EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Vintage Physicochemical Differentiation and Machine-Learning Classification of North Macedonian Wine Varieties

Cveta Martinovska Bande, Milena Taseska-Gjorgjjevski, Natasha Stojkovikj, Aleksandra Stojanova Ilievska

Beverages · 16.11.2026 · 12 (11) · 136

DOI: 10.3390/beverages12110136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Beverages, online erschienen am 16.11.2026. Verfasst von Cveta Martinovska Bande und 3 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Goce Delcev University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Routine physicochemical measurements may support wine varietal discrimination and quality control. This study assessed 614 red and 410 white wine samples from North Macedonia collected between 2008 and 2023 and analysed using standard OIV methods. Varietal differences were evaluated using one-way analysis of variance and Tukey’s post hoc test. Principal component analysis (PCA) identified major sources of variation, and five supervised classifiers were compared using the original and PCA-transformed feature spaces. Significant varietal differences were observed in alcohol content, specific weight, total extract, sugar, sugar-free extract and total acidity. Three principal components explained approximately 71% of the variance in red wines, while four explained approximately 81% in white wines. The reported Optuna-selected Random Forest models achieved approximately 56% test accuracy for red wines and 49% for white wines using the original variables, compared with approximately 52% and 41%, respectively, after PCA transformation. These findings indicate that routine physicochemical parameters contain useful varietal information, but PCA may discard lower-variance information relevant to classification. The original feature space was therefore preferable for predictive performance, while PCA remained useful for exploratory analysis and visualisation. Overall, the results suggest partial grape-variety discrimination within the studied datasets.

Förderung

  • Goce Delcev University

Zitieren

APA

Bande, C. M., Taseska-Gjorgjjevski, M., Stojkovikj, N., & Ilievska, A. S. (2026). Multi-Vintage Physicochemical Differentiation and Machine-Learning Classification of North Macedonian Wine Varieties. Beverages, 12(11), 136. https://doi.org/10.3390/beverages12110136

Vancouver

Bande CM, Taseska-Gjorgjjevski M, Stojkovikj N, Ilievska AS. Multi-Vintage Physicochemical Differentiation and Machine-Learning Classification of North Macedonian Wine Varieties. Beverages. 2026;12(11):136. doi:10.3390/beverages12110136

BibTeX
@article{Bande2026,
  author = {Bande, Cveta Martinovska and Taseska-Gjorgjjevski, Milena and Stojkovikj, Natasha and Ilievska, Aleksandra Stojanova},
  title = {Multi-Vintage Physicochemical Differentiation and Machine-Learning Classification of North Macedonian Wine Varieties},
  journal = {Beverages},
  year = {2026},
  volume = {12},
  number = {11},
  pages = {136},
  doi = {10.3390/beverages12110136}
}
Kostenlos starten →