Assessing the feasibility of up-scaling grapevine physiological trait estimation using multispectral UAV imagery
Abstract
Scalable grapevine physiological assessment is relevant for precision viticulture, but direct physiological measurements are labor-intensive and leaf-specific. This study evaluated whether a machine-learning framework developed for leaf-level hyperspectral measurements can be applied to UAV-derived multispectral imagery. In situ hyperspectral observations from 2024 and 2025 were combined and restricted to the visible and near-infrared (VNIR) range from 350 to 1000 nm to align with common UAV spectral coverage and assess multi-temporal performance and spectral resampling. UAV-derived multispectral observations from 2025 were analyzed for sunlit, shaded, and combined canopy extraction strategies. First-derivative preprocessing improved in situ performance, yielding best R2 values of 0.811 for net assimilation rate A , 0.792 for electron transport rate ETR, and 0.890 for effective quantum yield of photosystem II Φ PSII . Moderate spectral resampling caused limited performance losses for A and ETR. UAV-based models yielded R2 up to 0.765 for A , 0.768 for ETR, and 0.901 for Φ PSII . Shaded and combined observations improved A and ETR predictions relative to sunlit observations, whereas Φ PSII remained robust across extraction strategies. Plant-grouped validation supported generalization to unseen vines, whereas leave-one-date-out validation failed to demonstrate robust generalization to unseen measurement dates, highlighting temporal generalization as a key limitation of the UAV-based approach.
Related
- Mycorrhiza, water stress, and rootstock–scion combinations shape plant physiological traits and gene expression in grapevine
- Assessing the potential of deep learning to distinguish wild and domesticated grapevine pollen
- Assessing the suitability of a developed photogrammetric and multispectral method for detecting biostimulant effects on plants
- Physiology-informed UAV multispectral estimation of tobacco leaf nitrogen nutrition index for variable nitrogen management
- Assessing the feasibility of using long-read sequencing for population genomics in trees: case of the beech.
BibTeX
@article{lutz2026assessing,
title = {{Assessing the feasibility of up-scaling grapevine physiological trait estimation using multispectral UAV imagery}},
author = {Marco Lutz and Daniel Heßdörfer and Tobias Ullmann and Melanie Brandmeier},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-76877-z},
url = {https://www.nature.com/articles/s41598-026-76877-z},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Assessing the feasibility of up-scaling grapevine physiological trait estimation using multispectral UAV imagery
AU - Marco Lutz
AU - Daniel Heßdörfer
AU - Tobias Ullmann
AU - Melanie Brandmeier
PY - 2026
DA - 2026/10/20
JO - Scientific Reports
DO - 10.1038/s41598-026-76877-z
UR - https://www.nature.com/articles/s41598-026-76877-z
AB - Scalable grapevine physiological assessment is relevant for precision viticulture, but direct physiological measurements are labor-intensive and leaf-specific. This study evaluated whether a machine-learning framework developed for leaf-level hyperspectral measurements can be applied to UAV-derived multispectral imagery. In situ hyperspectral observations from 2024 and 2025 were combined and restricted to the visible and near-infrared (VNIR) range from 350 to 1000 nm to align with common UAV spectral coverage and assess multi-temporal performance and spectral resampling. UAV-derived multispectral observations from 2025 were analyzed for sunlit, shaded, and combined canopy extraction strategies. First-derivative preprocessing improved in situ performance, yielding best R^2 values of 0.811 for net assimilation rate A , 0.792 for electron transport rate ETR, and 0.890 for effective quantum yield of photosystem II Φ _PSII . Moderate spectral resampling caused limited performance losses for A and ETR. UAV-based models yielded R^2 up to 0.765 for A , 0.768 for ETR, and 0.901 for Φ _PSII . Shaded and combined observations improved A and ETR predictions relative to sunlit observations, whereas Φ _PSII remained robust across extraction strategies. Plant-grouped validation supported generalization to unseen vines, whereas leave-one-date-out validation failed to demonstrate robust generalization to unseen measurement dates, highlighting temporal generalization as a key limitation of the UAV-based approach.
SN - 2045-2322
ER -