Genotype × Environment Interaction Analysis in Plant Breeding: Integrating Contemporary Machine Learning Approaches

Genotype × environment (G × E) interaction is a central challenge in plant breeding, as differential genotype performance across environments complicates selection decisions and limits genetic gain. Traditional statistical models such as analysis of variance (ANOVA), stability parameters, and mixed models have long been used to dissect G × E interactions. However, the increasing availability of large-scale phenotypic, environmental, and genomic datasets necessitates more flexible and powerful analytical approaches. Recent advances in machine learning (ML) provide novel opportunities to model complex, nonlinear G × E patterns and improve prediction accuracy for genotype performance and stability. This review summarizes classical and modern G × E analysis methods, highlights emerging machine learning techniques, and discusses their applications, and limitations in plant breeding programs.