Autoplay settings
Off On


Leveraging Data to Support Smallholder Farmers’ Climate Resilience Globally

Graphic displaying the analytics data chain supported through the ECAAS program
Tetra Tech is catalyzing a global data ecosystem to increase the availability of ground-truth training data to scale artificial intelligence and machine learning (AI/ML) applications for smallholder agriculture.

The Enabling Satellite-based Crop Analytics at Scale (ECAAS) Initiative is a multiphase project funded by the Bill & Melinda Gates Foundation to unlock the promise of satellite remote sensing for smallholder agriculture. Tetra Tech is using its Tetra Tech Delta technology enablement program to support innovation, community partnerships, and data-sharing infrastructure to better collect, process, and share high-quality georeferenced training data for ML models. The integration of field data with satellite-based data and predictive analytics will modernize and improve production for smallholder farming systems.

With the goals of accelerating innovation in ground-truthing and scaling dataset availability, the initiative’s primary objectives are to:

  1. Develop and test innovative strategies and methods for dramatically reducing the costs of collecting ground-truth data for further use within the data chain
  2. Identify, map, and promote standards for collecting and aggregating high-quality training data, driven by priority use case applications of end products
  3. Facilitate the scaling of training dataset creation and exchange through an improved data-sharing ecosystem
  4. Improve access to repositories of regularly updated ground-truth data and core insights layers (i.e., crop yields, acreage, and production) to enable scalable satellite-based analytics in emerging agricultural economies

Tetra Tech is supporting more than $2.5 million in technology investments and working to facilitate digital agricultural applications driven by remote sensing data and machine learning tools to optimize farm production and food security outcomes. For example, as part of our community-driven innovation agenda, we have:

  • Developed new high-quality training datasets for field boundary, crop type, and in some cases, yield in Kenya, Zambia, Ghana, and Rwanda
  • Leveraged drones and ML to lower the costs and increase the accuracy of data collection and labelling at scale
  • Used remote sensing to enhance smart farming advice, including through improved weather forecasting


  • Mapped and conducted Social Network Analysis on the smallholder crop analytics stakeholder ecosystem
  • Led a community-driven innovation agenda to advance relevant science and practice
  • Developed business case and model for potential future data repository and sharing architecture
We continue to seek organizations working in this space to help identify and enhance a robust data sharing ecosystem

Connect with us. Reach out to discuss getting involved in the ECAAS data sharing system.

Scroll to Top