My current research focuses on deep learning in the area of fluid simulations. The basic idea is to accelerate and refine the simulations with machine learning techniques. Accordingly, part of my research deals with the intelligent interpolation of fluid simulations. In addition, I am currently also investigating upsampling methods for particle-based data.

Since 2018 I’m a Ph.D. candidate in Nils Thuerey’s group.


E-mail: lukas.prantl (at)
Phone: +
Fax: +
Room: 02.13.060



  • Lukas Prantl, “Neural Networks for Particle-based Fluid Data”, M.Sc. Thesis, Technische Universität München, April 2018. (English)
  • Lukas Prantl, “Interactive Interpolation of Fluid Simulations”, B.Sc. Thesis, Technische Universität München, August 2015. (English)

Talks and Posters

  • “Generating Liquid Simulations with Deformation-aware Neural Networks”, poster presentation, ICLR, May 2019
  • “Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds”, spotlight and poster presentation, ICLR, April 2020


Supervised Theses

  • Adversarial training of airfoil flow-predictions” – Daniel Matter, Bachelor’s Thesis, 2019