AI breeder: Genomic predictions for crop breeding

This is the authors' abstract. We don't add key points for this paper.

The integration of Artificial Intelligence (AI) into crop breeding represents a paradigm shift toward data-driven agricultural practices, aiming to enhance the efficiency and precision of crop improvement. In this perspective, we critically evaluate the impact of genomic prediction models like SoyDNGP (Soybean Deep Neural Genomic Prediction) on crop breeding. We discuss their current applications, challenges, and future potential. Addressing existing obstacles such as optimizing parent selection, accurately predicting the combined effects of multiple traits and genes, advancing explainable deep learning, and incorporating environmental factors, we propose practical approaches to overcome these challenges. Our insights aim to unlock the full potential of AI in genomic prediction, contributing to a comprehensive understanding of AI’s role in agriculture. We advocate for future research efforts that harness AI to cultivate sustainable and equitable food systems.