For model selection, the dataset underwent 80:20 stratified random split, to compose the train and the test set, respectively. The test set was used to verify the trained model performance, as it had not been previously seen by the model. All samples with unknown label values were taken out of the dataset before the stratified split was done. Both sets were composed of all 39 elements (B, Na, Mg, Al, P, S, Cl, K, Ca, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, As, Br, Rb, Sr, Y, Zr, Nb, Cd, Sn, I, Cs, Ba, La, Ce, Pr, Nd, Sm, W, Tl, Pb and U).

Six machine learning models were benchmarked: Random Forest, k-nearest neighbours (k-NN), support vector machine (SVM), Logistic Regression implemented in scikit-learn, eXtreme Gradient Boosting (XGB) implemented in the XGBoost library ( Chen and Guestrin, 2016) and an artificial neural network model (ANN) created using the TensorFlow library ( Abadi et al., 2015). No optimisation of the models’ functions was done for their comparison. The metric chosen for their comparison was the area under the receiver operating characteristic (ROC) curve. This curve is a graphic representation of the trade-off between specificity and sensitivity of a model ( Fawcett, 2006). The area under this curve (AUC) is an important metric when evaluating a model, it represents the probability that a classifier will correctly rank a randomly selected positive instance higher than a randomly chosen negative instance. An AUC of 0.5 reflects random guessing, while a perfect classifier achieves an AUC of 1.0 ( Fawcett, 2006).

The chosen classes were country, French region and principal grape variety. Only labels with more than 50 samples were classified. The model was trained and tested for 10 iterations. The AUC score was computed for each iteration and its mean was then calculated.

The XGB was found to be the best performing technique (as explained the “Results and discussion” section). XGB is a boosting ensemble learning algorithm, which uses many decision trees whose predictions are combined in order to obtain the final classification ( Chen and Guestrin, 2016). This machine learning method has been applied in several domains, such as disease and stock prediction ( Chen and Guestrin, 2016; Ma, 2021), with very good results when distinguishing the geographical origin of food products ( Kang, 2023; Wen, 2023).

In order to improve the model predictions after selection, a grid search was employed to optimise the model’s parameters: number of estimators were set to 500, maximum tree depth to five, learning rate to 0.1, gamma to zero and the regularisation parameter lambda to one. The model parameter “objective” was binary:logistic. The metrics chosen to evaluate the classifier performance were sensitivity, specificity, accuracy and the AUC. The first metric was the probability of a positive individual being correctly classified as positive and the second the probability of a negative individual being correctly classified as negative. Accuracy was the ratio of correctly classified samples to the total number of samples present in the evaluation dataset ( Hicks, 2022).

The same classes and labels were classified in the optimised XGB model. It was repeated 10 times and the means of the metrics were calculated.

For this study, the MWP of 12,966 wines of commercial origin as well as from international competitions were obtained. The wines originated from a wide variety of countries (more than 45), with France being the most represented (9,473 wines), as well as several regions (more than 200) and grape varieties (more than 200). Figure 2 illustrates the distribution of the analysed wines in the database. A more detailed description is given in Tables S1, S2 and S3.

Figure 2. Distribution of the 12,966 analysed wines based on the wine type (a), country (b), grape variety (c), and French wine region (d). The category “Others” contains labels with fewer than 150 samples. A more detailed description of each category is given in Tables S1, S2 and S3.

Semi-quantitative analysis is an interesting alternative to full-quantitative analysis and is particularly valuable for rapidly screening the elemental composition of samples, since it enables fast determination of the approximate elemental composition in unknown samples. In semi-quantitative mode, the entire mass range is scanned, thereby recording a signal for every possible element or isotope. Moreover, SQ analysis involves estimating the relative concentrations of elements without relying on the multi-standard calibration necessary for quantitative analysis. It also eliminates the need for multiple calibration curves due to incompatibility of the simultaneous presence of certain elements ( i.e., Zr in the presence of an excess of Na). As a consequence, this mode has high economical advantages both in time and reagents.

The accuracy was not determined, but several papers have reported high accuracy (bias < 20%) ( Catarino et al., 2006; Chen and Guestrin, 2008). While it is associated with lower accuracy compared to quantitative analysis, this method is suitable for creating a comprehensive database of mineral profiles that can be exploited in multivariate data analysis and machine learning algorithms. Indeed, the aim of the analysis is not to ascertain the concentrations of the different elements present in wine but to provide values that can be considered characteristic of a given wine. Reproducibility was determined via the analysis of the control wine over a 15 day-period and was found to not exceed 15 % for all the elements.

The developed SQ method enabled analysis of more than 200 samples per day, with each sample being analysed for seven minutes. To prevent any potential signal variation over time, several control points were implemented: analysis of the control wine at the start, midpoint and end of each sequence; analysis of blanks and 28-element standard every 40 analyses; monitoring of indium concentration in each sample. It was used to determine the MWP of the wines of this study.

Comprehensive statistical summaries, including the mean, median and interquartile range (IQR) of mineral element concentrations, are provided in Table 1. The concentration distributions across the database using Box-cox transformation are depicted in Figure 3. Lambda values are given in Table S4. Visual inspection of the histograms suggests multimodal distributions of data. Consequently, the Spearman correlation coefficient was adopted to evaluate the relationships between variables, given its non-parametric nature as a measure of rank correlation.

Figure 3 illustrates the noticeable dispersion of elemental content in wine. This phenomenon is documented in existing literature across various contexts, including comparisons between wines from different countries ( Bentlin, 2011; Griboff et al., 2021), within the same country ( Kment, 2005), across different types ( Griboff et al., 2021), and even when examining different vintages from the same vineyard ( Tanabe et al., 2020). This variability in elemental content underscores the intricate interplay of factors shaping wine composition, such as geographical origin, vinification techniques and environmental influences.

Given this complexity, establishing a comprehensive wine database that accounts for these diverse factors is indispensable for advancing our understanding of the relationships between elements and the broader context of wine production. In the subsequent sections, we delve more deeply into the examination of elemental correlations and their potential applications in wine traceability.

Figure 3. Element concentration distribution in the database. Concentration (x-axis) is transformed using the Box-Cox power transformation. If the concentration value was under the limit of quantification, the data was not plotted. The concentration and frequency scales have been adapted for each element. The Lambda values for each element are given in Table S4.

To investigate potential relationships between element concentrations, a Spearman correlation test was conducted at a 95 % confidence level. The correlation coefficients (ρ) are depicted in the correlation matrix plot, in Figure 4A. Positive (red shading) and negative (blue shading) correlations were found amid the pairs of elements, with the most significant being positive correlations between rare earth elements, Y, La, Ce, Pr, Nd and Sm (ρ varying from 0.93 to 0.79) and Zr-Y (ρ 0.71).

Rare earth elements are a group with similar chemical behaviour; thus their correlation is expected and has been reported elsewhere ( Alonso Gonzalez, 2021; Pasvanka, 2021). They are associated with soil content and bentonite treatment ( Catarino, 2008; Pohl, 2007). The correlation between Zr and Y may also be explained by this clarification agent, as well as by the use of Yttria-stabilised zirconia for wine stabilisation and/or filtration ( Catarino, 2008; Salazar, 2006; Silva-Barbieri, 2022).

Figure 4. (a) Correlation matrix plot illustrating the relationships between 39 pairs of element concentrations across all samples of the database. The colour gradient reflects the Spearman correlation coefficient (ρ), with statistically significant correlations ( p-value < 0.05) indicated in red (positive correlation) or blue (negative correlation). Non-significant correlations are in white cells. (b) Hierarchical cluster dendrogram generated using Ward's method and Euclidean distance for the 39 elements. Distances indicate the degree of correlation between different elements. Three clusters are identifiable: C1 (Ba, Mn, Co, Fe, Cr, Zn, Pb, Cu, Ni, Cd, Sn, Tl, Rb and Cs), C2 (K, Mg, P, I, Ca, S, Sr, B, Br, Cl and Na) and C3 (Zr, Al, U, As, V, W, Nb, Ti, Ce, La, Nd, Pr, Sm and Y).

To further elucidate metal concentration relationships, a cluster analysis was performed utilising the Ward method and Euclidean distance. The resulting dendrogram, depicted in Figure 4B, reveals three distinct clusters which are in agreement with the correlations found in Figure 4A. The first cluster (C1) comprises Ba, Mn, Co, Fe, Cr, Zn, Pb, Cu, Ni, Cd, Sn, Tl, Rb and Cs, which are predominantly micronutrients. These elements are essential to plant health and some ( e.g., iron and copper) also impact the colour and oxidative stability of wine ( Pohl, 2007).

The second cluster (C2) comprises plant macronutrients K, Mg, P, Ca and S, which have major roles in plant metabolism. Additionally, this cluster includes supplementary elements, such as I, Sr, B, Br, Cl and Na, whose presence in wine warrants further exploration. The third cluster (C3) encompasses rare earth elements alongside Zr, Al, U, As, V, W, Nb and Ti, their presence in wine originating from various sources, including soil composition and winemaking techniques ( Catarino, 2008; Pohl, 2007), as illustrated in Figure 1.

Building on the insights gleaned from the correlation coefficients and cluster analysis, principal component analysis (PCA) was subsequently employed to further explore the intricate relationships within the dataset. Due to its high dimensionality, visualisation was not possible. Therefore, a dimensionality reduction technique t-SNE was applied to the first ten principal components, which accounted for 70 % of total variance.

