EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sorghum yield prediction using UAV multispectral imaging and stacking ensemble learning in arid regions

Linqiang Deng, Yaoyu Li, Xifeng Liu, Zhimin Zhang, Juanjuan Mu, Shujie Jia, Yuqiao Yan, Wuping Zhang

Frontiers in Plant Science · 09.10.2025 · 16

DOI: 10.3389/fpls.2025.1636015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 09.10.2025. Verfasst von Linqiang Deng und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Software, Shanxi Agricultural University, Jinzhong, China. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Frequent droughts and climate fluctuations pose significant challenges to stabilizing and increasing the yields of drought-tolerant crops like sorghum. Accurate, detailed, and spatially explicit yield predictions are essential for precision irrigation, variable fertilization, and food security assessment.

Methods

This study was conducted in the Lifang dryland experimental area in Jinzhong, Shanxi Province, using a sorghum planting experiment. Multispectral imagery and meteorological data were collected simultaneously using a DJI Mavic 3M UAV during key growth stages (seedling emergence, jointing, flowering, and maturity). A “spectral-meteorological-spatial” three-dimensional prediction framework was developed using eight machine learning algorithms. SHAP values and Partial Dependency Plots were used to assess variable importance.

Results

Ensemble learning algorithms performed best, with the Gradient Boosting model achieving an R 2 of 0.9491 and Random Forest reaching 0.9070. SHAP analysis revealed that DVI and NDGI were the most important predictors. The jointing stage contributed most to prediction accuracy (R 2 = 0.9454), followed by maturity (R² = 0.9215) and flowering (R 2 = 0.9075). Yield spatial distribution ranged from 4,291 to 4,965 kg haR -1 , with a global Moran’s I index of 0.5552 indicating moderate positive spatial autocorrelation.

Discussion

Integrating UAV multispectral data with machine learning methods enables efficient sorghum yield prediction, with the jointing stage identified as the optimal monitoring period. This study provides crucial technical support for precision planting and efficient sorghum management in arid regions.

Schlagwörter

Stichwörter der Autor:innen

UAV multispectral imagingmachine learningsorghum yieldspatial autocorrelationvegetation indices

Autor:innen und Institutionen

  • College of Software, Shanxi Agricultural University, Jinzhong, China.
  • College of Agricultural Engineering, Shanxi Agricultural University, Jinzhong, China.

Zitieren

APA

Deng, L., Li, Y., Liu, X., Zhang, Z., Mu, J., Jia, S., Yan, Y., & Zhang, W. (2025). Sorghum yield prediction using UAV multispectral imaging and stacking ensemble learning in arid regions. Frontiers in Plant Science, 16. https://doi.org/10.3389/fpls.2025.1636015

Vancouver

Deng L, Li Y, Liu X, Zhang Z, Mu J, Jia S, et al. Sorghum yield prediction using UAV multispectral imaging and stacking ensemble learning in arid regions. Frontiers in Plant Science. 2025;16. doi:10.3389/fpls.2025.1636015

BibTeX
@article{Deng2025,
  author = {Deng, Linqiang and Li, Yaoyu and Liu, Xifeng and Zhang, Zhimin and Mu, Juanjuan and Jia, Shujie and Yan, Yuqiao and Zhang, Wuping},
  title = {Sorghum yield prediction using UAV multispectral imaging and stacking ensemble learning in arid regions},
  journal = {Frontiers in Plant Science},
  year = {2025},
  volume = {16},
  doi = {10.3389/fpls.2025.1636015}
}
Kostenlos starten →