Integrating Multi-Source and Multi-Temporal UAV Observations to Improve Wheat Yield Prediction Using Machine Learning
Plants · 28.04.2026 · 15 (9) · 1345
DOI: 10.3390/plants15091345 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 28.04.2026. Verfasst von Chen Chen und 10 weiteren Autor:innen. Beteiligte Einrichtung: Jiangsu Hilly Region Zhenjiang Agricultural Science Research Institute, Jurong 212400, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Special Fund for Independent Innovation of Agriculture Science and Technology in Jiangsu, Special Fund for Sciences Research in Zhenjiang Academy of Agricultural Sciences.
Abstract (Originalsprache)
Accurate yield estimation is vital for precision wheat management and breeding. Traditional methods based on single growth stages or single-source data cannot capture cumulative growth effects, limiting prediction accuracy. UAV remote sensing provides high-resolution, multi-source, and multi-temporal data, enabling improved non-destructive yield estimation. In this study, UAV-based multispectral and RGB imagery were collected at six key growth stages, and vegetation indices, texture, and color features were extracted to develop yield prediction models using RF, XGBoost, and KNN under single- and multi-temporal scenarios. The results showed that red-edge-based vegetation indices were highly sensitive to wheat yield and outperformed texture- and color-based features. Multi-feature fusion further improved prediction accuracy at key growth stages, particularly during booting and flowering (R2 = 0.53–0.67). Compared with single-temporal models, multi-temporal data fusion significantly enhanced yield estimation accuracy, achieving a maximum R2 of 0.72 by integrating data from the late-jointing, booting and flowering stages. Among the algorithms, XGBoost and KNN exhibited superior accuracy and stability across most growth stages. Overall, these results demonstrate that integrating UAV-based multi-source and multi-temporal remote sensing data effectively improves the accuracy and robustness of wheat yield estimation, providing valuable technical support for precision agriculture and phenotyping-assisted breeding.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Jiangsu Hilly Region Zhenjiang Agricultural Science Research Institute, Jurong 212400, China.
- College of Agriculture, Yangzhou University, Yangzhou 225009, China.
- Institute of Crop Sciences, Chinese Academy of Agricultural Sciences, Beijing 100081, China.
- Development Center of Science and Technology, Ministry of Agriculture and Rural Affairs, Beijing 100176, China.
ORCID-Profile: Xiuliang Jin
Förderung
- Special Fund for Independent Innovation of Agriculture Science and Technology in Jiangsu
- Special Fund for Sciences Research in Zhenjiang Academy of Agricultural Sciences
Zitieren
APA
Chen, C., Liu, J., Deng, Y., Guo, R., Yao, W., Yang, T., Zhang, W., Liu, T., Jin, X., Xiong, W., & Li, D. (2026). Integrating Multi-Source and Multi-Temporal UAV Observations to Improve Wheat Yield Prediction Using Machine Learning. Plants, 15(9), 1345. https://doi.org/10.3390/plants15091345
Vancouver
Chen C, Liu J, Deng Y, Guo R, Yao W, Yang T, et al. Integrating Multi-Source and Multi-Temporal UAV Observations to Improve Wheat Yield Prediction Using Machine Learning. Plants. 2026;15(9):1345. doi:10.3390/plants15091345
BibTeX
@article{Chen2026,
author = {Chen, Chen and Liu, Jiajun and Deng, Yao and Guo, Rui and Yao, Weicheng and Yang, Tianle and Zhang, Weijun and Liu, Tao and Jin, Xiuliang and Xiong, Wei and Li, Dongsheng},
title = {Integrating Multi-Source and Multi-Temporal UAV Observations to Improve Wheat Yield Prediction Using Machine Learning},
journal = {Plants},
year = {2026},
volume = {15},
number = {9},
pages = {1345},
doi = {10.3390/plants15091345}
}
EUVIMED