Physiology-informed UAV multispectral estimation of tobacco leaf nitrogen nutrition index for variable nitrogen management
Abstract
IntroductionSpatial variability in crop nitrogen (N) status limits the effectiveness of uniform fertilization in tobacco, yet remotely sensed spectral signals cannot be directly translated into crop N demand. This study developed a physiology-informed unmanned aerial vehicle (UAV) multispectral framework linking leaf dry matter (LDM), leaf N concentration (LNC), the leaf nitrogen nutrition index (NNIleaf), and variable N management.MethodsField experiments involving seven N application rates (0–150 kg N ha−1) were conducted in Yunnan, China, during 2023–2024. A critical leaf-N relationship was established using ln(LDM) and LNC. Multispectral vegetation indices were screened using Pearson correlation analysis and recursive feature elimination. Partial least squares regression (PLSR), random forest (RF), and extreme gradient boosting (XGBoost) were compared for estimating ln(LDM) and LNC, from which NNIleaf was subsequently derived.ResultsThe four seasonal critical points obtained in 2023 were described by Nc,leaf = −3.156[ln(LDM)]2 + 32.800ln(LDM) − 25.20 (R2 = 0.992; RMSE = 0.978 mg g−1). XGBoost provided the best overall performance. In the independent 2024 validation, R² values for ln(LDM), LNC, and NNIleaf were 0.826, 0.783, and 0.832, respectively, with an NRMSE of 5.51% for NNIleaf. The fitted N-response relationship identified 82.5 kg N ha−1 as the NNIleaf-defined physiological N baseline (Nphys), corresponding to the lowest total N rate at which fitted NNIleaf reached 1. In a production-scale cross-year demonstration, the NNIleaf-based strategy recommended an average of 97.12 kg N ha−1 and was associated with slightly lower N input, 3.18% higher yield, and a 2.77-percentage-point reduction in yield coefficient of variation relative to conventional management.DiscussionThe framework provides a physiologically interpretable link between multispectral traits, leaf N sufficiency, and spatial N recommendations. Wider validation of the critical-N relationship and same-year fertilizer comparisons remain necessary.
Related
- Replacing EEG with peripheral physiological signals for driving behavior recognition: a physiology-informed multimodal approach
- Assessing the feasibility of up-scaling grapevine physiological trait estimation using multispectral UAV imagery
- Climate change and citrus fruit quality: links with plant physiology and mineral nutrition
- Physiology-Informed Blink Artefact Detection from Bilateral Frontal EEG Under Asymmetric Interference
- Long-Term Effects of Vineyard Floor Vegetation Management on Grapevine Physiology, Yield and Wine Color Attributes Under Mediterranean Conditions
BibTeX
@article{yang2026physiologyinformed,
title = {{Physiology-informed UAV multispectral estimation of tobacco leaf nitrogen nutrition index for variable nitrogen management}},
author = {Jizhong Yang and Chuixin Lou and Shaorong Yang and Wenbiao Wu and Lin Peng and Xiangqi Xu and Xiaohe Gu and Bangshun Liao and Baoyuan Zhang},
journal = {Frontiers in Plant Science},
year = {2026},
month = nov,
doi = {10.3389/fpls.2026.2010688},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.2010688},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Physiology-informed UAV multispectral estimation of tobacco leaf nitrogen nutrition index for variable nitrogen management
AU - Jizhong Yang
AU - Chuixin Lou
AU - Shaorong Yang
AU - Wenbiao Wu
AU - Lin Peng
AU - Xiangqi Xu
AU - Xiaohe Gu
AU - Bangshun Liao
AU - Baoyuan Zhang
PY - 2026
DA - 2026/11/06
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.2010688
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.2010688
AB - IntroductionSpatial variability in crop nitrogen (N) status limits the effectiveness of uniform fertilization in tobacco, yet remotely sensed spectral signals cannot be directly translated into crop N demand. This study developed a physiology-informed unmanned aerial vehicle (UAV) multispectral framework linking leaf dry matter (LDM), leaf N concentration (LNC), the leaf nitrogen nutrition index (NNIleaf), and variable N management.MethodsField experiments involving seven N application rates (0–150 kg N ha−1) were conducted in Yunnan, China, during 2023–2024. A critical leaf-N relationship was established using ln(LDM) and LNC. Multispectral vegetation indices were screened using Pearson correlation analysis and recursive feature elimination. Partial least squares regression (PLSR), random forest (RF), and extreme gradient boosting (XGBoost) were compared for estimating ln(LDM) and LNC, from which NNIleaf was subsequently derived.ResultsThe four seasonal critical points obtained in 2023 were described by Nc,leaf = −3.156[ln(LDM)]2 + 32.800ln(LDM) − 25.20 (R2 = 0.992; RMSE = 0.978 mg g−1). XGBoost provided the best overall performance. In the independent 2024 validation, R² values for ln(LDM), LNC, and NNIleaf were 0.826, 0.783, and 0.832, respectively, with an NRMSE of 5.51% for NNIleaf. The fitted N-response relationship identified 82.5 kg N ha−1 as the NNIleaf-defined physiological N baseline (Nphys), corresponding to the lowest total N rate at which fitted NNIleaf reached 1. In a production-scale cross-year demonstration, the NNIleaf-based strategy recommended an average of 97.12 kg N ha−1 and was associated with slightly lower N input, 3.18% higher yield, and a 2.77-percentage-point reduction in yield coefficient of variation relative to conventional management.DiscussionThe framework provides a physiologically interpretable link between multispectral traits, leaf N sufficiency, and spatial N recommendations. Wider validation of the critical-N relationship and same-year fertilizer comparisons remain necessary.
SN - 1664-462X
ER -