tonyzyl/DiffusionReconstruct

Benchmarking of diffusion models for global field reconstruction from sparse observations

40
/ 100
Emerging

This project helps scientists and engineers reconstruct complete physical fields, like fluid flows or chemical concentrations, from only a few scattered measurements. You input sparse observation data, and it outputs a full, detailed map of the field. This is ideal for researchers in areas like environmental science, materials science, or meteorology who need to understand complex systems from limited sensor data.

No commits in the last 6 months.

Use this if you need to accurately fill in missing information for large-scale physical systems based on a small number of observed data points, especially when dealing with noisy measurements or requiring multiple possible outcomes.

Not ideal if you require extremely fast reconstruction times from noiseless data and are comfortable with a single, deterministic solution.

fluid-dynamics environmental-modeling materials-science atmospheric-science data-assimilation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

31

Forks

8

Language

Python

License

Apache-2.0

Last pushed

Dec 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tonyzyl/DiffusionReconstruct"

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