DEVELOPMENT OF A SOYBEAN MATURITY PREDICTION MODEL FOR SOYBEAN GROWN IN AFRICAN ENVIRONMENTS

Abstract

AbstractTime-to-maturity (TTM) is an important trait in soybean breeding programs. However, soybean is a relatively new crop in Africa. As such, TTM information is not yet well defined as in other major producing areas. Multi Environment trials (MET) allow breeders to analyze crop performance across diverse conditions but also pose statistical challenges (e.g. unbalanced data). Modern statistical methods, e.g.. Generalized Additive Models (GAM), can flexibly smooth a range of responses while retaining observations that could be lost under other approaches. We leveraged 5 years of data from a MET breeding program in Africa to identify the best geographical and seasonal variables to explain site and genotypic differences in soybean TTM. Using soybean-cycle features (minimum temperature, daylength) along with trial geolocation (longitude, latitude), a GAM model predicted soybean TTM within ± 10 days of the average observed TTM [days post-planting]. Further, we found significant differences between cultivars (p<0.05) in TTM sensitivity to minimum temperature and daylength. Our results show promise to advance the design of maturity systems that enhance soybean planting and breeding decisions in Africa.