<img src="docs/main_logo.png" alt="main_logo" width="300"/>

pyeogpr

Python based machine learning library to use Earth Observation data to map biophysical traits using Gaussian Process Regression (GPR) models. Works with Google Earth Engine and openEO cloud back-ends.

Features

• Access to GEE/openEO is required. Works best with the Copernicus Data Space Ecosystem. Register here or here
• Hybrid retrieval methods were used: the Gaussian Process Regression retrieval algorithms were trained on biophysical trait specific radiative transfer model (RTM) simulations
• Uncertainties provided!
• Runs "in the cloud" with the GEE/openEO Python API. No local processing is needed.
• Resulting maps in .tiff or netCDF format

Get started

Refer to the Documentation for instructions and examples.

Satellites and biophysical variables

You can select from a list of trained variables developed for the following satellites:

Sentinel-2 L1C

Sentinel-2 L2A

Sentinel-3

Cite as / Contact

• Kovács, Dávid D., Emma De Clerck, and Jochem Verrelst. "PyEOGPR: A Python package for vegetation trait mapping with Gaussian Process Regression on Earth observation cloud platforms." Ecological Informatics 92, no. 10349 (2025): 7.

or

• Dávid D.Kovács. (2024). pyeogpr (zenodo). Zenodo. https://doi.org/10.5281/zenodo.13373838
• david.kovacs@tuwien.ac.at

Supported by the European Union (European Research Council, FLEXINEL, 101086622) project.

<a href="https://leoipl.uv.es/flexinel/"> <img src="https://github.com/user-attachments/assets/940bf34f-04d3-4fb0-9d68-8d6f19c14bab" alt="ERC Logo"> </a>