Linux Foundation’s AgStack Project will build dataset of field boundaries

Image: fotokostic /iStock/Getty Images Plus/Getty Images

On Dec. 20, the Linux Foundation announced its AgStack Project, which will host an open-source code base, along with a fully automated, continuous computation engine that will maintain a global dataset of boundaries for agricultural fields. The AgStack Asset Registry dataset will aid food traceability, carbon tracking, crop production, and other field-level analytics.

This ‘registry’ is designed to continuously update using data from satellites and real field registrations that contain boundary information, which will train machine learning models to ascertain more boundaries, among other capabilities.

Agricultural datasets are rarely public information. By using computer science and artificial intelligence (AI), users can create global field boundaries as a digital open source for public use, which can help farmers, agricultural companies, and the public manage crop production, study management practices, assess levels of productivity, monitor the spread of pests and diseases and more.

The AgStack project seeks to enable all types of agricultural data and services by combining computing and AI expertise with a global network of partners in an open-source software system. All code is being contributed under an open-source license and will be governed by the AgStack community, within the Linux Foundation.