Key Takeaways
- NC State University's AIRS (Automating Intelligence from Research Stations) project released a software suite in December 2025 enabling researchers to access weekly drone-collected imagery from two North Carolina research stations.
- An autonomous drone-in-a-box system, operated remotely from NC State's Raleigh campus under a rare FAA beyond-visual-line-of-sight waiver, is now being tested at the Sandhills Research Station.
- The project aims to expand standardized data collection to all 18 of North Carolina's agricultural research stations, supporting real-time decision-making for growers.
- Drone-based high-throughput phenotyping replaces manual field measurement, with weekly flights capturing growth data across hundreds of plants in a fraction of the time.
- AIRS is backed by the N.C. Plant Sciences Initiative, the USDA Agricultural Research Service, and technology partners including NVIDIA, AWS, Dell, and Lenovo.
Autonomous Drones Take Flight Over North Carolina Research Stations
NC State University has reached a new phase of agricultural data collection, with an autonomous drone emerging from a weatherproof docking station at the Sandhills Research Station in Jackson Spring, ascending to a pre-programmed altitude, and conducting field surveys entirely without an on-site pilot. The mission is initiated remotely from the university's Raleigh campus, representing a significant advance in the AIRS project — short for Automating Intelligence from Research Stations.
Launched three years ago, AIRS reached a milestone in December 2025 with the release of a software suite that gives researchers access to data and imagery collected weekly from drone-mounted cameras at the Sandhills station and the Central Crops Research Station in Clayton. The project is led by Chris Reberg-Horton, a professor of crop and soil sciences who directs the N.C. Plant Sciences Initiative's resilient agriculture platform, and draws on a multidisciplinary team from NC State and the USDA Agricultural Research Service.
“We can make intelligence out of that data in real time that then helps a grower make decisions. We want to be able to tell them, for example, ‘You have an outbreak of this disease, and it looks like it's strongest in these fields and in these particular parts of those fields,'” said Chris Reberg-Horton, project leader and professor at NC State.
High-Throughput Phenotyping: Replacing Manual Field Work
A central driver of the AIRS project is high-throughput phenotyping — measuring plant characteristics across large numbers of plots at speed. Traditionally, this means researchers walking miles of field rows, manually recording plant height, disease ratings, and other traits using handheld tools. Joe Gage, an assistant professor in NC State's Department of Crop and Soil Sciences, explains the scope of what drone-based collection changes.
“Any given sort of plant breeding program may be running acres and acres worth of plots that need to be measured. In the past we've done that all by hand, and it takes time for somebody to manually, physically measure a characteristic on every single plant. With drones, you just need the time to fly once a week,” said Joe Gage, assistant professor at NC State.
Beyond labor savings, regular drone flights build a longitudinal record of plant development that would be impractical to produce manually. Drones also capture data beyond human perception, including infrared reflectance that reveals plant stress before it becomes visible. This feeds directly into the kind of precision agriculture applications that depend on dense, reliable field data, and connects to the broader growth of AI-driven farm intelligence.
Building the Digital Backbone
Realizing the AIRS vision required more than aerial hardware. It demanded a digital infrastructure capable of moving terabytes of imagery from remote stations to campus computing systems. Research computing specialist Jevon Smith spent December weekends digging trenches for fiber optic cables at research stations to enable that capacity. A specialized app now transfers drone-collected files overnight to NC State's compute cluster, where they are processed into orthomosaics, three-dimensional point clouds, and heat maps that convey field conditions down to the meter.
The Sandhills Research Station served as the pilot site due to its existing connectivity. Working with NC State's Office of Information Technology, Smith and his team built the upload and transfer system that now automates the entire data pipeline from field to researcher.
NC State Autonomous System and the Road Ahead
The drone-in-a-box docking system being tested by Frank Bai of the Department of Biological and Agricultural Engineering represents the next step. Operating under a rare FAA waiver for beyond-visual-line-of-sight operations, Bai's team can deploy drones at the Sandhills station entirely from Raleigh. The system currently supports drought-tolerant soybean research with the capacity for hourly flights on selected days.
“We have the drone at the site, and some of us can just operate the drone from Raleigh. That will save us a lot of money, because everything's automatic,” said Frank Bai, researcher at NC State's Department of Biological and Agricultural Engineering.
Reberg-Horton's longer-term vision is to scale standardized, automated data collection across all 18 of North Carolina's agricultural research stations, incorporating ground-based robots and tractor-mounted imaging systems. The goal is to develop tools tailored directly for growers — helping address precision crop management and the labor shortages many farming operations face. NC State aims to position its research station network as a testbed for the future of data-driven and sustainable agriculture.
