Characterization of cognacs and grape brandies by fluorescence spectra processed using machine learning methods

A method for express characterization of cognacs and grape brandies is proposed in the case study of their classification by geographical origin. The method is based on the use of informative fragments of fluorescence spectra of samples of different geographic origin and their subsequent processing using machine learning algorithms. Three types of fluorescence spectra were selected, i.e., spectra of synchronous scanning at a wavelength difference of 50 nm, and emission spectra at an excitation wavelength of 250 and 280 nm. These spectra were measured for 43 samples of cognacs and grape brandies, which were divided into 3 classes according to their geographical origin, the regions of the Russian Federation (except for Dagestan), the Republic of Dagestan (Russian Federation), and the Republic of Armenia. A training set consisting of 33 samples and a test set consisting of 10 samples were formed from the samples under study. To train the models, an extreme gradient boosting, one of the modern machine learning algorithms, was chosen as suitable for a limited number of samples in the training set. The correctness of the sample recognition of the test set (consisting of 10 samples not used in training) was 100% for models based on emission spectra and spectra of synchronous scanning. The results obtained demonstrate the fundamental possibility of using informative fragments of fluorescence spectra in combination with machine learning to characterize cognacs and grape brandies, including their classification by the geographical origin. However, the use of this method in regulated procedures of the product control is possible only for cognacs and grape brandies with a protected geographical indication (designation of the origin). The above approach can also be used to classify other liquid food products (juices, honey, etc.).

1. The shady market of alcoholic beverages: Research of the Center for Consumer Market Development of the Moscow School of Management Skolkovo and the Center for Social Design «Platform». https://sk.skolkovo.ru/storage/file_storage/b28ed58b-cc05-4c31-8e97-48c0dac647e0/SKOLKOVO_CMDC_Shadow_alcohol_market_Full_Report_Rus.pdf (accessed February 13, 2023) [in Russian].

2. Coetzee P., van Jaarsveld F., Vanhaecke F. Intraregional classification of wine via ICP-MS elemental fingerprinting / Food Chem. 2014. Vol. 164. P. 485 – 492. DOI: 10.1016/j.foodchem.2014.05.027

3. Geana I., Iordache A., Ionete R., et al. Geographical origin identification of Romanian wines by ICP-MS elemental analysis / Food Chem. 2013. Vol. 138. N 2 – 3. P. 1125 – 1134. DOI: 10.1016/j.foodchem.2012.11.104

4. Savchuk S. A., Palacio C., Gil A., et al. Determination of the chemical composition of alcoholic beverages by gas chromatography-mass spectrometry / J. Food Process. Preserv. 2020. Vol. 44. N 9. e14676. DOI: 10.1111/jfpp.14676

5. Double-aged brandy Torres 10 Double Barrel. https://www.torresbrandy.com/ru/brandies/torres-10-double-barrel (accessed February 13, 2023) [in Russian].

6. Levin A. D., Sadagov A. Yu., Nagaev A. I., Karakhotin S. N. Qualitative analysis of wines based on the joint use of their optical spectra of different physical nature / Analit. Kontrol’. 2018. Vol. 22. N 2. P. 147 – 156 [in Russian].

7. Ranaweera R. K. R., Gilmore A. M., Capone D. L., et al. Authentication of the geographical origin of Australian Cabernet Sauvignon wines using spectrofluorometric and multi-element analyses with multivariate statistical modeling / Food Chem. 2021. Vol. 335. 127592. DOI: 10.1016/j.foodchem.2020.127592

8. Basalekou M., Kyraliou M., Killithraka S. Authentication of wine and other alcohol-based beverages — Future global scenario / Future Foods. Global. Trends, Opportunities and Sustainability Challenges. Ch. 38. P. 669 – 695. DOI: 10.1016/B978-0-323-91001-9.00028-1

9. Dufour É., Letort A., Laguet A., et al. Investigation of variety, typicality and vintage of French and German wines using front-face fluorescence spectroscopy / Anal. Chim. Acta. 2006. Vol. 563. N 1 – 2. P. 292 – 299. DOI: 10.1016/j.aca.2005.11.005

10. Silveira A., Barbeira P. A fast and low-cost approach for the discrimination of commercial aged cachaças using synchronous fluorescence spectroscopy and multivariate classification / J. Sci. Food Agric. 2022. Vol. 102. N 11. P. 4918 – 4926. DOI: 10.1002/jsfa.11857

11. Tóthová J., Sádecká J., Májek P. Total Luminescence Spectroscopy for Differentiating Between Brandies and Wine Distillates / Czech J. Food Sci. 2009. Vol. 27. N 6. P. 425 – 432. DOI: 10.17221/125/2008-CJFS

12. Tóthová J., Sádecká J., Májek P. Classification of brandies and wine distillates using front face fluorescence spectroscopy / Food Chem. 2009. Vol. 117. N 3. P. 491 – 498. DOI: 10.1016/j.foodchem.2009.04.053

13. Mustapha I. B., Saeed F. Bioactive Molecule Prediction Using Extreme Gradient Boosting / Molecules. 2016. Vol. 21. N 8. 983. DOI: 10.3390/molecules21080983

14. Natekin A., Knoll A. Gradient boosting machines, a tutorial / Front. Neurorobotics. 2013. Vol. 7. DOI: 10.3389/fnbot.2013.00021

15. Skourikhin I. M. Chemistry of congac and brandy. — Moscow, DeliPrint, 2005. — 296 p. [in Russian].

16. CJSC «Stavropol Wine and Cognac Factory». http://www. stavvinprom.com/ index.php/predpriyatiya/item/174 (accessed February 13, 2023) [in Russian].

17. Derbent wine and cognac plant. https://derkonyak.ru/terroir (accessed February 13, 2023) [in Russian].

18. Kizlyar brandy plant. https://kizlyar-cognac.ru/%d0%bf%d1%80%d0%be%d0%b8%d0%b7%d0%b2%d0%be%d0%b4%d1%81%d1%82%d0%b2%d0%be/?age-verified=81f16562e7 (accessed February 13, 2023) [in Russian].

19. Law of the Republic of Armenia «On Alcoholic Beverages Based on Grape Raw Materials». Ch. 5. P. 24 – 25. http://www.parliament.am/legislation.php?sel=show&ID=3348&lang=rus#5 (accessed February 13, 2023) [in Russian].

20. Four-year old Russian cognac «Staraya Krepost’» with protected geographical indication. https://reestrinform.ru/federalnyi-reestr-alkogolnoi-produktcii/233-koniak-s-zashchishchennym-geograficheskim-ukazaniem/-obj200036395.html (accessed February 13, 2023) [in Russian].

21. Four-year old Russian cognac «Derbent ****» with protected geographical indication. https://reestrinform.ru/federalnyi-reestr-alkogolnoi-produktcii/233-koniak-s-zashchishchennym-geograficheskim-ukazaniem/-obj200036393.html (accessed February 13, 2023) [in Russian].

22. Five-year old Russian cognac «Derbent *****» with protected geographical indication. https://reestrinform.ru/federalnyi-reestr-alkogolnoi-produktcii/233-koniak-s-zashchishchennym-geograficheskim-ukazaniem/-obj200036417.html (accessed February 13, 2023) [in Russian].

23. Oseledtseva I. V. Scientific rationale and development of quality control methodology of cognac distillates and cognacs. Doctoral thesis. — Krasnodar, 2017. — 437 p. [in Russian].