Zheng-Meng/Dynamics-Reconstruction-ML

Published in Nature Communications: Bridging known and unknown dynamics by transformer-based machine-learning inference from sparse observations

35
/ 100
Emerging

This project helps scientists and researchers understand the underlying patterns of complex systems even when they only have scattered, incomplete observations. It takes a limited set of measurements from a system you want to analyze and outputs a reconstruction of its complete, long-term behavior. Researchers in fields like physics, biology, or climate science would find this useful for analyzing dynamic processes.

Use this if you need to reconstruct the full behavior of a chaotic or nonlinear system from very sparse and random observation data, especially when you lack training data specific to that target system.

Not ideal if you have abundant, dense observation data for your target system, or if your system's dynamics are simple and linear.

complex-systems nonlinear-dynamics scientific-modeling time-series-analysis data-reconstruction
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

MIT

Last pushed

Oct 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Zheng-Meng/Dynamics-Reconstruction-ML"

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