There is a growing need to establish a breed reassessment system responding to tomato spotted wilt virus (TSWV) mutations. Conventional visual survey methods allow for assessing TSWV severity and disease incidence, while enzyme-linked Immunosorbent Assay (ELISA) data analysis can replace and validate visual surveys. This study proposes a non-destructive evaluation technique for TSWV using an open software platform based on image processing and machine learning. Many studies have evaluated resistance to the TSWV. However, as strains that destroy TSWV resistance emerge, an evaluation technique that can identify new genetic resources with resistance to the variants is needed. Evaluation techniques based on images and machine learning have the strength to respond quickly and accurately to the emergence of new variants. However, studies on resistance to viruses rely on empirical judgment based on visual surveys. The accuracy of the training model using Support Vector Machine (SVM), Logistic Regression (LR), and neural networks (NNs) was excellent, in the following order: NNs (0.86), LR (0.81), SVM (0.65). Meanwhile, the accuracy of the validation model was good, in the following order NN (0.84), LR (0.79), SVM (0.71). NNs’ prediction performance was verified through ELISA data analysis, showing a causal relationship between the two data sets with an R² of 0.86 with statistical significance. Imaging and NN-based TSWV resistance assessment technologies show significant potential as key tools in genetic resource reassessment systems that ensure a rapid and accurate response to the emergence of new TSWV strains.

Watermelon (Citrullus spp.) is an economically important crop globally, but it is susceptible to various diseases, including powdery mildew. Previous studies have identified genetic factors associated with powdery mildew resistance. However, further research using diverse genetic approaches is necessary to elucidate the underlying genetic mechanisms of this resistance. In this study, the germplasm collection comprising highly homozygous inbred lines was employed, which enabled the accumulation of consistent data and improved the reliability of the genome-wide association study (GWAS) findings. Our investigation identified two significant single-nucleotide polymorphisms (SNPs), pm2.1 and pm3.1, which were strongly associated with disease resistance. Moreover, several candidate genes were revealed within the linkage disequilibrium (LD) blocks surrounding the significant SNPs. In conclusion, the identification of significant SNPs and their additive effects, combined with the discovery of relevant candidate genes, expanded our understanding of the genetic basis of disease resistance and can pave the way for the development of more resilient watermelon cultivars through marker-assisted selection.

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.