Identification of Early Stage Physiological Indicators for Summer Heat Resilience in Kimchi Cabbage (Brassica rapa L. ssp. pekinensis) via Integrated GWAS and Machine Learning

The production of Kimchi cabbage (Brassica rapa L. ssp. pekinensis) is increasingly threatened by concurrent heat and drought stress, which induce physiological disorders and severe heading failure. In this study, we implemented a dual-environment screening strategy to identify robust indicators of heat resilience in an F2 population. First, seedling-stage heat tolerance was evaluated in a controlled growth chamber using qualitative visual scoring (Scale 1–4) for shoot and root vigor. Second, the population was validated under summer field conditions in South Korea. Machine learning (ML) analysis revealed that the seedling-stage qualitative shoot-to-root (S/R) ratio was the most robust predictor of mature heat resilience, achieving a classification accuracy of 0.770 via SVM algorithms. The study also revealed a strong positive correlation (r = 0.71) between shoot apical meristem (SAM) wilting and localized calcium deficiency (tipburn). Individuals with severe SAM wilting were predominantly associated with severe tipburn and inner-leaf decay. Genome-wide association studies (GWAS) pinpointed the MIZU-KUSSEI 1-like (MIZ1-like) gene on Chromosome 2 as a primary candidate for S/R ratio regulation, potentially acting through the optimization of root hydrotropism. Our findings highlight that qualitative seedling-stage S/R ratio screening, integrated with ML models, serves as an efficient, breeder-friendly tool for early selection of climate-resilient B. rapa cultivars before field transplantation.