Protected Geographical Indication Research Articles

Traditional agri-food products and sustainability – A fruitful relationship for the development of rural areas in Portugal

Abstract The protection of agri-food regional products is taking on growing importance in a market dominated by global companies and brands, often with no personality. Thirty years ago, the European Union (EU) agricultural product quality policy introduced the protection of geographical indications (GIs) for agricultural products and foodstuffs, with the aim of highlighting the quality of products resulting from a specific origin, therefore helping their communication and positioning in the market. This is important in countries with a considerable percentage of rural regions, as is the case of Portugal. Bearing this in mind, the purpose of this study is to see what are the drivers of the spatial distribution of traditional products (protected geographical indications, protected designations of origin, and traditional speciality guaranteed) in Portugal. For this purpose, the distribution of traditional products by regions and categories in Portugal will be presented. Also, Portugal’s position will be analysed and compared to the other EU countries, regarding the number of traditional products. Results show that Portugal is the country with the fourth biggest number of traditional certified products in EU territory. In the national territory, the Northern Region of Portugal has the biggest percentage of protected products, followed by Alentejo and the Centre Region of Portugal. Also, in Portugal, looking at the type of products, from a list of ten different categories of GIs, the ranking is dominated by (1) fresh meat, (2) meat products (cooked, salted, or smoked), and (3) cheese and milk-based products. If we consider that many of the aforementioned products are produced in less favoured regions, these results constitute an opportunity for their sustainable development. This benefits not only the producers, but also consumers who increasingly seek “authentic” and more natural products.

Exposure of Portuguese viticulture to weather extremes under climate change

Grape berry quality and yield are notably influenced by complex multi-scale interactions between grapevines and local environmental conditions. In established wine-growing regions, bestowing to local climatic conditions, yield and quality are mostly optimized, planting the best wine variety and applying specific cultural practices. Thus, the sustainability of the winemaking sector worldwide is being challenged by ongoing climate change, requiring adaptation at different levels. Climate change will inflict progressively dry and warm conditions on Portuguese vineyards, with changes in frequency and intensity of weather extremes. However, the future projections of these extreme events and their potential impacts on viticulture are less understood. For this purpose, in this study, seventeen climate extreme indices were calculated for the Portuguese wine denomination of origin regions/subregions, in the historical period (1981–2010) and future periods (2041–2070 and 2071–2100), under the Representative Concentration Pathway 8.5, and based on a five-member ensemble of Regional Climate Model-Global Climate Model chain simulations. Furthermore, a principal component analysis was undertaken for both precipitation and temperature extreme indices independently. We found an increase in temperature extremes in all wine regions in Portugal, particularly in the westernmost regions. Regarding the precipitation extremes, they reveal a lessening effect for future periods, accompanied by a generalized decrease of precipitation, but will remain an important threat in the northeastern regions. Conversely, the dry extremes, potentiating severe droughts, will be significantly strengthened. Lastly, it was possible to identify the most exposed and vulnerable wine regions to weather extremes in future climates. This information is critical for supporting decision-making in the sector, namely for long-term planning, climate change adaptation and risk reduction. Practical ImplicationsIn the winemaking sector, resorting to climate information is an effective way of mitigating climate-related risks to attain specific terroirs. To effectively deliver this information to winemakers, climatic vulnerability needs to be identified regionally, in order to promote suitable and locally adjusted measures and policies. In this study, Wine Protected Denomination of Origin (PDO) in Portugal are the key target of the climate (temperature and precipitation) extreme variability between present and future periods. The results provided and synthesized in this study should be able to inform winemakers by identifying potential areas of risk concerning the ongoing climate change and acting accordingly based on the potential occurrence of these climate extremes in each PDO area. Furthermore, some short-term and long-term strategies are presented to mitigate the general increase in temperature and decrease in precipitation.

Quality and Genuineness in the World of Sicilian Olive Oil

This article draws on the concept of authenticity as it is often deployed in regards to food, and specifically in regards to foods with Geographical Indication certifications (GIs). Authenticity, as a concept, does boundary work by coding some objects or subjects as authentic, defining them against inauthentic others. Power dynamics inhere in any use of the processes of authentication, which render the authentic as noteworthy (Bendix 1997). Following calls to practice the “arts of noticing” (Tsing 2015) and to question our own ethnographic categories (De Martino 1975), this article takes the case of the olive oil sector in Sicily, Italy, and Sicilian Protected Geographical Indication (PGI) extra virgin olive oil, to think through authenticity and processes of authentication through the lens of two related concepts: quality (qualità) and genuineness (genuinità). I conceptualize qualità as a top-down articulation of authenticity: Sicilian olive and olive oil producers’ articulation of authenticity and excellence in response to a global hierarchy of value (Herzfeld 2004) in which they are situated and to which they respond. Genuinità, on the other hand, I argue is a bottom-up articulation of authenticity and goodness, one concerned less with international recognition and chemical purity and more with social relationships of trust and practices of commensality. I argue that qualità is a powerful measure of authenticity and a livelihood strategy for Sicilian oliviculturalists, but that genuinità is perhaps an even more powerful measure of authenticity in its capacity to create or reinscribe social bonds.

TaqMan Probes for Plant Species Identification and Quantification in Food and Feed Traceability.

