Rose-STL-Lab/dyffusion

[NeurIPS 2023] A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

48
/ 100
Emerging

This tool helps scientists and engineers predict how complex systems evolve over time. Given initial measurements or conditions of a physical system, it generates a sequence of future states or snapshots. It's designed for researchers and practitioners who need accurate, physics-informed spatiotemporal forecasts.

231 stars.

Use this if you need to accurately forecast the future states of complex physical systems, like fluid dynamics or mesh deformations, based on their initial conditions.

Not ideal if you're looking for a simple, off-the-shelf solution without any code-level setup or if your data isn't structured for spatiotemporal forecasting.

spatiotemporal-forecasting physics-simulation fluid-dynamics materials-science climate-modeling
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

231

Forks

26

Language

Python

License

Apache-2.0

Last pushed

Oct 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Rose-STL-Lab/dyffusion"

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