Artificial intelligence and synthetic biology for integrated crop improvement

Conventional crop breeding has delivered substantial yield and quality gains but faces persistent constraints from long breeding cycles, limited genetic diversity, and increasing climate volatility. Artificial intelligence (AI) and synthetic biology (SynBio) are emerging as complementary technologies that can accelerate allele discovery, trait design, and deployment across major staples and under-researched crops. Machine learning, computer vision, and robotics support high-throughput phenotyping from unmanned aerial vehicle (UAV) imagery and mobile devices, while genomic prediction models that integrate multi-omics and climate data can improve selection accuracy for traits such as yield stability and stress tolerance. SynBio platforms enable precise genome editing, synthetic circuits, and metabolic pathway engineering, with applications ranging from biofortified rice to multiplex editing in maize and pangenome-informed breeding in orphan crops such as chickpea and pearl millet. Their convergence, often described as “Breeding 5.0,” supports AI-guided design–build–test–learn (DBTL) cycles that optimize ideotypes for resource efficiency, resilience, and nutrition while reducing reliance on agrochemical inputs. This narrative review outlines the evolution from classical to molecular breeding, synthesizes current AI–SynBio pipelines with illustrative case studies, and highlights persistent challenges in data quality, transformation efficiency, biosafety, regulatory harmonization, and equitable access. We conclude with priorities for inclusive innovation to ensure that climate-smart, nutritious crops benefit diverse agroecosystems responsibly.