High throughput phenotyping in soybean breeding using RGB image vegetation indices based on drone

Abstract This study investigates the effectiveness of high-throughput phenotyping (HTP) using RGB images from unmanned aerial vehicles (UAVs) to assess vegetation indices (VIs) in different soybean pure lines. The VIs were accessed at various stages of crop development and correlated with agronomic performance traits. The field research was conducted in the experimental area of the Mato Grosso do Sul Foundation, Brazil, with 60 soybean pure lines. RGB images were captured at multiple stages of development (28, 37, 49, 70, 86, 105, 115, and 120 days after sowing). We used a linear mixed effects model, with restricted maximum likelihood (REML)/best linear unbiased prediction (BLUP) methods, to estimate variance components and genetic correlations, and to predict genotypic values. Significant genetic differences were identified among genotypes for all agronomic traits evaluated (p< 0.001), with high accuracy and heritability for plant height, maturity at R8, and 100-seed weight. There was a significant genotype $$\times$$ flight data interaction impact on VI expression, emphasizing the importance of timing data collection to enhance HTP with VIs in agronomic performance evaluation. In the early stages, the indices varied depending on the environment. On the other hand, the indices showed higher correlations with the traits of plant height and maturity at the R8 stage, at 105, 115, and 120 days after sowing. HTP with VIs based on RGB images from UAVs has proven to be more effective in the early and final stages of soybean development, providing essential information for the selection of superior genotypes. This study highlights the importance of the temporal approach in HTP, optimizing the selection of soybean genotypes and refining agricultural management strategies.