EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Temporal Dynamics of UAV Multispectral Vegetation Indices for Accurate Machine Learning-Based Wheat Yield Prediction

Krstan Kešelj, Zoran Stamenković, Marko Kostić, Vladimir Aćin, Aleksandar Ivezić, Mladen Ivanišević, Nenad Magazin

AgriEngineering · 16.02.2026 · 8 (2) · 71

DOI: 10.3390/agriengineering8020071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AgriEngineering, online erschienen am 16.02.2026. Verfasst von Krstan Kešelj und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate wheat yield prediction is essential for ensuring food security and sustainable resource management under the increasing challenges of climate change. This study investigates the integration of unmanned aerial vehicle (UAV)-based multispectral imaging and machine learning (ML) techniques to improve yield forecasting in European wheat cultivars. Field experiments were conducted on 400 sub-plots with varying NPK fertilization regimes and five wheat varieties, monitored across six phenological stages during the 2023 growing season in Vojvodina, Serbia. A DJI Phantom 4 Multispectral UAV collected high-resolution imagery, from which 65 vegetation indices were computed. Using PyCaret’s automated ML framework, 25 regression algorithms were evaluated for yield prediction. Ensemble models, particularly Random Forest, Extra Trees, Gradient Boosting, and LightGBM, consistently outperformed linear and kernel-based approaches. The highest prediction accuracy was achieved with the Random Forest Regressor during full flowering (BBCH 65–69), yielding an R2 of 0.952 and an RMSE of 0.44 t/ha. Results highlight the temporal dynamics of model performance, with optimal predictions occurring during reproductive stages. The findings confirm that UAV-derived multispectral data, coupled with ensemble machine learning, provide a non-invasive, accurate, and computationally efficient method for yield forecasting. This framework has significant potential for supporting precision agriculture, enabling real-time decision-making, and enhancing the resilience of wheat production systems.

Förderung

  • European Union

Zitieren

APA

Kešelj, K., Stamenković, Z., Kostić, M., Aćin, V., Ivezić, A., Ivanišević, M., & Magazin, N. (2026). Temporal Dynamics of UAV Multispectral Vegetation Indices for Accurate Machine Learning-Based Wheat Yield Prediction. AgriEngineering, 8(2), 71. https://doi.org/10.3390/agriengineering8020071

Vancouver

Kešelj K, Stamenković Z, Kostić M, Aćin V, Ivezić A, Ivanišević M, et al. Temporal Dynamics of UAV Multispectral Vegetation Indices for Accurate Machine Learning-Based Wheat Yield Prediction. AgriEngineering. 2026;8(2):71. doi:10.3390/agriengineering8020071

BibTeX
@article{Keelj2026,
  author = {Kešelj, Krstan and Stamenković, Zoran and Kostić, Marko and Aćin, Vladimir and Ivezić, Aleksandar and Ivanišević, Mladen and Magazin, Nenad},
  title = {Temporal Dynamics of UAV Multispectral Vegetation Indices for Accurate Machine Learning-Based Wheat Yield Prediction},
  journal = {AgriEngineering},
  year = {2026},
  volume = {8},
  number = {2},
  pages = {71},
  doi = {10.3390/agriengineering8020071}
}
Kostenlos starten →