Motivation
Big data and machine learning are driving comprehensive economic and social transformations and are rapidly re-shaping the toolbox and the methodologies of applied scientists. Machine learning tools are designed to learn functions from data with little to no need for prior knowledge. As continuous developments in experimental and numerical methods improve our ability to collect high-quality data, machine learning tools become increasingly viable and promising in disciplines rooted in physical principles. Fluid dynamics is one of them.
Objectives
This course gives an overview and practical hands-on experience on how to integrate machine learning in fluid dynamics. The course originate as a compressed version of the course Data Driven Fluid Mechanics and Machine Learning, given at the Research Master program at the von Karman Institute. After a brief review of the machine learning landscape, we show how to frame problems in fluid mechanics as machine learning problems, and we explore challenges and opportunities. Attendees will be guided through a series of tutorial sessions in Python and will tackle several relevant applications: aeroacoustic noise prediction, turbulence modelling, reduced-order modelling and forecasting, meshless integration of (partial) differential equations, super-resolution and flow control.
Approach
All lectures consist of a short theoretical session and a set of practical exercises using Python. At the end of each day, the participants will be challenged with a group exercise. These will be working sessions in which the role of the instructor will be marginal: participants must be able to complete their assignment independently to get the course certificate. The course includes a short overview of Python programming and the use of the python packages that will be implemented.
Pre-requisites
Therefore, the only course pre-requisite is a basic understanding of any programming language and basic knowledge of Calculus, Linear Algebra and Fluid dynamics. The course is pitched for undergraduate and graduate students alike, as well as practitioners in the fields.
Certificates
1. Certificates of Participation. This will certify that the participant attended all lectures. No grading is involved.
2. Graded Course Certificate. This will be a graded certificate, which participants can use to obtain ECTS in their home Universities. The grading is based on the results of the exercises and the results of an online quiz, which will be active for 1 hour on Thursday 17th . The students will have the possibility to resubmit their solution to the exercises on Monday 14th . The grades will be sent by Friday 25th . The evaluation criteria for the exercises in Python is based on the clear and bug-free implementation of the various algorithms developed during the course. The quiz will include both theoretical questions and exercises. Examples of questions will be provided during the course. The final grade will be the average between the results of the quiz and the exercises. The estimated workload of the course consist of 22.5 h of lectures, and 22.5 h of self study (of which 7.5 during the course).
This course will take place online and on-site.
The maximum number of participants is almost reached. We will therefore close the registration one day earlier, on February 1st.
Monday 7 February 2022: Introduction and Python Fundamentals
08:00 Registration
08:45 Welcome Address and Course Introduction
09:00 Lec 1: What is Machine Learning ?
Prof. Miguel Mendez, von Karman Institute
10:30 Coffee Break
11:00 Lec 2: An Introduction to Python Programming
Mr. Julien Christophe, von Karman Institute
12:30 Lunch Break
13:30 Lec 3: An Introduction to Scientific Computing with Python
Mr.Francisco Torres, von Karman Institute
15:00 Coffee Break
15:30 Exercise 1: Regression with Model Selection and Uncertainty Quantification
Prof. Miguel Mendez, von Karman Institute
17:00 End of day
Tuesday 8 February 2022: Optimization Methods for Machine Learning
