JamesTwallin/GridSeis

Predicting Carbon Intensity from Grid Frequency Data Using FFT Analysis and Gradient Boosted Regression

33
/ 100
Emerging

This project helps energy analysts and smart device developers estimate how carbon-intensive the electricity grid is, solely by looking at grid frequency data. It takes in raw, 1-second electrical grid frequency data and outputs a predicted carbon intensity value for that time period. This is useful for anyone needing to understand the real-time environmental impact of electricity without direct access to detailed generation mix information.

Use this if you need to estimate carbon intensity in real-time or in regions with limited data access, enabling applications like smart devices that optimize electricity usage during cleaner power periods.

Not ideal if you require precise, verified carbon intensity data from official sources, as this provides an estimation based on an indirect signal.

energy-monitoring carbon-estimation smart-grid energy-efficiency power-system-analysis
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

29

Forks

1

Language

Python

License

MIT

Last pushed

Dec 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JamesTwallin/GridSeis"

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