PICLas-ML

Machine-learning models for PICLas an open-source, 3D particle-based kinetic simulation framework for plasma dynamics and rarefied gas flows.

What we work on

• Machine-learning models used in PICLas - e.g. as gas-surface interaction (GSI) / scattering kernels
• Models are designed to be downloaded directly by PICLas and used during a simulation

Repositories

• PICLas-ML/GSI - gas-surface interaction / scattering kernel models. See the repo for architecture, training data, and usage details.

Links

• Code: PICLas-Github
• Documentation: PICLas-ReadTheDocs
• Developed in collaboration between the Institute of Space Systems at the University of Stuttgart and the spinoff company Boltzplatz