Abstract
In this paper, samples of Cabernet Sauvignon wines produced in California have been analyzed on the basis of their elemental content and classified according to its geographical origin by the use of machine learning. Overall, 13 metals (Al, Cd, Co, Cr, Cu, Li, Mn, Ni, P, Pb, Rb, Sr, and Zn) were determined by inductively coupled plasma mass spectrometry (ICP-MS). We used two algorithms of variable selection in order to estimate the relevance of each metal to classification. Predictive models based on chemometric tools and machine learning algorithms were developed to differentiate origin of wine samples. Li and Sr were identified as the main responsible for the differentiation of samples. The application of Random Forest permitted to correctly classify all samples. A second analysis was performed by removing the variables Li and Sr to investigate the relevance of the others metals. We found that a group of seven variables (Cd, Ni, Mn, Pb, Rb, Co, Cu) which were able to discriminate the wines in 89% of accuracy by using Support Vector Machines. Results suggested that the developed methodology by advanced machine learning techniques is robust and reliable for the geographical classification of wine samples, and the study of the elements that characterize the regions.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00217-020-03480-5/MediaObjects/217_2020_3480_Fig8_HTML.png)
Similar content being viewed by others
References
Versari A, Laurie VF, Ricci A, Laghi L, Parpinello GP (2014) Progress in authentication, typification and traceability of grapes and wines by chemometric approaches. Food Res Int 60:2–18. https://doi.org/10.1016/j.foodres.2014.02.007
Luykx DMAM, van Ruth SM (2008) An overview of analytical methods for determining the geographical origin of food products. Food Chem 107:897–911. https://doi.org/10.1016/j.foodchem.2007.09.038
I.O. of V. and Wine, State of the Vitiviniculture World Market (2019) https://www.oiv.int/public/medias/6679/en-oiv-state-of-the-vitiviniculture-world-market-2019.pdf. Accessed 1 Aug 2019
Hira A, Swartz T (2014) What makes Napa Napa? The roots of success in the wine industry. Wine Econ Policy 3:37–53. https://doi.org/10.1016/j.wep.2014.02.001
Umali AP, Ghanem E, Hopfer H, Hussain A, Kao YT, Zabanal LG, Wilkins BJ, Hobza C, Quach DK, Fredell M, Heymann H, Anslyn EV (2015) Grape and wine sensory attributes correlate with pattern-based discrimination of Cabernet Sauvignon wines by a peptidic sensor array. Tetrahedron 71:3095–3099. https://doi.org/10.1016/j.tet.2014.09.062
Hopfer H, Nelson J, Collins TS, Heymann H, Ebeler SE (2015) The combined impact of vineyard origin and processing winery on the elemental profile of red wines. Food Chem 172:486–496. https://doi.org/10.1016/j.foodchem.2014.09.113
Fabani MP, Arrúa RC, Vázquez F, Diaz MP, Baroni MV, Wunderlin DA (2010) Evaluation of elemental profile coupled to chemometrics to assess the geographical origin of Argentinean wines. Food Chem 119:372–379. https://doi.org/10.1016/j.foodchem.2009.05.085
Soares F, Anzanello MJ, Fogliatto FS, Marcelo MCA, Ferrão MF, Manfroi V, Pozebon D (2018) Element selection and concentration analysis for classifying South America wine samples according to the country of origin. Comput Electron Agric 150:33–40. https://doi.org/10.1016/j.compag.2018.03.027
Šelih VS, Šala M, Drgan V (2014) Multi-element analysis of wines by ICP-MS and ICP-OES and their classification according to geographical origin in Slovenia. Food Chem 153:414–423. https://doi.org/10.1016/j.foodchem.2013.12.081
Orellana S, Johansen AM, Gazis C (2019) Geographic classification of US Washington State wines using elemental and water isotope composition. Food Chem 1:100007. https://doi.org/10.1016/j.fochx.2019.100007
