Project

Testing
Package
Meta

Physics-Learning AI Datamodel

PLAID (Physics-Learning AI Datamodel) is a flexible and extensible framework for representing and sharing datasets of physics simulations. PLAID defines a unified standard for describing simulation data and is accompanied by a library for creating, reading, and manipulating complex datasets across a wide range of physical use cases. The data model and library have initially been developped at SafranTech, the research center of Safran group.

• Documentation
• Source code

Open-data

At the heart of PLAID is the seemless exchange of dataset for streamlined collaboration. Six interactive benchmarks are provided in a HuggingFace community. Corresponding datasets are provided in HuggingFace as well, and in a Zenodo community.

Each dataset comes with a visualization application, hosted as a Hugging Face space, for example: