ml-jku/mc-lstm
Experiments with Mass Conserving LSTMs
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.
Stars
40
Forks
14
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
aeon-toolkit/aeon
A toolkit for time series machine learning and deep learning
sktime/sktime
A unified framework for machine learning with time series
Nixtla/neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
tslearn-team/tslearn
The machine learning toolkit for time series analysis in Python
Nixtla/statsforecast
Lightning ⚡️ fast forecasting with statistical and econometric models.