Most of datasets that were either used to produce GEM results, or are results of GEM project, are made available publicly.
As our objective is also an uptake of GEM framework, we share example code on how to access data using example notebooks available at https://github.com/sentinel-hub/eo-learn-examples/.
The introductory notebook in particular gives an overview of the data used and produced within GEM framework. The examples, presented in Jupyter Notebooks, are structured according to data type:
- EO data: Earth Observation data (e.g., Sentinel and LandSat missions)
- EO derived data: data, derived from EO data (e.g., Global Land Cover)
- EO commercial data: commercial EO data (e.g., Maxar imagery)
- weather/climate data: weather data, accessible through meteoblue services
- GEM ML ready data-cubes: analysis/machine-learning ready datacubes, created within GEM project
- GEM datasets: various datasets/results/..., created within GEM project.
The GEM datasets facilitates easier navigation and clearer overview of data produced in various use-cases from GEM project, and is further structured into several notebooks.
Built-up areas use-case contains the following data:
- Google open buildings raster data over Africa
- Results of LightGBM regression built-up model
- Results of LightGBM categorical built-up model
- Results of several TFCN regression and classification built-up models
Each notebook will show how data collections, pertinent to GEM in general, or some of the GEM use-cases in particular, can be accessed with GEM processing framework - eo-learn. Some explanation about the collections is also given, so the notebooks represent a self-sufficient and concise documentation about the datasets.