OpenFOAM technology primer by T. Marić, J. Höpken, and K. G. Mooney
- The finite volume method in computational fluid dynamics by F. Moukalled, L. Mangani, and M. Darwish
- An introduction to computational fluid dynamics: the finite volume method by H. K. Versteeg and W. Malalasekera
- Books on linear algebra
- Introduction to linear algebra by G. Strang
- Books on data-driven modeling and control
- Data-driven science and engineering: machine learning, dynamical systems, and control by S. L. Brunton and J. N. Kutz
- Dynamic mode decomposition: data-driven modeling of complex systems by J. N. Kutz, S. L. Brunton, B. W. Brunton, and J. L. Proctor
- Grokking deep reinforcement learning by M. Morales
- Deep learning with PyTorch by E. Stevens, L. Antiga, and T. Viehmann
- Books on programming
- Python crash course by E. Matthes
- C++ crash course: a fast-paced introduction by J. Lospinoso
- The Linux command line by W. Shotts
The course overview organizes the lectures, exercises, and slides. Materials are linked as they are revised. Chapters are editable Python scripts in notebooks/, with Markdown cells. These Python scripts are the course sources.
See Working with the course sources for installation, running scripts, capturing figures and outputs, local preview, and GitHub Pages publishing.
quarto render
quarto preview --port 8002The website is generated in docs/. Whole-site builds reuse _freeze/; explicitly render a chapter to execute it and update its results.