Geana EI, Popescu R, Costinel D, Dinca OR, Ionete RE, Stefanescu I, Artem V, Bala C (2016) Classification of red wines using suitable markers coupled with multivariate statistic analysis. Food Chem 192:1015–1024. https://doi.org/10.1016/j.foodchem.2015.07.112
Šperková J, Suchánek M (2005) Multivariate classification of wines from different Bohemian regions (Czech Republic). Food Chem 93:659–663. https://doi.org/10.1016/j.foodchem.2004.10.044
da Costa NL, Castro IA, Barbosa R (2016) Classification of Cabernet Sauvignon from two different countries in South America by chemical compounds and support vector machines. Appl Artif Intell 30:679–689. https://doi.org/10.1080/08839514.2016.1214416
Urvieta R, Buscema F, Bottini R, Coste B, Fontana A (2018) Phenolic and sensory profiles discriminate geographical indications for Malbec wines from different regions of Mendoza, Argentina. Food Chem 265:120–127. https://doi.org/10.1016/j.foodchem.2018.05.083
Cozzolino D, Cynkar WU, Shah N, Smith PA (2011) Can spectroscopy geographically classify Sauvignon Blanc wines from Australia and New Zealand? Food Chem 126:673–678. https://doi.org/10.1016/j.foodchem.2010.11.005
Brereton RG (2015) Pattern recognition in chemometrics. Chemom Intell Lab Syst 149:90–96. https://doi.org/10.1016/j.chemolab.2015.06.012
Jiménez-Carvelo AM, González-Casado A, Bagur-González MG, Cuadros-Rodríguez L (2019) Alternative data mining/machine learning methods for the analytical evaluation of food quality and authenticity—a review. Food Res Int. https://doi.org/10.1016/j.foodres.2019.03.063
Callao MP, Ruisánchez I (2018) An overview of multivariate qualitative methods for food fraud detection. Food Control 86:283–293. https://doi.org/10.1016/j.foodcont.2017.11.034
Li H, Liang Y, Xu Q (2009) Support vector machines and its applications in chemistry. Chemom Intell Lab Syst 95:188–198. https://doi.org/10.1016/j.chemolab.2008.10.007
Ríos-Reina R, Morales ML, García-González DL, Amigo JM, Callejón RM (2018) Sampling methods for the study of volatile profile of PDO wine vinegars. A comparison using multivariate data analysis. Food Res Int 105:880–896. https://doi.org/10.1016/j.foodres.2017.12.001
Moreno J, Moreno-García J, López-Muñoz B, Mauricio JC, García-Martínez T (2016) Use of a flor velum yeast for modulating colour, ethanol and major aroma compound contents in red wine. Food Chem 213:90–97. https://doi.org/10.1016/j.foodchem.2016.06.062
Agazzi FM, Nelson J, Tanabe CK, Doyle C, Boulton RB, Buscema F (2018) Aging of Malbec wines from Mendoza and California: evolution of phenolic and elemental composition. Food Chem 269:103–110. https://doi.org/10.1016/j.foodchem.2018.06.142
Andreu-Navarro A, Russo P, Aguilar-Caballos MP, Fernández-Romero JM, Gómez-Hens A (2011) Usefulness of terbium-sensitised luminescence detection for the chemometric classification of wines by their content in phenolic compounds. Food Chem. https://doi.org/10.1016/j.foodchem.2010.08.014
La Torre GL, La Pera L, Rando R, Lo Turco V, Di Bella G, Saitta M, Dugo G (2008) Classification of Marsala wines according to their polyphenol, carbohydrate and heavy metal levels using canonical discriminant analysis. Food Chem. https://doi.org/10.1016/j.foodchem.2008.02.071
Martin AE, Watling RJ, Lee GS (2012) The multi-element determination and regional discrimination of Australian wines. Food Chem 133:1081–1089. https://doi.org/10.1016/j.foodchem.2012.02.013
Witten I, Frank E, Hall M, Pal C (2016) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, San Francisco (ISBN: 978-0-12-804291-5)
Bevilacqua M, Bucci R, Magrì AD, Magrì AL, Nescatelli R (2013) Classification and class-modelling. Data Handl Sci Technol 28:171–233. https://doi.org/10.1016/B978-0-444-59528-7.00005-3
Bajoub A, Medina-Rodríguez S, Gómez-Romero M, Ajal EA, Bagur-González MG, Fernández-Gutiérrez A, Carrasco-Pancorbo A (2017) Assessing the varietal origin of extra-virgin olive oil using liquid chromatography fingerprints of phenolic compound, data fusion and chemometrics. Food Chem 215:245–255. https://doi.org/10.1016/j.foodchem.2016.07.140
Ouyang Q, Zhao J, Chen Q (2013) Classification of rice wine according to different marked ages using a portable multi-electrode electronic tongue coupled with multivariate analysis. Food Res Int 51:633–640. https://doi.org/10.1016/j.foodres.2012.12.032
Xue H, Yang Q, Chen S (2009) SVM: support vector machines. In: Top ten algorithms data min, pp. 37–59
Jurado JM, Alcázar Á, Palacios-Morillo A, De Pablos F (2012) Classification of Spanish DO white wines according to their elemental profile by means of support vector machines. Food Chem 135:898–903. https://doi.org/10.1016/j.foodchem.2012.06.017
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans Syst Man Cybern 30:451–462. https://doi.org/10.1109/5326.897072
Gómez-Meire S, Campos C, Falqué E, Díaz F, Fdez-Riverola F (2014) Assuring the authenticity of northwest Spain white wine varieties using machine learning techniques. Food Res Int 60:230–240. https://doi.org/10.1016/j.foodres.2013.09.032
Costa NL, Llobodanin LAG, Castro IA, Barbosa R (2019) Using Support Vector Machines and neural networks to classify Merlot wines from South America. Inf Process Agric 6:265–278. https://doi.org/10.1016/j.inpa.2018.10.003
Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electr Eng 40:16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024
Chen Y-W, Lin C-J (2006) Combining SVMs with various feature selection strategies. In: Featur. extr. Springer, pp. 315–324. https://doi.org/10.1007/978-3-540-35488-8_13
R Core Team (2016) R: a language and environment for statistical computing. R Found. Stat. Comput, Vienna
Kuhn M (2015) Caret: classification and regression training. Astrophys Source Code Libr
Romanski P, Kotthoff L, Kotthoff ML (2018) Package Fselector: selecting attributes, repos. CRAN 18
Wickham H (2009) ggplot2: elegant graphics for data analysis. Springer, New York
Pérez-Álvarez EP, Garcia R, Barrulas P, Dias C, Cabrita MJ, Garde-Cerdán T (2019) Classification of wines according to several factors by ICP-MS multi-element analysis. Food Chem 270:273–280. https://doi.org/10.1016/j.foodchem.2018.07.087
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 Chem 138:1125–1134. https://doi.org/10.1016/j.foodchem.2012.11.104
Yamashita GH, Anzanello MJ, Soares F, Rocha MK, Fogliatto FS, Rodrigues NP, Rodrigues E, Celso PG, Manfroi V, Hertz PF (2019) Hierarchical classification of sparkling wine samples according to the country of origin based on the most informative chemical elements. Food Control 106:106737. https://doi.org/10.1016/j.foodcont.2019.106737
Villano C, Lisanti MT, Gambuti A, Vecchio R, Moio L, Frusciante L, Aversano R, Carputo D (2017) Wine varietal authentication based on phenolics, volatiles and DNA markers: state of the art, perspectives and drawbacks. Food Control 80:1–10. https://doi.org/10.1016/j.foodcont.2017.04.020
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interest.
Compliance with ethics requirements
This article does not contain any studies with human or animal subjects.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
da Costa, N.L., Ximenez, J.P.B., Rodrigues, J.L. et al. Characterization of Cabernet Sauvignon wines from California: determination of origin based on ICP-MS analysis and machine learning techniques. Eur Food Res Technol 246, 1193–1205 (2020). https://doi.org/10.1007/s00217-020-03480-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00217-020-03480-5