Communications

By G. Raynaud

Here is an informal list of scientific communications. For any question, feel free to contact me.

On my work on Physics-Informed Neural Networks (PINN) with Profs. Frédérick Gosselin and Sébastien Houde :

  • An introduction to PINNs, LM2 Lab meeting (May 2020)
  • An extension of PINNs with a modal approach, IVADO Octobre Numérique (Oct. 2020) - more details - replay.
  • Simplifying Physics Informed Neural Networks in case of periodicity to address low quality and sparse data while solving differential equations : an application in fluid dynamics, APS March 2021 - abstract - replay.
  • ModalPINN: an extension of Physics-Informed Neural Networks with enforced truncated Fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors, preprint submitted to Journal of Computational Physics in July 2021 - arxiv - code on github.
  • MSc's presentation on August, 23rd 2021 - replay.
  • Study of Physics-Informed Neural Networks to Solve Fluid-Structure Problems for Turbine-like Phenomena - master thesis at Polytechnique Montréal - pdf. 

Technical trainings :

  • Presenting on a lightboard, LM2 Lab meeting (April 2021)

Invited talk :

  • Insights on machine learning for CFD and an introduction to physics-informed neural networks, Mai 20th 2021 for the Simulation Based Engineering Science program at Polytechnique Montréal - replay.

Random scientific presentation (not on a specific topic I was working on...) :

  • The impossible flight of bumblebees (or the importance of leading-edge vortices), LM2 Lab meeting (Feb. 2021)