phi-rom/PhiROM

Repository for NeurIPS 2025 paper, "Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers."

34
/ 100
Emerging

This project helps engineers and scientists build better predictive models for complex systems described by time-dependent partial differential equations (PDEs), such as fluid dynamics or heat transfer. It takes observational data, even if sparse, from a system and incorporates the underlying physics to produce highly accurate, long-term forecasts of how the system will evolve under different conditions. Users are researchers or practitioners in fields like engineering, physics, or climate science who need to simulate and understand complex physical phenomena.

Use this if you need to create accurate, physics-informed reduced-order models (ROMs) for time-dependent PDEs, especially when you need to generalize to new parameters or perform long-term forecasting with potentially sparse data.

Not ideal if your problem does not involve time-dependent PDEs, or if you prefer purely data-driven models without enforcing physical consistency.

predictive-modeling fluid-dynamics physics-simulation numerical-methods engineering-analysis
No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Python

License

MIT

Last pushed

Nov 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/phi-rom/PhiROM"

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