EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Early Crop Type Classification Based on Seasonal Spectral Features and Machine Learning Methods

Ainagul Alimagambetova, Moldir Yessenova, Assem Konyrkhanova, Ten Tatyana, Aliya Beissegul, Zhuldyz Tashenova, Kuanysh Kadirkulov, Aitimova Ulzada, Gulalem Mauina

Technologies · 10.04.2026 · 14 (4) · 221

DOI: 10.3390/technologies14040221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technologies, online erschienen am 10.04.2026. Verfasst von Ainagul Alimagambetova und 8 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Committee of the Ministry of Education and Science of the Republic of Kazakhstan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper explores the feasibility of early-season crop classification based on Sentinel-2-time series using the TimeSen2Crop dataset (≈1 million pixels, 16 crops). The aim of the study was to evaluate the spectral-phenological separability of crops during the season and compare the performance of classical tabular algorithms, deep sequence models, and a seasonally oriented hybrid stacking scheme. Based on multispectral observations, a feature set was formed from 9 optical channels and 13 vegetation indices for 30 dates. F-criteria were calculated, confirming a sharp increase in interclass separability during the active vegetative growth phase and substantiating three time series truncation scenarios (early, early + mid-season, and full season). Random Forest (macro-F1: 0.46/0.74/0.75) was used as the base tabular model. LSTM, BiLSTM, GRU, 1D-CNN, and Transformer were trained in parallel, with Transformer showing the best results among the deep architectures (0.42/0.68/0.78). The main contribution of the work is a hybrid multi-layer stacking scheme combining heterogeneous base algorithms and OOF meta-features, which provides the highest quality (0.51/0.83/0.86) in all scenarios. The obtained results confirm the effectiveness of phenology-oriented selection of time windows, informative indices, and hybrid ensemble learning for improving the accuracy of early-season crop monitoring.

Förderung

  • Science Committee of the Ministry of Education and Science of the Republic of Kazakhstan

Zitieren

APA

Alimagambetova, A., Yessenova, M., Konyrkhanova, A., Tatyana, T., Beissegul, A., Tashenova, Z., Kadirkulov, K., Ulzada, A., & Mauina, G. (2026). Early Crop Type Classification Based on Seasonal Spectral Features and Machine Learning Methods. Technologies, 14(4), 221. https://doi.org/10.3390/technologies14040221

Vancouver

Alimagambetova A, Yessenova M, Konyrkhanova A, Tatyana T, Beissegul A, Tashenova Z, et al. Early Crop Type Classification Based on Seasonal Spectral Features and Machine Learning Methods. Technologies. 2026;14(4):221. doi:10.3390/technologies14040221

BibTeX
@article{Alimagambetova2026,
  author = {Alimagambetova, Ainagul and Yessenova, Moldir and Konyrkhanova, Assem and Tatyana, Ten and Beissegul, Aliya and Tashenova, Zhuldyz and Kadirkulov, Kuanysh and Ulzada, Aitimova and Mauina, Gulalem},
  title = {Early Crop Type Classification Based on Seasonal Spectral Features and Machine Learning Methods},
  journal = {Technologies},
  year = {2026},
  volume = {14},
  number = {4},
  pages = {221},
  doi = {10.3390/technologies14040221}
}
Kostenlos starten →