High-throughput unmanned aerial vehicle phenomics and machine learning enables accurate early single-plant biomass prediction in lettuce
Plant Phenome Journal, cilt.9, sa.1, 2026 (ESCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 9 Sayı: 1
- Basım Tarihi: 2026
- Doi Numarası: 10.1002/ppj2.70103
- Dergi Adı: Plant Phenome Journal
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, BIOSIS, Directory of Open Access Journals, Natural Science Collection (ProQuest), Biological Science Database (ProQuest)
- Akdeniz Üniversitesi Adresli: Evet
Özet
Lettuce (Lactuca sativa L.) exhibits pronounced genotype and environment-dependent growth variation, making early, non-destructive single-plant biomass prediction critical for breeding. However, harvest-based measurements fail to capture growth dynamics. In this study, we tested whether multi-temporal unmanned aerial vehicle (UAV) phenomics could accurately predict lettuce fresh weight at the single-plant level and how early reliable prediction was achievable under field conditions. Six UAV flights were conducted at 26, 34, 41, 48, 51, and 54 days after planting (DAP), from which single-plant structural and spectral traits including canopy PixelCount and 17 vegetation indices were extracted from high-resolution red, green, blue, and multispectral imagery. Temporal canopy development was characterized using generalized additive models (GAMs), and fresh weight was predicted using Ridge Regression, Least Absolute Shrinkage and Selection Operator, Elastic Net, and Random Forest algorithms within a stringent genotype-pair cross-validation framework (420 train–test splits), ensuring prediction of completely unseen genotypes. Canopy PixelCount emerged as the dominant predictor of biomass across all growth stages, showing consistently strong correlations from early development through harvest (e.g., peak r = 0.89 at 54 DAP). Spectral indices such as green normalized difference vegetation index exhibited promising but stage-dependent associations (e.g., peak r = 0.78 at 41 DAP). Biomass quartiles became clearly separable from mid-season onward, with strongest discrimination observed at DAP 48–54 (often p < 0.0001). GAMs captured nonlinear canopy expansion accurately (R2 = 0.84–0.87; root mean square error = 114.8–145.2 pixels), revealing distinct growth trajectories between low- and high-biomass plants. Importantly, meaningful biomass prediction was already achievable at the earliest flight (DAP 26; test r = 0.30–0.66) and improved consistently as additional flights were incorporated, reaching high accuracy when all six flights were used (r = 0.85–0.89). Ridge regression provided the most stable performance across genotypes, although alternative models occasionally showed slight early-stage advantages in specific genetic backgrounds. Overall, these results demonstrate that single-plant, multi-temporal UAV phenomics enables accurate early biomass prediction in lettuce, while the large-scale, temporally resolved single-plant dataset generated in this study provides a valuable resource for future phenomic research.