Classification of Russian Wines by Geographical Origin Using the Random Forest Method Based on Isotopic Ratios and Elemental Profile

Abstract. Due to the marked increase in consumer interest in wines with a protected geographical indication PGI and a protected designation of origin PDO, the development of reliable methods for confirming their geographical origin is becoming particularly relevant. Despite the widespread use of complex isotope ratio analysis, elemental profile, and machine learning methods in world practice, there are no scientifically sound classification models for Russian wines that take into account the characteristics of the country's main grape-growing areas. 

Purpose. To establish the possibility of classifying samples of domestic wines by their geographical origin based on a comprehensive analysis of the isotopic ratios of carbon, oxygen and hydrogen of ethanol and the elemental profile using machine learning methods. 

Materials and Methods. 63 samples of wines produced in the main wine-growing areas of Russia were selected. Of these, 20 samples are from the Krasnodar Territory, 32 samples from the Crimea, 7 samples from Dagestan, 4 samples from the Don Valley. The isotopic ratios δ13C, δ18O, and δD of the isolated ethanol were measured in these samples, as well as 71 mass concentrations of macro-, microelements, and rare earth metals. The Random Forest model was used in the study, precision, recall, and f1-score were used as metrics, and stratified k-fold cross-validation with 100 repetitions was used to obtain confidence intervals for metrics. 

Results. After training and validating the model, its average accuracy was 0.92 for Dagestan, 0.99 for the Don Valley, 0.82 for the Krasnodar Territory and 0.90 for the Crimea. The most important parameters for the model were the isotope ratios of the elements in the composition of ethanol molecules, as well as the mass concentrations of Li, B, Cs, Sr, W, Ni, and Sn. Among rare earth metals, the concentrations of Dy, Lu, Yb, Tm, Ho, Y, and La were the most important for the model. 

Conclusion. The results obtained show the prospects of applying machine learning methods to the tasks of authenticating domestic wine products. This model is the basis for classifying wines produced in more limited geographical areas, including wine-growing areas and specific terroirs. 

1. Klimenko, L.V., & Krivosheeva Mediantseva, D.D. (2024). Viticulture in Southern Russia: development barriers and positioning strategies. Upravlenets, 15(1), 97–111. (In Russ.). https://doi.org/10.29141/2218-5003-2024-15-1-7

2. Sviridov, D.A., Ganin, M.Yu., Il'in, A.A., & Shmigelskya, N.A. (2023). Study of the features of the elemental profile of wines of the Bakhchisarai region of the Republic of Crimea. Food Industry, 8, 71-77. (In Russ.). https://doi.org/10.52653/PPI.2023.8.8.013

3. Adami, L., Dutra, S.V., & Marcon, A.R. (2013). Characterization of wines according the geographical origin by analysis of isotopes and minerals and the influence of harvest on the isotope values. Food Chemistry, 141, 2148–2153. https://doi.org/10.1016/j.foodchem.2013.04.106

4. Azcarate, S.M., Martinez, L.D., Savio, M., Camiña, J.M., & Gil, R.A. (2015). Classification of monovarietal Argentinean white wines by their elemental profile. Food Control, 68–274. https://doi.org/10.1016/j.foodcont.2015.04.025

5. Camin, F., Bontempo, L., Perini, M., Tonon, A., Breas, O., Guillou, C., Moreno Rojas, J.M., & Gagliano, G. (2013). Control of wine vinegar authenticity through δ¹⁸O analysis. Food Control, 29(1), 107–111. https://doi.org/10.1016/j.foodcont.2012.05.055

6. Camin, F., Dordevic, N., Wehrens, R., Neteler, M., Delucchi, L., Postma, G., & Buydens, L. (2015). Climatic and geographical dependence of the H, C and O stable isotope ratios of Italian wine. Analytica Chimica Acta, 853(1), 384–390. https://doi.org/10.1016/j.aca.2014.09.049

7. Coetzee, P.P., Van Jaarsveld, F.P., & Vanhaecke, F. (2014). Intraregional classification of wine via ICP MS elemental fingerprinting. Food Chemistry, 164, 485–492. https://doi.org/10.1016/j.foodchem.2014.05.027

8. Dordevic, N., Wehrens, R., Postma, G.J., Buydens, L.M.C., & Camin, F. (2012). Statistical methods for improving verification of claims of origin for Italian wines based on stable isotope ratios. Analytica Chimica Acta, 757, 19–25. https://doi.org/10.1016/j.aca.2012.10.046

