ml-jku/mc-lstm

Experiments with Mass Conserving LSTMs

41
/ 100
Emerging

This project helps scientists and engineers working with complex systems predict outcomes more accurately when the total quantity of something (like water or energy) needs to stay constant. It takes historical data for processes like river flow, traffic patterns, or pendulum movements and provides improved forecasts. Hydrologists, traffic engineers, and physicists can use this to get better predictions while respecting fundamental conservation laws.

No commits in the last 6 months.

Use this if you need to predict time-series data for physical or economic systems where a specific quantity, like mass or energy, must be conserved, and standard prediction models aren't accurate enough.

Not ideal if your prediction problem doesn't involve any conservation laws, or if you need to model static, non-sequential data.

hydrology traffic-forecasting physics-modeling time-series-prediction conservation-laws
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

40

Forks

14

Language

Python

License

MIT

Last pushed

Jul 20, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ml-jku/mc-lstm"

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