Ol’ MacDonald never had a farm like this, AI-AI-O. On this farm they’ll have a drone, with a robot here and a robot there.
The 250-acre Grand Farm in Perry, Georgia, will sprout in 2025 – with crops seeded, cultivated, watered, monitored and harvested with the assistance of AI, robotics and predictive analytics.
“By bringing together our world-class researchers and the UGA Institute for Integrative Precision Agriculture, with Grand Farm’s ecosystem of innovation, we will revolutionize the way we feed and clothe the world’s population,” said Nick Place, dean and director of the College of Agricultural and Environmental Science at the University of Georgia, announcing earlier this year a collaborative effort with Grand Farm, an organization of growers, corporations, start-ups, educators, researchers, governmental officials and investors.
“The University of Georgia Grand Farm will be a hub for research, education and sustainable agriculture practices and we will harness the power of precision agriculture, robotics and data analytics to increase productivity, conserve resources and ensure food security for future generations,” Mr. Place said.
Through advancements in AI algorithms, sensors and data cloud storage, there has been rapid innovation across hundreds of fields, and now the technology is proving useful in actual fields, such as the one in Perry. According to UGA’s Institute for Integrative Precision Agriculture, chores that have been performed by humans for hundreds of years will now become the domain of robotics and automation.
“Combining these trends has led to a significant increase in robotics and automation research and solutions for more robust, resilient and profitable agriculture—from the mundane tasks of robotically moving pots in a nursery to the advent of automated tractors, unmanned aerial vehicles, robotic fruit harvesters, automated milking parlors and pest management. UGA researchers are developing a small, multi-purpose robotic platforms to use in peanuts, cotton, vegetables and other crops. These small rovers will be used in teams and can be scaled by their numbers to the size of operation and required product throughput. Other current research is focused on weed management solutions, cotton harvesting, planting and scouting operations. Encoders, inertial measurement units, GPS-enabled real-time kinetic positioners and stereo-cameras are the main sensors used for navigating rows of crops and providing data on crop yield, fruit location and abiotic/biotic plant stress.”
The Institute is applying AI to “better understand and dissect the main drivers of crop yield and quality that includes digital soil mapping, weather forecasting and envirotyping at both the within-field and regional scales. For that, geospatial crop performance data and management and genetics information are matched with publicly available soils and weather big data. These complex data sets are then used to train a suite of machine learning and AI algorithms including tree ensembles, neural and deep networks, time series prediction, Bayesian and mechanistic soil-plant-atmosphere models to untangle the main drivers of crop response.”
They will also apply something known as Variable Rate Application (VRA) and Variable Rate Irrigation (VRI), a sort of tailored-fit of application of fertilizer, lime, seed and water. Based on a grid analysis that measures crop and soil properties in different areas, because no field is the same across its entirety, VRA and VRI determine applications across the field, and dispense accordingly, through machinery systems.
Through a web of advanced sensors and other communication tools, beyond Wi-Fi or Bluetooth, drones, robots and automated guided vehicles will work together to maximize crop output and minimize lost resources.
For large farms, the cost savings could be in the millions of dollars, and for small or mid-size farms, a manpower multiplier. What effect AI and robotics will have on the industry remains to be seen, but the automated labor may be just what is needed. Farming in the U.S. continues to fall off, as younger generations who grew up on farms set their sights on different career paths, and farmers are getting older. And the trend towards consolidation of smaller and mid-sized farms continues. According to the U.S. Department of Agriculture, Economic Research Service, the number of farms in this country peaked in 1935, with 6.8 million farms. The decline was sharp through the 1970’s, and continued through 1982 at a much slower rate. The most recent survey revealed there were 1.89 million farms in 2023, down 7% from the 2.04 million in the 2017 Census of Agriculture. Acreage also fell, as there was 900 million acres of farmland in 2017, compared to 879 million acres in 2023.
Microsoft developed a software program, FarmBeats for Students, that teaches high-tech farming. According to the company, “Today’s farms are beginning to look a lot more like smart cities; digital signals connect people to each other, to the cloud, and to data. Growers use multiple sensors for a more complete view of their crops. Their insights drive decisions like turning on irrigation systems, indicating where fertilizer should be applied, and predicting crop yields based on weather patterns. By applying computer vision and artificial intelligence, growers are seeing their crops in new ways, which helps them with crop monitoring, discovering inefficiencies, and unlocking new insights to improve food production. The FarmBeats for Students Program brings these modern tools into the hands of today’s learners.”
