ClarkCGA/cloud-gap-filling-td

Training data generation for cloud gap imputation fine-tuning of Prithvi Geospatial Foundation Model

27
/ 100
Experimental

This tool helps geospatial analysts and researchers create high-quality training datasets for models that 'see through' clouds in satellite imagery. It takes raw HLS (Harmonized Landsat Sentinel) satellite data and USDA Cropland Data Layer (CDL) information for the Continental United States. The output is a collection of processed image chips with precise cloud masks, ready for training advanced geospatial AI models.

No commits in the last 6 months.

Use this if you need to generate a robust and diverse training dataset of satellite imagery, specifically HLS data across the CONUS, for developing AI models capable of imputing missing data due to cloud cover.

Not ideal if you are looking for a pre-trained model to perform cloud gap imputation directly, or if your primary interest is in satellite data from regions outside the Continental United States.

geospatial-analysis remote-sensing satellite-imagery land-cover-mapping AI-training-data
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

9

Forks

3

Language

Jupyter Notebook

License

Last pushed

Oct 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ClarkCGA/cloud-gap-filling-td"

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