ClarkCGA/cloud-gap-filling-td
Training data generation for cloud gap imputation fine-tuning of Prithvi Geospatial Foundation Model
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.
Stars
9
Forks
3
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
satellite-image-deep-learning/techniques
Techniques for deep learning with satellite & aerial imagery
DPIRD-DMA/OmniCloudMask
OmniCloudMask is a Python library for fast, accurate cloud and cloud shadow segmentation in...
developmentseed/label-maker
Data Preparation for Satellite Machine Learning
NRCan/geo-deep-learning
Deep learning applied to georeferenced datasets
satellite-image-deep-learning/software
Software for working with satellite & aerial imagery ML datasets