Environmental clusters defining breeding zones for tropical irrigated rice in Brazil

Geographic and seasonal effects are important in driving selection decisions in rice breeding research. Adopting new strategies for characterizing environmental-phenotype associations is critical to understanding these effects, and the outcomes of their study could reflect the benefits of developing locally adapted cultivars. This study aimed to characterize Brazil's tropical irrigated rice (IR) environment, Latin America's largest rice production system. We integrated unsupervised (K-means clustering) and supervised (decision tree classifier) algorithms to identify environmental clusters (EC) based on historical yield data. The data set included 31 locations and 471 genotypes from 1982 to 2017. We used environmental features (EF), such as weather and geography, as input variables for our analysis, assuming the model as EC similar to f (EF). Results indicate that the tropical IR production region can be divided into four primary breeding zones, with temperature emerging as a significant factor in the study area. After employing a linear mixed model analysis, we observed that the current relationship between genetics (G), environmental variation (E), and their interaction (GxE) in Brazil's tropical IR has a 1:6:2 ratio. However, when introducing our data-driven model based on EC, we reduced this ratio to 1:5:1. Therefore, the selection for local adaptability across a large region became more reliable. Our approach successfully identified EC in Brazil's tropical production region of IR, providing valuable insights for defining breeding zones and identifying more productive and stable seed production fields. Machine learning links phenotypic and environmental features to cluster trialing locations for rice breeding.This approach also revealed the climatic causes of environmental quality for a group of genotypes or cultivars.As an alternative approach to reducing costs, the strategy benefits many stages of breeding and postbreeding.This approach facilitates postbreeding (cultivar recommendations and optimization of seed production sites).