09:00 Lec 5: A Review of Optimization Tools
Mr. Pedro Marques, von Karman Institute
10:30 Coffee Break
11:00 Lec 6: Bio-Inspired Optimization: Genetic Algorithms and Particle Swarms
Prof. Miguel Mendez, von Karman Institute
12:30 Lunch Break
13:30 Lec 7: An Introduction to Genetic Programming
Mr. Joachim Dominique, von Karman Institute
15:00 Coffee Break
15:30 Exercise 2: Aeroacoustics Noise Prediction with Genetic Programming
Mr. Joachim Dominique, von Karman Institute
17:00 End of day
Wednesday 9 February 2022: Regression Methods from Machine Learning
09:00 Lec 9: Linear Tools for Nonlinear Regression and Super Resolution
Prof. Miguel Mendez, von Karman Institute
10:30 Coffee Break
11:00 Lec 10: The Bayesian Formalism: Gaussian Processes
Prof. Miguel Mendez, von Karman Institute
12:30 Lunch Break
13:30 Lec 11: Deep Learning and Physics Informed Artificial Neural Networks
Mr. Jan Van den Berghe, von Karman Institute
15:00 Coffee Break
15:30 Exercise 3: Deep Learning for Turbulence Modeling
Mrs. Matilde Fiore, von Karman Institute
17:00 End of day
Thursday 10 February 2022: Dimensionality Reduction
09:00 Lec 13: Dimensionality Reduction and Autoencoders
Prof. Miguel Mendez, von Karman Institute
10:30 Coffee Break
11:00 Lec 14: Linear Autoencoders and Modal Analysis
Prof. Miguel Mendez and Mr. Pedro Marquez, von Karman Institute
12:30 Lunch Break
13:30 Lec 15: Nonlinear Autoencoders: Manifold Learning, Kernel Methods and ANN
Prof. Miguel Mendez and Mr. Jan Van den Berghe, von Karman Institute
15:00 Coffee Break
15:30 Exercise 4: Autoencoding and Forecasting Flow Fields
Prof. Miguel Mendez, von Karman Institute
17:00 End of day
Friday 11 February 2022: Flow Control via Machine Learning
09:00 Lec 17: Fundamentals of Flow Control
Prof. Miguel Mendez, von Karman Institute
10:30 Coffee Break
11:00 Lec 18: Reinforcement Learning, Part I
Mr. Fabio Pino, von Karman Institute
12:30 Lunch Break
13:30 Lec 19: Reinforcement Learning, Part II
Mr. Romain Poletti, von Karman Institute
15:00 Coffee Break
15:30 Exercise 5: Flow Control via Genetic Programming and Reinforcement Learning
Mr. Romain Poletti and Mr. Fabio Pino, von Karman Institute
17:00 End of day
Reduction policy:
- 10% early bird registration (discount visible on the price list)
- 30% discount for citizens of NATO countries (discount will be applied during the registration process)
- 50% discount in case of online participation.
The citizens of the following countries are eligible to attend the von Karman Institute Lecture Series:
- EU member countries
- NATO member countries
- NATO's Mediterranean Dialogue (Algeria, Egypt, Israel, Jordan, Mauritania, Morocco, Tunisia)
- Istanbul Cooperation Initiative (Bahrain, Kuwait, Qatar, United Arab Emirates)
- Argentina, Australia, Bolivia, Brazil, Cabo Verde, Cameroon, Chile, Colombia, Japan, India, Indonesia, Macedonia, Malaysia, Mauritania, Mexico, Montenegro, Mozambique, New Zealand, Nigeria, Republic of Korea, Saudi Arabia, Serbia, Singapore, South Africa, Switzerland, Thailand, Uruguay, South-Africa and Vietnam.
VKI reserves the right to request a clearance check with Belgian authorities.
The participants will have to present their ID card (for EU citizens) or passport (for other citizens) the first day of the lecture series.
Sales Conditions:
| on-site - Undergraduate Students (Full) | 350.0 |
| on-site - PhD Students (Full) | 960.0 |
| on-site - Recognized Universities / Research Center (Full) | 1520.0 |
| on-site - Commercial organizations (Full) | 1920.0 |
| on-site - Special Registration (Full) | 0.0 |
| on-site - Lecturer (Full) | 0.0 |
| online - Undergraduate Students (Proof Needed) (Full) | 175.0 |
| online - PhD Students (Proof Needed) (Full) | 480.0 |
| online - Recognized Universities / Research Center (Full) | 760.0 |
| online - Commercial organizations (Full) | 960.0 |
| online - Special Registration (Full) | 0.0 |
| online - Lecturer (Full) | 0.0 |
*Fees are VAT included.
Hands on Machine Learning for Fluid Dynamics
By purchasing this product you agree with our sales conditions.