Initially, the grouping of all the samples was studied, as shown in Figure 5 and Figure S2. In terms of wine type, red wines are well separated from rosé and white wines, which is expected due to the differences in winemaking processes. This is consistent with other studies ( Gajek, 2021), which have also shown–albeit using a limited number of samples–differences in mineral wine profiles for red, rosé and white wines. For the distribution of data based on the country of origin, French wines constitute the majority and are represented in the large (blue) cluster. Smaller groups of Spanish and Italian wines are visible. Lastly, grape variety grouping was also studied, for which the samples containing unknown varieties were taken out in order to better illustrate the existing clusters. These grape variety clusterings were attributed to the interaction of two different factors: the unique composition of each variety and its region of origin. Therefore, the assessment of wine region clusters was carried out for French wines, as most of their regions are well represented in the database, which resulted in the t-SNE representations in Figure C and Figure S2B.

For French wine type, the separation of red wines from white and rosés is clear. For the French wine regions and principal grape variety, all the categories with more than 50 samples have been represented and only French samples with known categories have been plotted. Clusters are evident for the Beaujolais, Vallée du Rhône, Bordeaux and Champagne regions. The separation of the former three regions may be due to the typicity of their soils, as well as the typical varieties that are used in the production of the respective wines. This is supported by the separation of the principal grape varieties, as the clusters of Gamay, Grenache noir and Merlot correspond to those of Beaujolais, Vallée du Rhône and Bordeaux, respectively.

For the Champagne region separation there is an additional explanation to that involving principal variety (Chardonnay) and soil. Most of the sparkling wines in the dataset come from this region, thus the chemical difference between a white still wine and a white sparkling wine may artificially play a role in this difference.

The promising patterns observed in both the data grouping and a rich database containing more than 12,000 samples have motivated the development of machine learning techniques tailored to sample classification.

Figure 5. (a-c) t-SNE representation of international MWP samples according to country (a), international main grape variety (b) and French region (c) of the 10 first principal components (67 % of total variance). Only samples with known labels are represented in the images. For complementary images (type and French varieties), see Figure S2. Figure 5C and Figure S2B have similarities, showing that the typicity of the wine producing region is related to the grape variety. A clear separation for red and white/rosé is illustrated for international samples in Figure S2A.

Various supervised learning algorithms have been employed in the literature to determine and differentiate the origin of wines. These include the support vector machine ( Astray, 2021; Da Costa, 2020), stepwise linear discriminant analyses ( Pérez-Magariño, 2004), random forest ( Astray, 2021; Da Costa, 2020) and artificial neural networks ( Astray, 2021; Da Costa, 2020; Pérez-Magariño, 2004; Wu, 2021). Ranaweera et al. (2022) were also able to identify blending percentages using spectrofluorimetric analysis with another machine learning algorithm, the extreme gradient boosting discriminant analysis.

Given the extensive array of machine learning techniques prevalent in the literature, an initial performance assessment was conducted to determine the optimal model for sample classification. The models were trained and tested ten times, using 80:20 random stratified split, and the mean AUC score was computed after classification of test samples. The results are given in Table 2. The model with the best performance was eXtreme Gradient Boosting (XGB), and was thus chosen to be developed in this study.

The performance metrics of the classifier for countries, French region and principal grape varieties of the wines are given in Table 3. When assessing the classifier performance in terms of country prediction, it is evident that the models can accurately predict a wine's country. The AUC surpasses 0.9 across all of the countries, indicating the models' high reliability when distinguishing between different samples. Furthermore, the accuracy metrics show remarkable values, with at least 83 % correctly classified samples across all countries. Particularly noteworthy are the results for Brazil and Australia, with accuracy levels exceeding 96 %.

French wines constitute the predominant country; this facilitates the comprehensive coverage of various French wine regions within the database, which enables the development of classifiers to predict the origin of these wines within their respective territory. The developed models showed high predictive ability, with their AUCs varying from 0.906 to 0.996. Their best performance, as illustrated by the AUC, was for Bordeaux, Beaujolais and Champagne regions. This is in agreement with their natural separation in the set, as presented in Table 3 and led to accurate predictions, varying from 95.2 % to 97.8 %.

These results are promising as they indicate that the MWP is a robust tool for verifying the origin of a wine. Further avenues of research include the exploration of its use when tracing a wine to sub-regional level, thereby providing insights into the unique terroir characteristics within a larger wine-producing region. Additionally, this tool can be applied in further research to explore the differences between the mineral signatures of wine-producing regions, as it translates not only the fingerprint of the soil but also viticultural practices and winemaking techniques, as illustrated in Figure 1.

When distinguishing grape varieties, XGB demonstrates reliability when distinguishing the principal wine varieties, with an AUC exceeding 0.8 for all of the labels. The classification of the principal wine varieties proves more complex than country or region due to the prevalence of multivarietal wines in certain regions, as well as the use of rootstocks. Moreover, the International Organisation of Vine and Wine’s labelling rules ( International Organisation of Vine and Wine, 2024) do not require varietal names and their percentages to be mentioned, which increases the difficulty of the classification.

