AI helping advance FEWS research at NDSU

Artificial Intelligence (AI) has expanded into all realms of life – and will continue to do so – and that includes agricultural research conducted at North Dakota State University.

For NDSU researchers involved with Food, Energy and Water Security projects – NDSU Endowed Chair and Director of the Peltier Institute Xin “Rex” Sun, NDSU director of ag analytics Ana Heilman Morales, NDSU assistant professor of electrical and computer engineering Shuvashis Dey and NDSU associate professor of precision agriculture Ahmed Rabia – AI is already playing an essential role in their work.

Frank Casey, Associate Director the NDAES and leader of the FEWS Initiative stated, “This past year, I’ve had the privilege to experience firsthand the power of artificial intelligence in action, from riding in a Waymo self-driving to climbing into the cab of John Deere’s See & Spray self-propelled sprayer. Watching AI safely maneuver through people pushing strollers, cyclists weaving by, and pedestrians stepping off curbs, and then seeing that same precision technology applied in the field, was truly paradigm shifting. Furthermore, the billions of dollars now being invested into data centers right here in North Dakota, illustrate just how quickly AI accelerating. Agriculture generates enormous amounts of data, and AI now enables us to connect those data into meaningful relationships, helping us understand complex systems in ways that were impossible before. This will profoundly influence how we conserve resources, manage disease, and push yields, which are vital advances as global food demand continues to rise and natural resources remain limited.”

Rex Sun’s interest in AI began in 2007 when he was pursuing his graduate degree. He first used the tool to determine the quality of beef; soon, it expanded into agricultural robots and sensing research. Additional uses for Sun include using machine learning to identify weeds, detect diseases, and map soil properties.

“I’ve come to realize that AI isn’t a magic tool that works everywhere. It needs careful data preparation, special algorithms designed for each task and real-world testing to make sure it’s reliable,” Sun said. “In agriculture, where data is often messy and unpredictable, AI models need to be strong, easy to understand and based on the knowledge of experts in the field.”

NDSU’s FEWS research projects study how soil, crops, water, and energy interact. AI is used to identify patterns and support decision-making. This enables the processing of data from sensors, soil samples, and satellite or drone imagery in real-time, providing producers with fast and accurate recommendations.

For the FEWS research Sun is conducting, AI is proving to be a good fit. Sun’s team utilizes AI for soil health assessment, employing autonomous, uncrewed ground vehicles to classify soil salinity and organic matter levels. Computer models trained on field imagery help with identifying weeds and crops; these models allow researchers to differentiate between crop species and invasive weeds, such as Palmer amaranth and kochia. AI-powered image recognition determines symptoms of diseases with models deployed on edge devices for near real-time diagnosis.

“We’ve taken soil and crop monitoring to the next level by bringing AI into the mix,” Sun said. “In the past, collecting and analyzing samples took weeks, but now we can get real-time insights right in the field. Our models are super accurate, consistently predicting soil salinity and plant disease. This means our field trials can help us make better management decisions faster.”

For decades, many public breeding researchers at NDSU relied on pen and paper to record data obtained from the field. At the same time, private breeders had already begun using automation, cutting-edge analytics, and machine learning to accelerate genetic gain.

“Bridging this gap is not just about technology—it’s about equity, efficiency, and innovation. Empowering public breeding programs with modern analytics and digital infrastructure will level the playing field, enabling breeders everywhere to make faster, smarter, and more impactful decisions for global food security,” Heilman Morales said.

Heilman Morales’s team utilizes AI in AgSkySight, a software platform designed to streamline the process of drone image stitching and vegetation index calculations for agricultural research. AGSkySight turns drone images into detailed data for each field plot. AGSkySight converts UAV mosaics into plot-level data products using a custom YOLO detector enhanced with SAHI (Slicing Aided Hyper Inference). The YOLO model is trained on research-field layouts (ranges × rows, alleys, borders) to recognize plot boundaries even under variable lighting, dense canopy, or stitching artifacts.

Analyzing omics data is challenging due to its large and complex nature, which necessitates the use of advanced tools and expertise. There is a need for systems that combine traditional statistics with AI/ML to help plant breeding and biological research. PredictPro is a user-friendly software that facilitates working with complex genomics and phenomics data. It allows users, even without coding skills, to run genomic prediction models using standard statistical methods or AI/ML algorithms.

“AI/Machine Learning facilitates workflows and speeds up performance and tasks, also reduces cost as time management and by using prediction instead of actual plots in the field as physical experiments translate into cost savings and speeding up the breeding pipeline,” Heilman Morales said.

Dey’s background includes designing antennas, RFID sensors and other electromagnetic devices. When working with those sensors, Dey saw that many data was generated, but there was a need to translate the data into clear, concise information. It turns out that the same holds for the FEWS research project he is working on.

“I decided to bring AI into our FEWS project because the kinds of data we deal with in food, energy, and water systems are complex, dynamic, and often pretty noisy,” Dey said. “We’re collecting information from different types of sensors, things like soil moisture measurements, electromagnetic signals, environmental data streams, and these signals don’t always behave in neat, predictable ways. Traditional analysis methods can overlook subtle trends and often struggle to adapt when field conditions change. That’s where AI really adds value.”

An example of AI's influence on Dey’s research is in the area of soil moisture sensing. His team developed a low-cost, passive RF sensor that can be distributed throughout fields and paired with machine learning models to calibrate its readings against soil properties, such as bulk density and electrical conductivity.

“As a result, we achieved significantly more accurate soil moisture estimates, even under variable field conditions,” Dey said. “This advancement is highly valuable for applications like irrigation scheduling and drought monitoring.”

Dey said the use of AI has helped his team tackle problems that, at one time, were too complex or too time-consuming to address.

“AI has made our research faster, smarter, and more scalable, and it’s enabling applications that simply wouldn’t be feasible otherwise,” Dey said.

Rabia’s experience with AI has deep roots in precision agriculture applications, which include machine learning used for weed detection, crop monitoring, and data fusion from various sensors.

“I decided to incorporate AI into the FEWS research project because AI offers a scalable, data-driven pathway to address the interconnections among food, energy, and water systems,” Rabia said. “Agriculture generates vast and complex datasets, from soil and crop sensors to UAV imagery and field machinery, and AI provides the analytical power to extract actionable intelligence from these data streams.”

Rabia’s team is using AI to model images of robots to identify weeds and guide laser actuators for targeted, chemical-free weed removal.

“This integration demonstrates how AI can drive automation and sustainability simultaneously in field-scale operations,” Rabia said.

Rabia said AI-driven image analysis has increased early weed identification accuracy by more than 25 percent compared to manual assessments. AI models have revealed links between topography, drainage patterns and infestation levels. The near real-time processing of UAV and sensor data enables adaptive management decisions that optimize inputs and conserve resources, two crucial components of the FEWS mission.

“For FEWS, AI supports real-time monitoring, predictive modeling, and autonomous decision systems, aligning perfectly with the initiative’s goals of developing next-generation technologies that enhance resilience, efficiency, and sustainability in agricultural systems,” Rabia said.