Research HighlightsPlanning for the Future: Mapping Soybean Fields for Protein and Oil Quality
By Carol Brown
There is growing interest among farmers and those in the soybean market for increased protein and oil in the crop. Future markets may pay premium prices for higher quality grains, and Kansas State University farming systems professor Ignacio Ciampitti is working to ensure farmers will be ready.
Ciampitti leads a multi-year project, funded by the North Central Soybean Research Program, to help farmers predict the areas in their fields that can produce higher protein soybeans.
“The goal of the project is to develop prediction models that will help farmers to start thinking about segregating soybean quality before harvest and identifying field areas where they might have high or low protein,” says Ciampitti. “We’re already seeing some companies that are interested in this market and paying premiums for better quality.”
The project currently includes 10 states, with the intent to have all 13 NCSRP states involved. Ciampitti worked with soybean specialists in each state to secure participating farmers and fields. At harvest, the specialists sent seed and soil samples to Ciampitti’s lab in the agronomy department at Kansas State. His team retrieves the readily available satellite imagery of those fields to link with the seed samples obtained from farmers across the North Central region.
“Seed and soil sampling at farmer fields and satellite data from past growing seasons are used to create management zones within a field. A sampling protocol process was established to define sampling points within the fields to better quantify variations,” he explains. “Depending on the number of acres, we allocate different numbers of sampling points per field that represent the variability. We want to ensure everyone is sampling in the same location each time and the protocols are the same for the data collection across all participating famers. We then create interactive maps so the soybean specialists can locate those sampling points when they go into the field to collect the samples.”
The research team also conducted a farmer survey to gather agronomic data about the crop and the fields, which included seeding rates, soybean varieties, seed treatments, irrigation, yields and more. Ciampitti and his team are in the process of creating a database with the amassed information.
“We are using machine learning analysis with the data collected from the farmers and the specialists, and adding soil type, weather and satellite information,” he says. “We have built maps of field management zones that show variability — sections of the field that are high-yielding, to medium- to low-yielding.”
These maps will be shared with the individual farmers to help them visualize the overall soybean quality variability in their fields. As they harvest these fields, they can separate by zone based on soybean quality to ultimately get the best price for their crop.
In 2022, the team received samples from nearly 100 fields across the 10 states, which included more than 1,000 seed samples and 250 soil samples. For crop year 2023, it may seem like starting from the beginning as crop rotation means new fields need to be mapped. Ciampitti hopes the project will be funded for four years in order to gather data over two years for each field.
Ciampitti and the team are in the early stages of testing the prediction models at one month prior to harvest. He wants to move the timeline up to predict quality nearer to harvest time, which would better represent the true quality of the soybeans.
Ultimately, the research team hopes their work will improve farmer competitiveness.
“Imagine if we have the possibility of developing soybean quality maps in nearly real-time,” he remarks. “Farmers could position themselves and their soybeans in competitive markets around the world if they have the right data, right away, instead of several months later.”
Published: Jun 19, 2023
The materials on SRIN were funded with checkoff dollars from United Soybean Board and the North Central Soybean Research Program. To find checkoff funded research related to this research highlight or to see other checkoff research projects, please visit the National Soybean Checkoff Research Database.