These factors may explain the separation shown in Figure 5 with clustering remarkable only to the Gamay variety. However, the model showed high overall performance for the classification of principal wine varieties with accuracy ranging from 73.7 % to 98.0 %. Two possible avenues of improvement are possible: training the model exclusively on monovarietal wines and enriching the database with the rootstock used for each variety in a wine. Even though this is a possibility, the models performed remarkably well without these options, showing their potential for grape variety classification.

In order to further adapt the model to wine authentication, the type of wine can be taken into account when segmenting the dataset. To this end, red wines were used to carry out a binary classification of French, Italian and Spanish wines and thus evaluate how the metrics would change. The results are presented in Table 4. It can be seen that model performance for all three countries displays an AUC higher than 0.9. The same behaviour was found in terms of the model’s accuracy, which reached at least 94 % of correct classifications for France and Spain. This performance warrants further exploitation of the data, and it reinforces the need for a polyvalent database that can be refined as required.

The differentiation between the previously classified categories relies exclusively on the features available within the database, consisting of 39 elements in the MWP. When differentiating between these categories, their significance is evaluated through the mean importance feature, as depicted in Figure 6 for the three countries. This metric has positive and negative values, depending on how the presence (positive, black shading) or absence (negative, blue shading) of a feature helps in distinguishing each category. In the differentiation of French wines, the absence of strontium is the most important feature that differentiates them from all the other wines, while for Spanish, the presence of this element helps in their classification.

Fifteen elements contribute to the differentiation of the wines originating from Italy. The variation in the features influencing the model highlights the necessity of conducting a comprehensive MWP assessment of each wine, as different categories can be differentiated by various features; this is further illustrated for the three main regions and grape varieties in Figure S3 and Figure S4.

Figure 6. Element Mean Feature Importance for the three major countries. Values are presented in decreasing order of importance. Values in black indicate positive correlations and values in blue, negative correlations between the element’s concentration and the wine category. These values for the three main regions and three main grape varieties are shown in Figure S2 and Figure S3.

The segmentation of the dataset previously carried out for the country classifications is not the only strategy that can be used to adapt the model to sample classification. The decision threshold of the model can be tuned in order to achieve higher values of specificity or sensitivity, which could be used to better determine whether the sample is from the target category or not. A specificity of over 99 % can be thereby be obtained, increasing the reliability of the classification as non-belonging to a category. This optimisation was conducted for the three major countries, French regions and grape variety, producing the metrics presented in Table 5.

When comparing the models described in this study with others in the literature, similar performances were found. Tanabe (2020) analysed 62 elements to differentiate neighbouring American viticultural regions, with an accuracy of over 94 %. In terms of grape variety, their study was limited to Pinot noir with a limited number of samples [ n = 53] ( Tanabe et al., 2020). As a comparison, the model developed in this study obtained a region classification accuracy of up to 98 % using more samples and a more diverse dataset.

Griboff et al. (2021) analysed 18 elements by ICP-MS and 2 isotopes by isotope ratio mass spectrometry of 62 wine samples from Argentina and Australia. As already explained in the Introduction, sample preparation for isotope ratio analysis is time-consuming and hinders the acquisition of data for a large and comprehensive dataset. The method developed in this study provides a more time-efficient analysis, as well as a more comprehensive database to be exploited via machine learning methods.

Forina et al. (2009) analysed a dataset extracted from the European Wine DataBank. It was composed of 58 selected organic and inorganic analytical parameters of 1188 wine samples that were available in the databank. This was the most comprehensive study found in the literature, but it was still limited to four countries and the methods of data acquisition were costly and time-consuming.

When distinguishing varieties, other studies have explored the elemental content of wine as a fingerprint ( Feher, 2019; Temerdashev et al., 2019), using chemometric or machine learning approaches. This study achieved comparable results with a larger and more origin-diverse dataset. As this profile is usually only associated with a wine’s origin, being able to differentiate varieties in a multiple-origin set is promising for the future of wine authentication. Recently Temerdashev et al. (2024) have shown that, using chemometric analysis and 153 samples, it is possible to distinguish between three grape varieties (Chardonnay, Riesling and Muscat) and four regions of the Krasnodar territory: this therefore also validates our ICP-MS mineral analysis methodology for classifying wines.

While previous studies have obtained good results for wine classification, no other existing research has used the same number of samples and representation of countries, wine regions and varieties as in the present study. Such a large database is essential for creating a polyvalent model that can verify the origin of an unknown wine by exploiting exclusively its mineral wine profile.

