Using Juypter Notebooks

One of the most common ways to use an Open Data Cube is through interactively writing Python code within a Jupyter Notebook. This allows dynamically loading data, performing analysis and developing scientific algorithms.

Several GitHub repositories of example Open Data Cube notebooks are available, showing how to access data through ODC, along with example algorithms and visualisations:

Digital Earth Australia Notebooks

Digital Earth Australia Notebooks banner

Digital Earth Australia Notebooks hosts Jupyter Notebooks, Python scripts and workflows for analysing data from the Digital Earth Australia (DEA) instance of the Open Data Cube. This documentation provides a guide to the wide range of geospatial analyses that can be achieved using Open Data Cube and xarray. The repository contains the following key content:

  • Beginners guide: Introductory notebooks aimed at introducing Jupyter Notebooks and how to load, plot and interact with Open Data Cube data

  • Frequently used code: A recipe book of simple code examples demonstrating how to perform common geospatial analysis tasks using Open Data Cube

  • Real world examples: More complex workflows demonstrating how Open Data Cube can be used to address real-world challenges

Digital Earth Africa Notebooks

Digital Earth Africa Notebooks banner

Digital Earth Africa Notebooks provides a similarly comprehensive repository of Jupyter notebooks and code that allow users to use, interact and engage with data from the Digital Earth Africa instance of the Open Data Cube. This includes code examples based on USGS Landsat Collection 2, Level 2 and Copernicus Sentinel-2 Level 2A data that are available globally for use in Open Data Cube implementations.

DEA and DE Africa Tools code

Both Digital Earth Australia Notebooks and Digital Earth Africa Notebooks provide pip-installable Python modules containing useful tools for analysing Open Data Cube data, including functions for loading and plotting satellite imagery, calculating band indices, analysing spatial datasets, and machine learning. These tools can be accessed here: