By Amanda Kerr
Early in their careers, Chris Reberg-Horton, a professor in the Department of Crop and Soil Sciences at NC State University, and Steven Mirsky, director of digital agriculture for the U.S Department of Agriculture’s Agricultural Research Service, became frustrated by how hard it was to turn research on crop and soil management into something more tangible for farmers and growers. They turned to technology for help.
Two decades and numerous computer vision projects later, the pair and their teams launched the Ag Image Repository (AgIR) in 2025. Powered in conjunction with artificial intelligence, AgIR is a growing collection of 1.5 million high-quality photographs of plants and associated data collected at different stages of growth. They envision the repository as the building blocks for a variety of digital agriculture tools.
“The idea for us was how can we create a public open-access resource of high quality, curated images that are annotated that anybody can use to build models and their own programs,” Reberg-Horton, director of the N.C. Plant Sciences Initiative’s Resilient Agricultural Systems Platform, told attendees at the 2026 AI in Agriculture Conference in Raleigh.
The NC State-hosted conference, March 31-April 2, brought together more than 460 academics, students, researchers, extension professionals and industry leaders from across the country to explore how AI is reshaping the future of agriculture.
Source : ncsu.edu