To the best of our knowledge, this study is the first that involves the analysis of over twelve thousand wine samples and their corresponding MWP. The extensive dataset opens up numerous avenues for further research. For example, MWP could be used as a tool for studying various ecological phenomena over time and to support necessary adaptations to climate change and modifications in viticultural practices. For instance, elements like potassium are already closely monitored by winegrowers, as potassium nutrition is directly correlated with grapevine growth and ultimately with wine quality ( Villette, 2020). Interestingly, potassium levels in berries have been steadily increasing over the past few decades and serve as a reliable indicator of climate change, which is linked to a decline in wine quality ( Nistor, 2022). Similarly, an increase in calcium levels in wine has been observed, attributed to global warming-induced water stress in plants, which is also linked to changes in wine quality ( Fioschi, 2024). In addition to these well-known minerals associated with global warming, MWP, when integrated with large datasets, may be used in the future to identify new indicators related to subtle climate changes in specific regions.

The findings of this study demonstrate the remarkable capabilities of MWP in determining the country and region of wine production. It is noteworthy that contemporary consumers increasingly seek detailed information regarding authenticity that goes beyond just the region of origin. The concept of terroir, ranging from MACRO-terroir to MICRO-terroir via MESO-terroir ( Marre et al., 2012), underscores the intricate interplay of factors shaping wine characteristics. Regions like Bourgogne, Bordeaux, and Champagne boast diverse soils, microclimates, grape varieties and cultivation methods.

Analysing the mineral composition of wines and leveraging AI to process this data unlocks the potential of authenticating wines at a granular geographical level. This necessitates working within specific regions with hundreds of wines sourced from geologically homogeneous plots to ensure precise metadata. In the medium-term, correlating this metadata with sensory profiles of wines promises a deeper understanding of their origins and thus quality. The combination of mineral wine profile and artificial intelligence could thus be an indispensable tool for such investigations.

This study pioneers the development of a semi-quantitative method that enables rapid and robust screening of 41 elements present in wines (about 200 samples can be analysed in just one day), leading to the creation of a database of over 12,000 mineral wine profiles in just over a year. Here, correlations between metal traces, rare earth elements, macro and micronutrients were initially analysed, and their further exploration could be an intriguing avenue for future research endeavours.

By leveraging a large and diverse dataset, the present study developed an Extreme Gradient Boosting model, which achieved mean accuracies of 92 % for country classification, 91 % for French wine region and 85 % for grape variety. Additionally, the initial specialisation of the dataset to assess the performance of the model separating countries for red wines produced promising results, with an increase in AUC scores (> 0.9) and accuracy (> 90 %) for the classification of the three countries tested. These findings have practical implications for the wine industry in that this comprehensive dataset serves as a robust foundation for a versatile AI model capable of identifying a wine’s origin with over 99% specificity solely based on its mineral wine profile.

Future research should focus on correlating the MWP and geological data to explore terroir signature, as well as correlating the MWP and sensory profiles to delve more deeply into association of MWP with the quality of wine. In conclusion, combining MWP and AI is indispensable for the wine industry, which needs to cater to the ever-evolving demands of consumers for detailed origin authentication beyond mere geographical regions.

We would like to express our gratitude to Victor Gomez and Henri-Laurent Arnould, wine competition organisers, and to Gilles Masson, president of Centre du Rosé, for providing the majority of the samples.

1 M. Abadi A. Agarwal P. Barham E. Brevdo Z. Chen C. Citro G. S. Corrado A. Davis J. Dean M. Devin S. Ghemawat I. Goodfellow A. Harp G. Irving M. Isard Y. Jia R. Jozefowicz L. Kaiser M. Kudlur X. Zheng 2015 TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. 2 P. Alonso Gonzalez E. Parga-Dans P. Arribas Blázquez O. Pérez Luzardo M. L. Zumbado Peña M. M. Hernández González Á. Rodríguez-Hernández C. Andújar 2021 Elemental composition, rare earths and minority elements in organic and conventional wines from volcanic areas: The Canary Islands (Spain). PLOS ONE, 16 11 e0258739 https://doi.org/10.1371/journal.pone.0258739 3 G. Astray C. Martinez-Castillo J.-C. Mejuto J. Simal-Gandara 2021 Metal and metalloid profile as a fingerprint for traceability of wines under any Galician protected designation of origin. Journal of Food Composition and Analysis, 102 104043 https://doi.org/10.1016/j.jfca.2021.104043 4 M. M. Baleiras-Couto J. E Eiras-Dias 2006 Detection and identification of grape varieties in must and wine using nuclear and chloroplast microsatellite markers. Analytica Chimica Acta, 563 1-2 283–291 https://doi.org/10.1016/j.aca.2005.09.076 5 F. R. S. Bentlin F. H. Pulgati V. L. Dressler D. Pozebon 2011 Elemental analysis of wines from South America and their classification according to country. Journal of the Brazilian Chemical Society, 22 2 327–336 https://doi.org/10.1590/S0103-50532011000200019 6 M. Del M. Castiñeira R. Brandt N. Jakubowski J. T Andersson 2004 Changes of the Metal Composition in German White Wines through the Winemaking Process. A Study of 63 Elements by Inductively Coupled Plasma−Mass Spectrometry. Journal of Agricultural and Food Chemistry, 52 10 2953–2961 https://doi.org/10.1021/jf035119g 7 S. Catarino A. S. Curvelo-Garcia R. B De Sousa 2006 Measurements of contaminant elements of wines by inductively coupled plasma-mass spectrometry: A comparison of two calibration approaches. Talanta, 70 1073-1080 https://doi.org/10.1016/j.talanta.2006.02.022 8 S. Catarino M. Madeira F. Monteiro F. Rocha A. S. Curvelo-Garcia R. B De Sousa 2008 Effect of Bentonite Characteristics on the Elemental Composition of Wine. Journal of Agricultural and Food Chemistry, 56 1 158–165 https://doi.org/10.1021/jf0720180 9 R. Cellier S. Berail J. Barre E. Epova F. Claverie A.-L. Ronzani S. Milcent P. Ors O. F. X Donard 2021 Analytical strategies for Sr and Pb isotopic signatures by MC-ICP-MS applied to the authentication of Champagne and other sparkling wines. Talanta, 234 122433 https://doi.org/10.1016/j.talanta.2021.122433 10 C. Chen E. Dabek-Zlotorzynska P. E. Rasmussen H. Hassan M. Lanouette 2008 Evaluation of semiquantitative analysis in ICP-MS. Talanta, 74 1547-1555 https://doi.org/10.1016/j.talanta.2007.09.037 11 T. Chen C. Guestrin 2016 XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785 12 N. L. Da Costa J. P. B. Ximenez J. L. Rodrigues F. Barbosa R. Barbosa 2020 Characterization of Cabernet Sauvignon wines from California: Determination of origin based on ICP-MS analysis and machine learning techniques. European Food Research and Technology, 246 6 1193–1205 https://doi.org/10.1007/s00217-020-03480-5 13 S. A. Drivelos C. A Georgiou 2012 Multi-element and multi-isotope-ratio analysis to determine the geographical origin of foods in the European Union. TrAC Trends in Analytical Chemistry, 40 38–51 https://doi.org/10.1016/j.trac.2012.08.003 14 D. I. Ellis V. L. Brewster W. B. Dunn J. W. Allwood A. P. Golovanov R. Goodacre 2012 Fingerprinting food: Current technologies for the detection of food adulteration and contamination. Chemical Society Reviews, 41 17 5706 https://doi.org/10.1039/c2cs35138b 15 T. Fawcett 2006 An introduction to ROC analysis. Pattern Recognition Letters, 27 8 861–874 https://doi.org/10.1016/j.patrec.2005.10.010 16 I. Feher D. A. Magdas A. Dehelean C. Sârbu 2019 Characterization and classification of wines according to geographical origin, vintage and specific variety based on elemental content: A new chemometric approach. Journal of Food Science and Technology, 56 12 5225–5233 https://doi.org/10.1007/s13197-019-03991-4 17 G. Fioschi I. Prezioso L. Sanarica R. Pagano S. Bettini V. M Paradiso 2024 Carrageenan as possible stabilizer of calcium tartrate in wine. Food Hydrocolloids, 157 110403 https://doi.org/10.1016/j.foodhyd.2024.110403 18 M. Forina P. Oliveri H. Jäger U. Römisch J. Smeyers-Verbeke 2009 Class modeling techniques in the control of the geographical origin of wines. Chemometrics and Intelligent Laboratory Systems, 99 2 127–137 https://doi.org/10.1016/j.chemolab.2009.08.002 19 M. Gajek Pawlaczyk A Szynkowska-Jozwik M I 2021 Multi-elemental analysis of wine samples in relation to their type, origin, and grape variety. Molecules, 26 214 https://doi.org/10.3390/molecules26010214 20 M. Giaccio A. Vicentini 2008 Determination of the geographical origin of wines by means of the mineral content and the stable isotope ratios: A review. Journal of Commodity Science, Technology and Quality 47 21 J. Godshaw H. Hopfer J. Nelson S. Ebeler 2017 Comparison of Dilution, Filtration, and Microwave Digestion Sample Pretreatments in Elemental Profiling of Wine by ICP-MS. Molecules, 22 10 1609 https://doi.org/10.3390/molecules22101609 22 J. Griboff M. Horacek D. A. Wunderlin M. V Monferrán 2021 Differentiation Between Argentine and Austrian Red and White Wines Based on Isotopic and Multi-Elemental Composition. Frontiers in Sustainable Food Systems, 5 657412 https://doi.org/10.3389/fsufs.2021.657412 23 E. Hatzakis 2019 Nuclear Magnetic Resonance (NMR) Spectroscopy in Food Science: A Comprehensive Review. Comprehensive Reviews in Food Science and Food Safety, 18 1 189–220 https://doi.org/10.1111/1541-4337.12408 24 S. A. Hicks I. Strümke V. Thambawita M. Hammou M. A. Riegler P. Halvorsen S. Parasa 2022 On evaluation metrics for medical applications of artificial intelligence. Scientific Reports, 12 1 5979 https://doi.org/10.1038/s41598-022-09954-8 25 and Wine International Organisation Of Vine 2024 International Standard For The Labelling Of Wines. https://www.oiv.int/sites/default/files/publication/2024-03/OIV-%20Wine%20labelling%20Standard%20EN_2024%20final%20.pdf 26 X. Kang Y. Zhao Z. Tan 2023 An explainable machine learning for geographical origin traceability of mussels Mytilus edulis based on stable isotope ratio and compositions of C, N, O and H. Journal of Food Composition and Analysis, 123 105508 https://doi.org/10.1016/j.jfca.2023.105508 27 P. Kment M. Mihaljevič V. Ettler O. Šebek L. Strnad L. Rohlová 2005 Differentiation of Czech wines using multielement composition – A comparison with vineyard soil. Food Chemistry, 91 1 157–165 https://doi.org/10.1016/j.foodchem.2004.06.010 28 C. Van Leeuwen J.-C. Barbe P. Darriet O. Geffroy E. Gomès S. Guillaumie P. Helwi J. Laboyrie G. Lytra N. L. Menn S. Marchand M. Picard A. Pons A. Schüttler C. Thibon 2020 Recent advancements in understanding the terroir effect on aromas in grapes and wines: This article is published in cooperation with the XIIIth International Terroir Congress November 17-18 2020, Adelaide, Australia. Guest editors: Cassandra Collins and Roberta De Bei. OENO One, 54 4 29 I. Le Mao G. Da Costa T. Richard 2023 1H-NMR metabolomics for wine screening and analysis. OENO One, 57 1 15–31 https://doi.org/10.20870/oeno-one.2023.57.1.7134 30 C. Li X. Kang J. Nie A. Li M. A. Farag C. Liu K. M. Rogers J. Xiao Y. Yuan 2023 Recent advances in Chinese food authentication and origin verification using isotope ratio mass spectrometry. Food Chemistry, 398 133896 https://doi.org/10.1016/j.foodchem.2022.133896 31 M. M. M. Lima D. Hernandez A. Yeh Reiter T R. C Runnebaum 2021 Reproducibility of elemental profile across two vintages in Pinot noir wines from fourteen different vineyard sites (2021). Food Research International. 141, 110045. https://doi.org/10.1016/j.foodres.2020.110045 32 M. M. M. Lima D. Hernandez R. C Runnebaum 2023 Reproducibility of the Elemental Profile of Pinot Noir Wines: A Comparison across Three Vintages. ACS Food Science & Technology, 3 10 1646–1653 https://doi.org/10.1021/acsfoodscitech.3c00183 33 M. Ma G. Zhao B. He Q. Li H. Dong S. Wang Z. Wang 2021 XGBoost-based method for flash flood risk assessment. Journal of Hydrology, 598 126382 https://doi.org/10.1016/j.jhydrol.2021.126382 34 A. Marre A. Combaud L. Chalumeau C. Philbiche 2012 Le concept de terroir en Champagne: Un outil adaptable à toutes les échelles. 35 E. Nistor A. G. Dobrei G. B. Mattii A. Calcium and Potassium Accumulation During The Growth Season in Cabernet Sauvignon and Merlot Grape Variety Dobrei 2022 Plants, 11, 1536. https://doi.org/10.3390/plants11121536 36 K. Pasvanka M. Kostakis M. Tarapoulouzi P. Nisianakis N. S. Thomaidis C. Proestos 2021 ICP–MS Analysis of Multi-Elemental Profile of Greek Wines and Their Classification According to Variety, Area and Year of Production. Separations, 8 8 119 https://doi.org/10.3390/separations8080119 37 F. Pedregosa G. Varoquaux A. Gramfort V. Michel B. Thirion O. Grisel M. Blondel A. Müller J. Nothman G. Louppe P. Prettenhofer R. Weiss V. Dubourg J. Vanderplas A. Passos D. Cournapeau M. Brucher M. Perrot É. Duchesnay 2012 Scikit-learn: Machine Learning in Python. https://doi.org/10.48550/ARXIV.1201.0490 38 S. Pérez-Magariño 2004 Comparative study of artificial neural network and multivariate methods to classify Spanish DO rose wines. Talanta, 62 5 983–990 https://doi.org/10.1016/j.talanta.2003.10.019 39 M. Perini L. Bontempo 2022 Liquid Chromatography coupled to Isotope Ratio Mass Spectrometry (LC-IRMS): A review. TrAC Trends in Analytical Chemistry, 147 116515 https://doi.org/10.1016/j.trac.2021.116515 40 P. Pohl 2007 What do metals tell us about wine? TrAC Trends in Analytical Chemistry, 26 9 941–949 https://doi.org/10.1016/j.trac.2007.07.005 41 A. Popîrdă C. E. Luchian V. V. Cotea L. C. Colibaba E. C. Scutarașu A. M Toader 2021 A Review of Representative Methods Used in Wine Authentication. Agriculture, 11 3 42 R. K. R. Ranaweera A. M. Gilmore S. E. P. Bastian D. L. Capone D. W Jeffery 2022 Spectrofluorometric analysis to trace the molecular fingerprint of wine during the winemaking process and recognise the blending percentage of different varietal wines. OENO One, 56 1 189–196 https://doi.org/10.20870/oeno-one.2022.56.1.4904 43 F. N. Salazar I. Achaerandio 2006 Comparative Study of Protein Stabilization in White Wine Using Zirconia and Bentonite: Physicochemical and Wine Sensory Analysis. Journal of Agricultural and Food Chemistry, 54 26 9955–9958 https://doi.org/10.1021/jf062632w 44 M. Schartner J. M. Beck J. Laboyrie L. Riquier S. Marchand A. Pouget 2023 Predicting Bordeaux red wine origins and vintages from raw gas chromatograms. Communications Chemistry, 6 1 247 https://doi.org/10.1038/s42004-023-01051-9 45 D. Silva-Barbieri F. N. Salazar F. López N. Brossard N. Escalona J. R Pérez-Correa 2022 Advances in White Wine Protein Stabilization Technologies. Molecules, 27 4 1251 https://doi.org/10.3390/molecules27041251 46 Y. Su Y. Li J. Zhang L. Wang K. R. Rengasamy W. Ma A. Zhang 2023 Analysis of soils, grapes, and wines for Sr isotope characterisation in Diqing Tibetan Autonomous Prefecture (China) and combining multiple elements for wine geographical traceability purposes. Journal of Food Composition and Analysis, 122 105470 https://doi.org/10.1016/j.jfca.2023.105470 47 C. K. Tanabe J. Nelson R. B. Boulton S. E. Ebeler H. Hopfer 2020 The Use of Macro, Micro, and Trace Elemental Profiles to Differentiate Commercial Single Vineyard Pinot noir Wines at a Sub-Regional Level. Molecules, 25 11 2552 https://doi.org/10.3390/molecules25112552 48 Z. Temerdashev A. Khalafyan A. Kaunova A. Abakumov V. Titarenko Akin V 2019 Using neural networks to identify the regional and varietal origin of Cabernet and Merlot dry red wines produced in Krasnodar region. Foods and Raw Materials, 124–130. https://doi.org/10.21603/2308-4057-2019-1-124-130 49 Z. Temerdashev A. Khalafyan A. Abakumov M. Bolshov V. Akin'shina A. Kaunova 2024 Authentication of selected white wines by geographical origin using ICP spectrometric and chemometric analysis. Heliyon, 10 e29607 https://doi.org/10.1016/j.heliyon.2024.e29607 50 L. Van Der Maaten G. Hinton 2008 Viualizing data using t-SNE. Journal of Machine Learning Research, 9 2579–2605 51 C. Villano M. T. Lisanti A. Gambuti R. Vecchio L. Moio L. Frusciante R. Aversano D. Carputo 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 52 J. Villette Cuéllar T Verdeil J L Delrot S Gaillard I 2020 Grapevine potassium nutrition and fruit quality in the context of climate change. Frontiers in Plant Science, 11 123 https://doi.org/10.3389/fpls.2020.00123 53 P. Virtanen R. Gommers T. E. Oliphant M. Haberland T. Reddy D. Cournapeau E. Burovski P. Peterson W. Weckesser J. Bright S. J. Van Der Walt M. Brett J. Wilson K. J. Millman N. Mayorov A. R. J. Nelson E. Jones R. Kern E. Larson Y. Vázquez-Baeza 2020 SciPy 1. 0: Fundamental algorithms for scientific computing in Python. Nature Methods, 17 3 261–272 https://doi.org/10.1038/s41592-019-0686-2 54 J. Wen J. Li D. Wang C. Li A. Robbat L. Xia 2023 Identification of geographical origin of winter jujube based on GC–MS coupled with machine-learning algorithms. Journal of Food Composition and Analysis, 124 105710 https://doi.org/10.1016/j.jfca.2023.105710 55 H. Wu G. Lin L. Tian Z. Yan B. Yi X. Bian B. Jin L. Xie H. Zhou K. M Rogers 2021 Origin verification of French red wines using isotope and elemental analyses coupled with chemometrics. Food Chemistry, 339 127760 https://doi.org/10.1016/j.foodchem.2020.127760 56 S. Zambianchi G. Soffritti L. Stagnati V. Patrone L. Morelli M. Busconi 2022 Effect of storage time on wine DNA assessed by SSR analysis. Food Control, 142 109249 https://doi.org/10.1016/j.foodcont.2022.109249 57 D. Zhang Z. Wei Y. Han Y. Duan B. Shi W. Ma 2023 A Review on Wine Flavour Profiles Altered by Bottle Aging. Molecules, 28 18