Integrating Artificial Intelligence and Biotechnology to Enhance Cold Stress Resilience in Legumes

Abstract

Cold stress severely limits legume productivity, threatening global food security, particularly in climate-vulnerable regions. This review synthesizes advances in understanding and enhancing cold tolerance in key legumes (chickpea, soybean, lentil, and cowpea), addressing three core questions: (1) molecular/physiological foundations of cold tolerance; (2) how emerging technologies accelerate stress dissection and breeding; and (3) integration strategies and deployment challenges. Legume cold tolerance involves conserved pathways (e.g., ICE-CBF-COR, Inducer of CBF Expression, C-repeat Binding Factor, Cold-Responsive genes) and species-specific mechanisms like soybean’s GmTCF1a-mediated pathway. Multi-omics have identified critical genes (e.g., CaDREB1E in chickpea, NFR5 in pea) underlying adaptive traits (membrane stabilization, osmolyte accumulation) that reduce yield losses by 30–50% in tolerant genotypes. Technologically, AI and high-throughput phenotyping achieve >95% accuracy in early cold detection (3–7 days pre-symptoms) via hyperspectral/thermal imaging; deep learning (e.g., CNN-LSTM hybrids) improves trait prediction by 23% over linear models. Genomic selection cuts breeding cycles by 30–50% (to 3–5 years) using GEBVs (Genomic estimated breeding values) from hundreds of thousands of SNPs (Single-nucleotide polymorphisms). Advanced sensors (LIG-based, LoRaWAN) enable real-time monitoring (±0.1 °C precision, <30 s response), supporting precision irrigation that saves 15–40% water while maintaining yields. Key barriers include multi-omics data standardization and cost constraints in resource-limited regions. Integrating molecular insights with AI-driven phenomics and multi-omics is revolutionizing cold-tolerance breeding, accelerating climate-resilient variety development, and offering a blueprint for sustainable agricultural adaptation.