Shawn P. Conley

Farmers are making decisions every year under weather variability, input cost fluctuations, and commodity price uncertainty. Traditional replicated field trials cannot recommend actionable knowledge at the field level accounting for all sources of variability and uncertainty. Decision support tools aim to fill the gap that traditional agricultural research cannot. Agroptimizer ( www.agroptimizer.com ), a machine learning cloud‐based decision support tool (DST) has a user‐friendly interface that users can easily input field and management information and was designed to identify optimum corn and soybean cropping systems, for maximum yield and profit, across the United States. The recommended management practices of the DST were compared against cropping systems that were generated by University of Wisconsin researchers (called typical hereafter) across Wisconsin between 2021 and 2023. Agroptimizer recommendations for corn resulted in similar yield and profit compared to typical. For soybean, Agroptimizer recommendations resulted in increased yield and similar profit compared to typical. There was no downside yield and profit risk difference between Agroptimizer‐based and typical cropping systems for both crops. Overall results showed that Agroptimizer successfully identified cropping systems that resulted in high yield and profit for both crops suggesting that in the absence of available expert recommendation, it can provide management practices with high yield and profit potential. Agroptimizer is being constantly updated and will be evaluated in additional locations across the United States in subsequent years.