9. Dutra, S.V., Adami, L., Marcon, A.R., Carnieli, G.J., Roani, C.A., Spinelli, F.R., Leonardelli, S., & Vanderlinde, R. (2013). Characterization of wines according the geographical origin by analysis of isotopes and minerals and the influence of harvest on the isotope values. Food Chemistry, 141(3), 2148–2153. https://doi.org/10.1016/j.foodchem.2013.04.106

10. Dutra, S.V., Adami, L., Marcon, A.R., Carnieli, G.J., Roani, C.A., Spinelli, F.R., & Leonardelli, S. (2013). Characterization of wines according the geographical origin by analysis of isotopes and minerals and the influence of harvest on the isotope values. Food Chemistry, 141(3), 2148–2153. https://doi.org/10.1016/j.foodchem.2013.04.106

11. Fan, S., Zhong, Q., Gao, H., Wang, D., Li, G., & Huang, Z. (2018). Elemental profile and oxygen isotope ratio (δ¹⁸O) for verifying the geographical origin of Chinese wines. Journal of Food and Drug Analysis, 26(3), 1033–1044. https://doi.org/10.1016/j.jfda.2017.12.009

12. Farquhar, G.D., von Caemmerer, S., & Berry, J.A. (1980). A biochemical model of photosynthetic CO₂ assimilation in leaves of C₃ species. Planta, 149, 78–90. https://doi.org/10.1007/BF00386231

13. Frías, S., Pérez Trujillo, J., Peña, E., & Conde, E. (2001). Classification and differentiation of bottled sweet wines of Canary Islands (Spain) by their metallic content. European Food Research and Technology, 213, 145–149. https://doi.org/10.1007/s002170100344

14. Geana, I., Iordache, A., Ionete, R., Marinescu, A., Ranca, A., & Culea, M. (2013). Geographical origin identification of Romanian wines by ICP MS elemental analysis. Food Chemistry, 138(2–3), 1125–1134. https://doi.org/10.1016/j.foodchem.2012.11.104

15. Gonzalvez, A., Llorens, A., Cervera, M.L., Armenta, S., & De la Guardia, M. (2009). Elemental fingerprint of wines from the protected designation of origin Valencia. Food Chemistry, 112, 26–34. https://doi.org/10.1016/j.foodchem.2008.05.043

16. Hardie, W., & Considine, J. (1976). Response of grapes to water deficit stress in particular stages of development. American Journal of Enology and Viticulture, 27, 55–61. https://doi.org/10.5344/ajev.1976.27.2.55

17. Mar Castiñeira Gómez del, M., Feldmann, I., Jakubowski, N., & Andersson, J.T. (2004). Classification of German white wines with certified brand of origin by multielement quantitation and pattern recognition techniques. Journal of Agricultural and Food Chemistry, 52(9), 2962–2974. https://doi.org/10.1021/jf035120f

18. Pepi, S., & Vaccaro, C. (2018). Geochemical fingerprints of “Prosecco” wine based on major and trace elements. Environmental Geochemistry and Health, 40(2), 833–847. https://doi.org/10.1007/s10653-017-0029-0

19. Scheidegger, Y., Saurer, M., Bahn, M., & Siegwolf, R. (2000). Linking stable oxygen and carbon isotopes with stomatal conductance and photosynthetic capacity: A conceptual model. Oecologia, 125(3), 350–357. https://doi.org/10.1007/s004420000466

20. Shimizu, H., Akamatsu, F., Kamada, A., Koyama, K., Iwashita, K., & Goto Yamamoto, N. (2020). Variation in the mineral composition of wine produced using different winemaking techniques. Journal of Bioscience and Bioengineering, 130(2), 166–172. https://doi.org/10.1016/j.jbiosc.2020.03.012

21. Soler, F., Garcia Rodriguez, G., & Perez Lopez, M. (2011). Characterization of “Ribera del Guadiana” and “Méntrida” Spanish red wines by chemometric techniques based on their mineral contents. Journal of Food and Nutrition Research, 50(1), 41–49.

22. Temerdashev, Z.A., Abakumov, A.G., Kaunova, A.A., Shelud’ko, O.N., & Tsyupko, T.G. (2023). Assessment of quality and region of origin of wines. Journal of Analytical Chemistry, 78(12), 1724–1740. (In Russ.). https://doi.org/10.1134/S1061934823120171

23. Titarenko, V.O., Khalafyan, A.A., Temerdashev, Z.A., Kaunova, A.A., & Abakumov, A.G. (2018). Identification of the varietal and regional origin of red wines by classification analysis. Journal of Analytical Chemistry, 73(2), 195–206. (In Russ.). https://doi.org/10.1134/S1061934818020132