Breeding 5.0: Artificial intelligence (AI)-decoded germplasm for accelerated crop innovation.

Area of Science:

• Agricultural Science
• Plant Breeding
• Computational Biology

Background:

• Traditional crop breeding methods face limitations due to climate change, land degradation, and pest resistance.
• Global food security necessitates innovative approaches to enhance crop yield, stress tolerance, and nutritional value.

Purpose of the Study:

• Introduce the Breeding 5.0 framework, leveraging artificial intelligence (AI) and robotics for advanced crop improvement.
• Shift crop breeding from empirical selection to intelligent, data-driven systems for enhanced efficiency and outcomes.

Main Methods:

• AI-driven germplasm intelligence to understand genetic architecture, plasticity, regulatory logic, and environmental interactions.
• Four technical paradigms: multimodal data integration (genotype-phenotype), omni-simulated environments, peopleless data capture, and expert, explainable AI.
• Development of the 'breeding flywheel' concept for a self-reinforcing crop improvement cycle.

Main Results:

• AI enables predictive trait modeling, optimized parental selection, and targeted germplasm selection.
• Algorithmic conversion of germplasm data into actionable breeding insights.
• Acceleration of the entire crop development cycle from design to elite line creation.

Conclusions:

• Breeding 5.0 represents a paradigm shift in crop breeding, moving towards intelligent systems.
• The framework accelerates crop improvement, contributing to a sustainable food future.
• Continuous refinement through the 'breeding flywheel' ensures ongoing advancements in crop performance.