AI4Science-WestlakeU/RealPDEBench

[ICLR26 Oral] RealPDEBench: A Benchmark for Complex Physical Systems with Paired Real-World and Simulated Data

46
/ 100
Emerging

This project helps scientists and engineers working with complex physical systems to forecast future states of these systems more accurately. It provides a benchmark dataset with both real-world measurements and matched numerical simulations, which can be used to train and evaluate machine learning models. Researchers in fluid dynamics, combustion, and other simulation-heavy fields can use this to develop better predictive models.

Use this if you are developing or evaluating machine learning models for spatiotemporal forecasting of physical phenomena, and you need a robust benchmark dataset that combines real sensor data with high-fidelity simulations.

Not ideal if your primary interest is in simple, non-physical time series forecasting or if you do not work with partial differential equations (PDEs) or complex physical simulations.

physical-system-modeling fluid-dynamics combustion-engineering spatiotemporal-forecasting scientific-machine-learning
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 13 / 25
Community 15 / 25

How are scores calculated?

Stars

58

Forks

9

Language

Python

License

Last pushed

Mar 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AI4Science-WestlakeU/RealPDEBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.