Prediction of cereal rye biomass accumulation in Wisconsin based on weather and agronomic management

Abstract Cereal rye ( Secale cereale L.) biomass accumulation is strongly influenced by weather conditions and management practices, making accurate biomass estimates critical for guiding farmers’ management decisions. In this study, we evaluated how weather (e.g., temperature and rainfall) and management practices (including planting and termination dates, nitrogen application, and field latitude) affect cereal rye cover crop biomass production in Wisconsin and compared the performance of different models for estimating cereal rye biomass. A comprehensive dataset was compiled from 135 site‐years of commercial fields and small‐plot research trials conducted in Wisconsin during the 2015–2016 through 2024–2025 growing seasons. Cumulative growing degree days (CGDDs) for the growing season and cumulative rainfall were calculated for the fall (from planting to December 31) and spring (from January 1 to the biomass sampling date) periods. Linear and nonlinear logistic least‐squares regression models were evaluated using the leave‐one‐out cross‐validation method. Our findings show a positive and significant correlation between biomass and the CGDDs of the growing season ( r = 0.71). A nonlinear logistic least‐squares regression model that included CGDDs of the season, fall rainfall, planting date, and latitude provided the best predictive performance, with the lowest error magnitude (RMSE = 1870.39 lb ac −1 ). Overall, this predictive model can be incorporated into cereal rye biomass forecasting platforms to provide support for practical agronomic guidance in Wisconsin cropping systems.