NRCan/geo-deep-learning
Deep learning applied to georeferenced datasets
This project helps geoscientists and remote sensing specialists train deep learning models using various Earth observation data sources like satellite imagery. It takes in multi-sensor geospatial datasets, often in WebDataset or CSV format, and outputs trained models for tasks such as identifying land cover, detecting objects, or performing regressions on geographic features. This tool is for researchers and practitioners who need to analyze complex spatial data.
193 stars.
Use this if you are working with Earth observation data from multiple sensors and need a flexible framework to train deep learning models for tasks like semantic segmentation or object detection.
Not ideal if you need a simple, out-of-the-box solution for common image processing tasks that don't involve complex geospatial or multi-sensor data.
Stars
193
Forks
66
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NRCan/geo-deep-learning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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
satellite-image-deep-learning/software
Software for working with satellite & aerial imagery ML datasets
rifqiharrys/sdb_gui
Python based GUI for Satellite Derived Bathymetry processing