Precision spraying prototype reduces herbicide use in turfgrass trials
Aug. 25, 2026
By John Lovett
University of Arkansas Division of Agriculture
Fast Facts
- Spot-spray technology adapted from row crops with simpler detection method
- System reduced herbicide volume by as much as 62 percent, with 90 percent accuracy
- Jogging stroller retrofitted as prototype turfgrass smart sprayer
(975 words)
Download PHOTOS of the researchers and the prototype
FAYETTEVILLE, Ark. — A three-wheeled jogging stroller might seem out of place in precision agriculture research, but it turned out to be the perfect platform for turfgrass science researchers with the Arkansas Agricultural Experiment Station.
Applying the same automated spot-spraying concept used with tractors in row crops, researchers developed a simplified push-cart version for turfgrass. The system showed it could reduce herbicide use on golf courses, athletic fields and sod farms.
For turf managers, herbicide reductions made possible with this sort of technology could translate into substantial savings, said Wendell Hutchens, an assistant professor of turfgrass science in the department of horticulture for the Arkansas Agricultural Experiment Station, the research arm of the University of Arkansas Division of Agriculture.
In field trials, the system reduced herbicide volume by up to 62 percent compared with a conventional broadcast application. It maintained at least 90 percent weed detection in three of four trials. The system also required less time to operate than hand-spot spraying weeds with a backpack sprayer.
“If you are managing a golf course and have 30 acres to treat with herbicide, reducing those 30 acres down to only 12 acres of application results in considerable cost and labor reductions, and it lessens the environmental impact,” Hutchens said.
The weed-spraying stroller prototype cost about $850 in parts, not including the $3 stroller found at a yard sale. It combines a camera, custom software, and electronically controlled spray nozzles to detect and then spot-spray green winter weeds amid the dormant, brown bermudagrass. Weed detection thresholds can be adjusted in real time on a touchscreen monitor.
“This was really about trying to make precision application cheap, easy and user-friendly,” Hutchens added. “You don’t need a data science degree to be able to operate this machine.”
The methods and findings were published this spring in Weed Technology by Hutchens and Sam Kreinberg, who completed his master’s degree in 2025 at the University of Arkansas and is now pursuing a doctorate at Virginia Tech.
A simple approach to a common problem
The project began in 2023 at a Division of Agriculture Turfgrass Field Day, when Jason Davis approached Hutchens to discuss the idea of adapting row crop technologies for turfgrass systems. Davis is an assistant professor in the department of crop, soil, and environmental sciences and a remote sensing and pesticide application specialist for the Division of Agriculture’s Cooperative Extension Service.
The idea came at an ideal time because Hutchens was working with Kreinberg to find a master’s degree project. Kreinberg’s bachelor’s degree in mathematics and his software development experience made him well-suited for the project, Hutchens said.
The researchers focused on a common winter management practice in bermudagrass. During dormancy, turf managers often spray nonselective herbicides such as glyphosate to control winter annual weeds. Because the weeds remain green while dormant bermudagrass turns brown, the contrast creates a natural target for computer vision.
Rather than relying on machine-learning models that require thousands of labeled images for training, the team developed a simpler system based on the dark green color index, or DGCI, a vegetation index developed by Division of Agriculture researchers in 2003.
The system processes 30 images per second from a camera mounted above the sprayer. When the number of green pixels exceeds a threshold indicating the presence of a weed, the software activates a spray nozzle.
“One challenge with machine-learning models is that it takes a long time to collect, process and label images,” Hutchens said. “Sam’s technology is very simple, user-friendly, and the detection threshold can be adjusted in real time.”
The project brought together expertise from several areas. Along with Kreinberg and Hutchens, Arkansas collaborators included Davis; Michael Richardson, a professor of turfgrass science in the department of horticulture; and John McCalla Jr., a horticulture research program associate who fabricated the hardware. Hannah Wright-Smith, an assistant professor and extension weed specialist with the University of Tennessee Institute of Agriculture, was also part of the study. All are co-authors of the study published in Weed Technology.
“I am truly fortunate to have had such a great team at the University of Arkansas to complete this project,” Kreinberg said. “I also think this is such a great example of what research can entail. The results from this study offer great potential for precision turfgrass management, and we used a former baby stroller to test our hypotheses!”
Platform adaptability
Although the prototype rides on a stroller, Hutchens said the same detection-and-control system could be installed on an ATV, a mower or a larger commercial sprayer.
“The software really carries the weight in this technology,” he said. “You can retrofit and customize the hardware to whichever system you want to attach it to.”
With the current camera and image-processing system, the prototype was limited to about 1.5 mph. However, Hutchens said that upgrading those components could allow it to operate at higher speeds.
Looking ahead
The researchers view the prototype as a proof of concept rather than a finished commercial product.
The study identified several opportunities for improvement, including refinements to camera performance, computing power and spray coverage. The team also believes the technology could eventually be adapted for turfgrass applications beyond winter weed control.
“Starting with the baseline of winter weed control in dormant bermudagrass was a proof-of-concept that demonstrated this technology is effective and can be improved upon in the future,” Hutchens said.
Parker Cole, associate director of the Division of Agriculture’s Technology Commercialization Office, said he is exploring opportunities to license the software technology for further development and potential commercial use.
The Arkansas Agricultural Experiment Station and the University of Tennessee Institute of Agriculture are part of a system of agricultural research centers at 1862 and 1890 land-grant universities in the southern U.S., where scientists collaborate to conduct research and outreach focused on preserving the region’s natural resources and enhancing food production for a growing global population.
To learn more about ag and food research in Arkansas, visit aaes.uada.edu. Follow the Arkansas Agricultural Experiment Station on LinkedIn and sign up for our monthly newsletter, the Arkansas Agricultural Research Report. To learn more about the Division of Agriculture, visit uada.edu. To learn about extension programs in Arkansas, contact your local Cooperative Extension Service agent or visit uaex.uada.edu.
About the UADA Technology Commercialization Office
The Technology Commercialization Office (TCO) commercializes world-class University of Arkansas Division of Agriculture research to support a lasting knowledge-based economy to benefit Arkansas and the world. We help faculty and research scientists identify, protect, and commercialize intellectual property developed from their research or other university-supported activities. To contact the TCO, please email agritco@uada.edu.
About the Division of Agriculture
The University of Arkansas Division of Agriculture’s mission is to strengthen agriculture, communities, and families by connecting trusted research to the adoption of best practices. Through the Agricultural Experiment Station and the Cooperative Extension Service, the Division of Agriculture conducts research and extension work within the nation’s historic land grant education system.
The Division of Agriculture is one of 22 entities within the University of Arkansas System. It has offices in all 75 counties in Arkansas and faculty on three system campuses.
Pursuant to 7 CFR § 15.3, the University of Arkansas Division of Agriculture offers all its Extension and Research programs and services (including employment) without regard to race, color, sex, national origin, religion, age, disability, marital or veteran status, genetic information, sexual preference, pregnancy or any other legally protected status, and is an equal opportunity institution.
# # #
Media Contact:
John Lovett
U of A Division of Agriculture
Arkansas Agricultural Experiment Station
(479) 763-5929
jlovett@uada.edu