Skip to main content

Earth Genome

Earth Genome Datasets on Source​

Introducing Earth Genome​

Earth Genome focuses on data, science and people for the planet. Earth Genome was started to translate increasingly massive Earth data into useful, accessible, affordable analysis to enable more rational and sustainable use of natural resources. Their expertise is working with AI and Earth data. They build tools to create data, apply science, influence, guide and measure effective actions on the most pressing issues of our times.

Creating Global Earth Imagery and Embeddings​

One of Earth Genome's projects is the Earth Index application, a search tool for the environment, harnessing satellite imagery and machine learning to extract an area's "genetic signature." Earth Index helps to solve one of the greatest challenges for conservationists which is detecting environmental harms before it's too late. Earth Index enables users to easily find and act on damaging activities, like illegal mining or illegal farm expansion, in minutes not months.

Earth Index uses multiple large-scale datasets and a global, cloud-optimized satellite imagery composite, which is about 60 terabytes, and approximately 3.5 billion embeddings. Their pipelines have been highly optimized, resulting in substantial cost savings which are orders of magnitude cheaper than other methods, so they can responsibly steward resources to rapidly process new data and new models when available. These resources have potential to be widely useful. Since Earth Genome is committed to being a contributor to the Earth+AI community they were driven to openly share this processed data for use in new and unexpected ways.

Earth Genome Shares Through Source Cooperative​

Earth Genome believes that foundational planetary data should be open and accessible. That's why they chose to release these datasets on Source Cooperative, which they see as a platform dedicated to fostering collaboration around open data for public good. Source provides the infrastructure necessary to host and share these large-scale datasets, enabling the community to easily access, explore, and build upon them.

"Source has allowed us to open up all of this data to really anybody in the world… we would have been hesitant to do this without Source. We get people from local communities, indigenous groups, and others from almost every continent, who have reached out to us about this data."

— Tom (Hutch) Ingold, Earth Genome, CTO

Sharing Through Source: Key Benefits and Impact​

  • Global Accessibility: Source enables worldwide access to over 60 terabytes of processed satellite imagery that would otherwise be financially or technically out of reach for many organizations, particularly nonprofits and communities in developing regions.
  • Simplified Distribution: Source's catalog infrastructure and self-service model eliminated the need for Earth Genome to build and maintain their own hosting infrastructure and web interfaces, allowing them to focus resources on core mission activities.
  • Global Empowerment: The open availability has attracted inquiries from journalists, indigenous groups, local communities, and researchers across nearly every continent, with trillions of pixels processed and shared with the global community.

Looking Forward​

Earth Genome values Source cooperative model, which aligns with their commitment to open data and community-driven approaches. The organization appreciates being part of a collaborative ecosystem where data publishers work together to democratize access to valuable geospatial resources.

Find Out More About Earth Genome​

Learn more about Earth Genome: www.earthgenome.org

About Source Cooperative​

Source Cooperative is the data publishing utility for the web, allowing trusted organizations and individuals to publish data of any kind at any scale.

Find out more at Source Cooperative