JohnNay/forecastVeg

A Machine Learning Approach to Forecasting Remotely Sensed Vegetation Health in Python

43
/ 100
Emerging

Automates MODIS satellite data ingestion and preprocessing, then trains gradient-boosted models (via H2O) on hundreds of millions of spatiotemporal pixel observations to predict Enhanced Vegetation Index across multi-year timescales. Uses spatially-stratified train/test splitting and nested hyperparameter search via Hyperopt to compare raw spectral bands against Level-3 MODIS products, requiring 100+ GB RAM and multi-threaded compute for production-scale training.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

51

Forks

20

Language

Python

License

Last pushed

Feb 22, 2021

Commits (30d)

0

Get this data via API

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

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