Master-Seminar - Deep Learning in Physics (IN2107, IN0014)

Prof. Dr. Nils ThuereyDr. Liwei Chen, Benjamin Holzschuh,


Studies Master Informatics
Time, Place

Wednesdays 14:00-16:00 Online


20th., October 2021

BBB link


Using deep learning methods for physical problems is a very quickly developing area of research. The research group of Prof. Thuerey has studied learning-based methods for Navier-Stokes problems and fluid flow applications in recent years, examples of which include learning latent-spaces for physical predictions, generative adversarial networks with temporal coherence, and the inference of Reynolds-averaged Navier-Stokes flows around airfoils. Beyond these physics-based deep learning works of the Thuerey group, this seminar will give an overview of recent developments in the field.

In this course, students will autonomously investigate recent research about machine learning techniques in the physical simulation area. Independent investigation for further reading, critical analysis, and evaluation of the topic are required.


Participants are required to first read the assigned paper and start writing a report. This will help you prepare for your presentation.
  • It is only allowed to miss a single time-slot. Missing a second one means failing the seminar. If you have to miss any, please let us know in advance.
  • An advisor is assigned to each one with the paper.
  • Two weeks before the talk there will be a mandatory meeting with your advisor to review the report and discuss the structure of the presentation.
  • A short report (4 pages max., excluding references in the ACM SIGGRAPH TOG format (acmtog) - you can download the precompiled latex template) should be prepared before the meeting with the advisor.
  • Guideline: You can begin with writing a summary of the work you present as a start point; but, it would be better if you focus more on your own research rather than just finishing with the summary of the paper. We, including you, are not interested in revisiting the work done before; it is more meaningful if you make an effort to put your own reasoning about the work, such as pros and cons, limitation, possible future work, your own ideas for the issues, etc.
Presentation (slides)
  • The participants have to present their topics in a talk (in English), which should last 25 minutes. Don't put too many technical details into the talk, make sure the audience gets the paper's main idea. Be prepared to answer questions regarding the technical details, you could prepare backup slides for that.
  • Afterwards, a short discussion session will follow.
  • Plagiarism is important; please do not simply copy the original authors' slides. You can certainly refer to them.
  • The semi-final slides (PDF) should be sent one week before the talk; otherwise, the talk will be canceled. We strongly encourage you to finalize the semi-final version as far as possible. We will take a look at the version and give feedback. You can revise your slides until your presentation.
  • Be ready in advance. We suggest testing the machines you are going to use before the lecture starts. You can bring your laptop or ask us one (also any converter you need for the projector) in advance. A laser pointer will be provided, so you can use if you want.
  • The final slides and report should be sent after the talk.

Preliminary Schedule

  Paper list sent via Email
  Send preferred 5 topics/papers by 05 September 2021 (Sunday 23:59)

- 20.10 Kickoff (Introduction lecture)

- 27.10 No meeting

- 3.11 No meeting

- 10.11 Meeting #1 (First presentation) 

- 17.11 Meeting #2

- 24.11 Meeting #3

- 1.12 Meeting #4

- 8.12 Meeting #5

- 15.12 Meeting #6

- 22.12 No meeting

- 12.1 Meeting #7

- 19.1 Meeting #8

- 26.1 Meeting #9 (if necessary!)

Paper list

No. Paper Date First name Last name Supervisor
1 Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction 10 November  Louis Dorge de Vacher de Saint Géran Chen
2 Machine learning accelerated computational fluid dynamics 10 November  Tianhao Lin Holzschuh
3 Assessment of unsteady flow predictions using hybrid deep learning based reduced-order models


4 Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

17 November

Annalena Kofler Chen
5 Deep learning methods for super-resolution reconstruction of turbulent flows


6 Transfer learning for nonlinear dynamics and its application to fluid turbulence

17 November

Ege Ahmed Holzschuh
7 Learning to control PDEs with differentiable physics

24 November

Anis Yaich Chen
8 Discovering physical concepts with neural networks

24 November

Ajla Karisik Holzschuh
9 Neural Ordinary Differential Equations

1 December

Robert Hajda Chen
10 Hamiltonian Neural Networks

1 December

José Miguel

Ferreira Henriques

11 Physics Informed Deep Learning: Data-driven Solutions of Nonlinear Partial Differential Equations 8 December Christina Nuss-Brill Holzschuh
12 Model identification of reduced order fluid dynamics systems using deep learning


13 Deep learning for universal linear embeddings of nonlinear dynamics

8 December

Qing Sun Chen
14 tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow

15 December

Mert Ülker Chen
15 Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations 15 December Stefan Frisch Holzschuh
16 Lagrangian Fluid Simulation with Continuous Convolutions


17 Solving high-dimensional partial differential equations using deep learning


18 Learning data-driven discretizations for partial differential equations


19 SPNets: Differentiable Fluid Dynamics for Deep Neural Networks

12 Jan. 2022

Anirudh Narayanan Balaraman Chen
20 Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

12 Jan. 2022

Tobias Neumeier Holzschuh
21 Discovering Symbolic Models from Deep Learning with Inductive Biases

19 Jan. 2022

Andreas Stöckeler Chen
22 Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming

19 Jan. 2022

Nadiia Matsko Holzschuh
23 DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators