Modelling Strategies in Plant Breeding

Plant breeding is moving beyond traditional methods to leverage modelling strategies that provide faster and more accurate predictions to improve agricultural productivity and crop quality. While traditional methods rely on long-term field trials, emerging digital agriculture applications and modelling strategies have gained importance to improve efficiency in areas such as genomic selection, phenotype prediction and environment-genotype interaction analysis. Machine learning algorithms enable a better understanding of complex agricultural systems in plant breeding by evaluating genetic and environmental data. Algorithms such as support vector machines (SVM), random forests (RF) and artificial neural networks (ANN) are widely used in the prediction of phenotypic traits and genotype-environment interactions. These methods contribute to sustainable agricultural production by enabling the optimal utilization of genetic potential and adaptation to environmental variability. This review highlights the importance of deep learning and other artificial intelligence-based techniques in modelling environmental stressors in plant breeding and predicting the response of genotypes to these conditions. Modelling strategies have the potential to make plant breeding processes more efficient and contribute to food security. In this context, the effective use of modelling strategies in plant breeding in the future will lead to significant advances in the field of agricultural biotechnology