Prediction of late blight severity in a large panel of potato genotypes using low-altitude aerial images and machine learning methods

Potato ( Solanum tuberosum L.) is a staple crop crucial to global food security, yet its production is severely threatened by late blight (LB), caused by Phytophthora infestans , one of the most destructive plant diseases worldwide. Breeding programs for LB resistance have traditionally relied on labor-intensive and subjective visual assessments, which limit scalability and consistency, particularly in early-generation trials. Unmanned aerial vehicle (UAV)-based remote sensing combined with machine learning (ML) offers a promising alternative for objective, high-throughput disease phenotyping. This study evaluated the potential of this technology to estimate LB severity at the genotype level across two large potato trials in Peru comprising 2,745 breeding clones and 492 genebank accessions. We compared vegetation index–based approaches with a ML framework that integrates K-means clustering and Kernel Ridge Regression (KRR). While NDVI correlated strongly with visually assessed LB severity, particularly at advanced stages, the multispectral KRR approach outperformed linear NDVI models by capturing nonlinear relationships between spectral response and disease progression. Best linear unbiased estimates (BLUEs) of LB severity from both models were strongly and consistently related to the area under the disease progress curve (AUDPC), particularly in later UAV acquisitions. Selection coincidence with AUDPC-based rankings was substantially higher at intermediate to advanced stages of disease progression, indicating that a single UAV inspection at those stages captures enough phenotypic variation to distinguish genotypes. UAV-based multispectral phenotyping integrated with ML, therefore offers a practical, scalable alternative to the time-consuming visual assessments traditionally used in potato breeding programs.