UAV-based phenotyping outperforms visual canopy wilting for evaluating soybean drought tolerance and yield retention under rainfed conditions

Authors: PAWAR, POPAT SHIVAJI - University Of Arkansas; WU, CHENGJUN - University Of Arkansas; HARRISON, DERRICK - University Of Arkansas; ROGERS, DANIEL - University Of Arkansas; Fallen, Benjamin; VIERIA, CAIO CANELLA - University Of Arkansas

Submitted to: Frontiers in Plant Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/19/2026
Publication Date: 6/2/2026
Citation: Pawar, P., Wu, C., Harrison, D., Rogers, D., Schapaugh, W., Fallen, B.D., Vieria, C. 2026. UAV-based phenotyping outperforms visual canopy wilting for evaluating soybean drought tolerance and yield retention under rainfed conditions. Frontiers in Plant Science. 17, 1835549. https://doi.org/10.3389/fpls.2026.1835549.
DOI: https://doi.org/10.3389/fpls.2026.1835549

Interpretive Summary: Drought is a major challenge for soybean producers, significantly limiting growth and yield. Identifying which soybean varieties can maintain high yields under dry conditions has been difficult, as traditional visual assessments of wilting are often subjective, capture only a small window of plant stress, and don't reliably correlate with yield at the end of the season. To overcome this limitation, this study employed a technique called high-throughput phenotyping, using drones (UAVs) equipped with multispectral cameras to assess soybean drought tolerance over three years. The data from drone-derived vegetation indices showed a consistent, positive correlation with final grain yield, while traditional visual scores had weak and inconsistent associations. This drone-based approach successfully separated the soybean varieties into two distinct groups based on their canopy health, and these groupings were consistent across all three years. Crucially, these groups also showed significant differences in yield, with the more resilient group yielding higher than the less resilient group under drought conditions. This breakthrough provides a powerful, reliable, and efficient tool for scientists and breeders, enabling them to quickly and accurately identify and develop new, drought-tolerant soybean germplasm. Ultimately, this innovation will help producers ensure more stable harvests under challenging growing conditions and increase the value of the crop.

Technical Abstract: Drought is the major abiotic stress limiting soybean growth and yield, yet accurately identifying genotypes that sustain yield under rainfed conditions remains a major bottleneck in soybean breeding. Canopy wilting scores are widely used as a proxy for evaluating plant responses to drought stress. However, most assessments rely on leaf-level visual observations that are inherently subjective and typically based on single time-point scores, providing only a snapshot of stress expression and failing to capture their relationship with yield retention under rainfed conditions. To address these limitations, this study employed Unmanned Aerial Vehicle (UAV)-based high-throughput phenotyping as a quantitative and yield-relevant approach to assess soybean drought tolerance. From 2023 to 2025, a total of 85 soybean genotypes developed by soybean breeding programs in Arkansas, Missouri, Kansas, and North Carolina, along with commercial checks, were evaluated under irrigated and rainfed conditions in Stuttgart, Arkansas. Visual canopy wilting scores were recorded at R4/R5, along with vegetation indices captured using UAV-based multispectral imagery. UAV-derived indices showed significant correlations with yield (r = 0.22 to 0.45, p<0.05) under rainfed conditions. In contrast, visual canopy wilting scores displayed weak and inconsistent associations with yield (r = -0.28 to 0.35, p<0.05), suggesting limited ability to capture yield retention under rainfed conditions. Unsupervised k-means clustering (n = 2) of UAV-derived vegetation indices separated genotypes into two distinct canopy response groups that were consistent across 2023 to 2025 rainfed seasons. Significant differences were observed among clusters for several vegetation indices (ARI, CIG, CIRE, GSAVI, GNDVI, GOSAVI, OSAVI, NDVI), indicating contrasting canopy stress responses. Under rainfed conditions, these UAV-defined clusters also differed for grain yield (2023: 1,925.6 vs 1,703.1 kg/ha; 2024: 1,849.9 vs 1,229.2 kg/ha; 2025: 2,056.7 vs 1,773.8 kg/ha), whereas visual wilting scores failed to distinguish yield-retaining genotypes. Overall, UAV-based high-throughput phenotyping offers a robust and yield-relevant alternative to visual wilting scores, supporting the development of drought-tolerant soybean germplasm and cultivars.