Using Physics Informed Neural Network (PINN) to Improve a k-omega Turbulence Model



L. Davidson
"Using Physics Informed Neural Network (PINN) to Improve a k-omega Turbulence Model" (to be presented), ERCOFTAC Symposium on Engineering Turbulence Modelling and Measurements (ETMM-15), Dubrovnik on 22-24 September 2025.

pyCALC-RANS has now been extended with PINN.

  • View paper
  • Download the code here (18 MB, 2 July 2025)
  • Flowchart
  • pyCALC-RANS report. In Section 7.3 you find instructions on how to run the code.
  • The PINN Python script is found in folder PINN and also found here
  • Please read the README file

  • Download the 3D DNS/LES/DES pyCALC-LES code here








Department of Mechanics and Maritime Sciences
Division of Fluid Dynamice