Physics-Learning AI Datamodel (PLAID) datasets: a collection of physics simulations for machine learning

TL;DR

PLAID introduces a standardized, extensible framework and datasets for physics simulations to facilitate machine learning applications across diverse physical domains.

Contribution

It provides a unified data model, a library for dataset handling, and six benchmark datasets covering mechanics and fluid dynamics, promoting standardization and community engagement.

Findings

Six curated physics simulation datasets released under PLAID standard

Baseline benchmarks established for various machine learning methods

Tools available for community participation and ongoing evaluation

Abstract

Machine learning-based surrogate models have emerged as a powerful tool to accelerate simulation-driven scientific workflows. However, their widespread adoption is hindered by the lack of large-scale, diverse, and standardized datasets tailored to physics-based simulations. While existing initiatives provide valuable contributions, many are limited in scope-focusing on specific physics domains, relying on fragmented tooling, or adhering to overly simplistic datamodels that restrict generalization. To address these limitations, we introduce PLAID (Physics-Learning AI Datamodel), 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 (gitlab.com/drti/plaid). We release six carefully crafted datasets under the PLAID standard, covering structural mechanics and computational fluid dynamics, and provide baseline benchmarks using representative learning methods. Benchmarking tools are made available on Hugging Face, enabling direct participation by the community and contribution to ongoing evaluation efforts (huggingface.co/PLAIDcompetitions).