With low grain prices and tight margins, farmers may need to find new ways to stay in the black. The solution could be in their data, says Ryan Stien, go-to-market manager at John Deere.
Looking at harvest yield data and layering on additional information can help unlock a lot of insights, Stien says. “When you have that full dataset,” he notes, “you can really put that to use in making decisions versus just having a binder full of field data from every year.”
In-Season Insights
Don’t wait until after harvest to analyze your data.
Chris Krieg, who raises corn and soybeans with his dad, Ken, in northwest Iowa, combines Intelinair’s AgMRI imagery with tissue samples to identify potential in-season nutrient deficiencies. AgMRI imagery from one of their cornfields alerted them to an underperforming area due to a potential nutrient deficiency. Despite a visual inspection showing an apparently healthy crop, Krieg pulled tissue samples that showed a potassium deficiency.
“We have a drone, and we were able to apply foliar feed to just those spots,” Krieg says. “The next set of aerial images already showed improvement to where those spots were almost even with the rest of the field.”
To investigate trouble spots, Krieg also overlays the in-season aerial images with his yield maps. “It’s been effective in showing us those spots that you didn’t think were a problem,” he says.
Matthew Burt agrees that it’s key to find and remedy yield-limiting factors in-season and not wait solely on yield monitor data. The Marshalltown, Iowa, farmer started using AgMRI imaging in 2024 to fine-tune his fungicide timing. He was concerned about the potential for tar spot, and the aerial imaging technology allowed him to manage fungicide application scheduling.
“I felt good delaying application in fields where the reports showed that disease pressure was low,” Burt says. “That allowed me to delay application and extended a week more of protection from the fungicide on the back end.”
Identifying Trends
In-season insights also can help spot trends in the final data. Often, farmers spend valuable time manually compiling and analyzing data from different systems. Technology can help process that data and present it in a more user-friendly format, making it easier to identify trends.
John Deere Operations Center’s Field Analyzer and Work Analyzer tools help farmers gather and analyze data for current and past seasons, Stien says. Field Analyzer includes data layers that farmers can compare, whether agronomic or equipment. “When you have a nice, holistic dataset, yield is maybe your scorecard, and you can start to identify some of the key factors throughout the year and compare layer to layer in each field,” Stien says.
When anomalies present themselves, a holistic dataset allows comparing across years. “It’s not necessarily giving a prescribed solution, but it’s pointing you to the problem area where you should investigate,” Stien says.
Work Analyzer aids in decision-making by giving a total picture of all fields. “If I want to have an idea of how a specific variety performed on my farm, I can quickly see my yield by variety across all fields,” Stien explains.
Stien highlights the importance of capturing a full dataset throughout the season to maximize the tools efficiency. “If I didn’t have my varieties well-documented, I can’t go back in and use Work Analyzer to hone in on my varieties,” he says. “If I didn’t capture application data, I can’t go back and know exactly what was applied, and if there was a yield lift, and which field I should make a decision differently for next year.”
AI Analysis
When it comes to technology on his northeast Arkansas farm, Travis Senter always thinks about what’s next. Senter says the data collected, artificial intelligence (AI), and machine learning will improve his efficiency and ultimately the way things are done.
“ChatGPT gives you the ability at your fingertips to ask a question and get an answer without judgment,” Senter says. “There are thousands of things that go on in the field every day. But you can put in lots of information that can be processed quickly.”
Senter also has experimented with Apple’s Vision Pro, a new technology that combines digital content with physical space. He shares his experience of taking a picture of a weed with Vision Pro and feeding it to ChatGPT to identify. “From there,” Senter says, “I could ask, ‘What is this? What can I spray on this? How can I kill this?’ And it just feeds me all that information directly on my display.”
Senter sees technologies such as Vision Pro becoming more refined, and speculates on the ability to just look at a stressed field and make decisions quicker. “I believe we will see an influx in ways that we can increase our productivity and our decision-making in a faster timeline,” he says.
Opher Flohr, chief executive officer of Taranis, says in many cases detected issues may not be able to be fixed in-season. It’s about accumulating that medical chart or game tape of the entire crop season, he says, and leveraging field data with action taken throughout the season. That, he adds, gives a better picture and plan how to improve in the next season.
This past August, Taranis rolled out Ag Assistant, its new AI-powered crop analysis tool. Ag Assistant, Flohr explains, leverages AI to provide the farmer and agronomist with a season-end recommendation based on data such as stand counts, weeds, nutrient deficiencies, and pest damage. “Instead of the agronomist or the farmer having to analyze the data themselves, Ag Assistant automatically creates the expert agronomy recommendation that provides the AI’s recommended solution,” he explains. “We’re not only taking our own data but we’re using different data sources that we can tie in, in order to provide that expert recommendation.”
Flohr also stresses the importance of a robust dataset to maximize Ag Assistant insights. “The more data sources that we can incorporate in, the more powerful the outcome and recommendation AI will deliver for the farmer going into next season,” he says.