Soybean seed composition quality is receiving increased attention among farmers, agronomists and commodity traders. Higher nutritional content of U.S. soybeans can help in marketing efforts and increase the economic value of each bushel. In the past, measuring soybean protein and oil content required the collection of soybean seed samples and laboratory analyses.
Recent pilot projects in Iowa and Kansas were focused on calibrating an on-the-go protein NIR sensor to produce the first soybean quality maps in the USA. The NIR spectra were collected during the soybean harvest and then calibrated using soybean seed samples collected during the harvest to produce soybean quality maps.

1. Develop a multistate database to allow upscaling of soybean quality predictions to regional levels and benchmark agronomic practices, soybean genetics, management, and environmental conditions that can lead to large-scale improvements in soybean quality.
2. Communicate the economic value of soybean quality mapping to farmers and agronomists through an online interactive simulation tool, technical publications and social media.

Year 1 focus: Soybean quality data from on-farm quality surveys will be the main focus for this year. Coordinate, identify, and work with farmers to obtain seed quality samples. In-season data (aerial from plane and satellite imagery) will be correlated with final seed quality data. Within-field protein predictions will be explored between the field and remotely sensed quality data.
Year 2 focus: Coordinate, identify, and work with farmers to obtain seed quality samples. In-season data (aerial from plane and satellite imagery) will be correlated with final seed quality data. Within-field protein predictions will be explored between the field and remotely sensed quality data.
Year 3 focus: Coordinate, identify, and work with farmers to obtain seed quality samples. In-season data (aerial from plane and satellite imagery) will be correlated with final seed quality data. Within-field protein predictions will be explored between the field and remotely sensed quality data. Finalizing data gathering, creating a final database and the online simulation tool - focus on releasing this service to farmers and to start making field soybean quality predictions.

Updated March 28, 2022:
The team has formalized all the collaborators from multiple states (Ohio, Indiana, South Dakota, Missouri, Iowa, Michigan, Illinois, North Dakota, Nebraska, Iowa, and Kansas), including John Fulton, Shaun Casteel, Peter Kovacs, Greg Luce and John Lory, Scott Nelson, Mark Seamon and Mani Sing, Randy Pearson, David Kramar and Michael Ostlie, and Laila Puntel and Laura Thompson.

Two main goals were achieved from the field coordination, i) all collaborators already committed to contribute to the project and provide between 5-to-15 fields per state (with a target of at least 150 fields per year across the North Central region), and ii) an initial survey, a protocol for data collection has been developed to obtain field data related to management on seed quality.
From the soybean quality tool, the research team discussed new improvements, in addition to have several presentations on this topic during January and February 2022.
Here is the link to the field survey data collection: https://forms.gle/5wBfdj9ZhsoJYsbNA

View uploaded report

At the end of this project, the team expects to have the largest dataset on the within field variation soybean quality at farmer scale around the world, estimating a total close to 500 farmer fields across the US North Central Region. This project is important and timely since it will provide relevant information to growers related to potential capability to learn and segregate quality at the field level, with the ultimate outcome of improving overall profits from the current soybean farming systems.

Three years of farm data collection and a final year for deploying the database to finish the online tool for spatial characterization of soybean quality. Fall and Winter 2021-2022 will be utilized to identify potential farmers for this project.