EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Evaluating UAV Multispectral Imagery, Machine Learning and Image Analysis Techniques for Mapping Taro and Sweet Potato in a Smallholder Cropland in Swayimane, South Africa

Mishkah Abrahams, Mbulisi Sibanda, Timothy Dube, James Magidi, Richard Kunz, Vimbayi G. P. Chimonyo, Alistair D. Clulow, Tafadzwanashe Mabhaudhi

Geo: Geography and Environment · 2026-01 · 13 (1)

DOI: 10.1002/geo2.70078 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geo: Geography and Environment, online erschienen am 17.04.2026. Verfasst von Mishkah Abrahams und 7 weiteren Autor:innen. Die Arbeit nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Water Research Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate mapping of neglected and underutilised crop species (NUS) in complex smallholder fields is critical for enhancing food security, yet it remains a significant challenge due to landscape heterogeneity, spectral similarities between crops and the spatial complexity of strip intercropping systems. This study evaluates the efficacy of unmanned aerial vehicle (UAV) multispectral imagery for mapping taro and sweet potato, addressing the limitations of traditional pixel‐based image analysis (PBIA), which often fails in fragmented agricultural landscapes. We quantitatively compare the performance of PBIA and object‐based image analysis (OBIA) frameworks using a Gradient Tree Boost (GTB) classifier and determine the optimal input dataset by testing raw spectral bands, vegetation indices (VIs) and their combination. The findings demonstrate the clear superiority of the OBIA–GTB approach: using the combined dataset, OBIA–GTB achieved a mean overall accuracy of 95% ± 3.66%, kappa = 0.9419. In contrast, PBIA‐GTB yielded 83% ± 7.10% overall accuracy, with kappa = 0.8016. This study validates a robust, scalable workflow for NUS mapping, concluding that the integration of high‐resolution UAV data, OBIA and GTB provides a precise solution for agricultural monitoring in heterogeneous, intercropped smallholder systems.

Förderung

  • Water Research Commission

Zitieren

APA

Abrahams, M., Sibanda, M., Dube, T., Magidi, J., Kunz, R., Chimonyo, V. G. P., Clulow, A. D., & Mabhaudhi, T. (2026). Evaluating UAV Multispectral Imagery, Machine Learning and Image Analysis Techniques for Mapping Taro and Sweet Potato in a Smallholder Cropland in Swayimane, South Africa. Geo: Geography and Environment, 13(1). https://doi.org/10.1002/geo2.70078

Vancouver

Abrahams M, Sibanda M, Dube T, Magidi J, Kunz R, Chimonyo VGP, et al. Evaluating UAV Multispectral Imagery, Machine Learning and Image Analysis Techniques for Mapping Taro and Sweet Potato in a Smallholder Cropland in Swayimane, South Africa. Geo: Geography and Environment. 2026;13(1). doi:10.1002/geo2.70078

BibTeX
@article{Abrahams2026,
  author = {Abrahams, Mishkah and Sibanda, Mbulisi and Dube, Timothy and Magidi, James and Kunz, Richard and Chimonyo, Vimbayi G. P. and Clulow, Alistair D. and Mabhaudhi, Tafadzwanashe},
  title = {Evaluating UAV Multispectral Imagery, Machine Learning and Image Analysis Techniques for Mapping Taro and Sweet Potato in a Smallholder Cropland in Swayimane, South Africa},
  journal = {Geo: Geography and Environment},
  year = {2026},
  volume = {13},
  number = {1},
  doi = {10.1002/geo2.70078}
}
Kostenlos starten →