In the last few years, the traceability and labeling of processed food and feeds have gained increasing importance due to the impact that mislabeling and product fraud may have on human/animal health or on the quality of final products, such as milk, cheese, and meat, as a consequence of animal dietary. The presence of contaminants or possible frauds due to the use of alternative plant materials in food and feeds can greatly impact the economy; therefore, they are becoming important targets for product certification by competent institutional services. This is especially relevant when complex matrixes are considered, in which the visual identification of the different components is quite difficult or even impossible. Despite the existence of mandatory traceability requirements for the analysis of feed/food composition addressed by European Community regulations, the labels do not always provide a sufficient guarantee about the ingredients and additive composition of those products. In this sense, the development of new methodologies that aim to assess the traceability of feed and food complex matrixes is crucial. In this chapter, a general protocol is presented for the establishment of quantitative real-time PCR-based techniques based on TaqMan assays applied to feed/food traceability, with a special focus on applications in the areas of food and feed security (e.g., for the detection of plant species involved in allergenic reactions), fraud detection (e.g., genetically modified organisms), and certification (e.g., protected denomination of origin).

Old but still good – Comparison of malting and brewing characteristics of current and historical malting barley varieties

Historical Czech malting barley varieties Chlumecký, Stupický staročeský, Opavský Kneifel, and Diamant were tested in pilot malting and brewing tests (50 L) of 12% pale lager and compared with five Czech barley varieties recommended for the production of the beer with the protected geographical indication ‘České pivo’. The grain yield of the historical varieties (6.00–7.83 t/ha) was lower compared to the current varieties (8.23–9.39 t/ha). The malts from the historical varieties had high nitrogen content (12.45–13.89%), and low extract (75.2–78.6%, proteolytic (Kolbach index 37.4–40.9%) and cytolytic modification (friability 46.2–57.7%) was also low. Apart from lower extract yield and lower beer filtration rate, the experimental malts from the historical varieties were well processable in the pilot brewery. The sensory quality of the beers was very good (overall impression 3.3–3.8 points), fully comparable to beers made from malts from current barley varieties (3.4–3.9 points). Cluster analysis clearly differentiated the sensory profile of beers of historical and current barley varieties. The historical malting barley varieties under study may find their use mainly in the production of regional microbreweries.

Quality assessment of traditional food by NMR analysis

Traditional foods are made by high quality raw material and consolidated artisanal processes which confer particular organoleptic characteristics well appreciated worldwide. These products have been object of interest for the European Union (EU), which established to protect these precious food heritages. For this reason, PDO (Protected Denomination of Origin), PGI (Protected Geographical Indication) as well as TSG (Traditional Specialties Guaranteed) labels have been adopted to control and to protect foods and beverages with characteristics of unicity. Due to their high quality, the commercial evaluation is also quoted and therefore these products are prone to be object of fraudulent practices. Among the advanced analytical techniques, NMR spectroscopy has already proven to be very powerful in the authentication of foods also dissecting counterfeits and fraudulent practices. In the present review, the results concerning the quality assessment of traditional foods covering the period of 2010–2022 are reported as case stories and discussed. • NMR spectroscopy and chemometrics to address foods quality issues. • Development of advanced techniques in the quality and functions of traditional food. • PDO, PGI products characterization by NMR techniques.

Presence of Certain Foodborne Pathogens in Traditional Balearic Islands' Meat, Pastry, and Cheese Specialties Supported by European Union Quality Schemes, from 2018 to 2021.

The cuisine of the Balearic Islands (Spain, southern Europe) has several products of a great tradition, recognized worldwide and covered by European Union quality schemes, such as Protected Designation of Origin (PDO) and Protected Geographical Indication (PGI). Among them, the most emblematic products are sobrasada de Mallorca (a type of raw curated pork meat), ensaimada de Mallorca (pastry product), and Mahón-Menorca cheese (cow's milk cheese). During 4 consecutive years (2018-2021), the presence/absence of Escherichia coli β-glucuronidase positive (henceforth as E. coli), Listeria monocytogenes, Salmonella spp., and Staphylococcus aureus in these products has been monitored, as well as the total yeast and mold count in ensaimada de Mallorca. The results of the microbiological analysis showed that sobrasada presented similar microbiological patterns to those of other raw curated meat products (some presence of E. coli and L. monocytogenes). Furthermore, the sobrasada de Mallorca made with white pork tended to be positive in E. coli compared to other sobrasada subtypes. In the case of ensaimada, only a reduced number of cases within filled ensaimadas (with higher moisture content) presented unacceptable mold and yeast counts (>500 colony-forming unit [CFU]/g). Finally, the Mahón-Menorca cheese presented a surprising microbiology pattern: higher E. coli contamination in the pasteurized milk cheese compared to its raw counterpart. This pattern was observed for all the years, being statistically significant in 2020. This study has detected good microbiological status in the three traditional products studied. However, worrisome issues in Good Hygienic Practices have been detected for some companies that produce pasteurized milk Mahón-Menorca cheese under the PDO quality label. The companies involved and even the competent authorities should address these problems to correct this deviation in food security.

Tenderness of PGI "Ternera de Navarra" Beef Samples Determined by FTIR-MIR Spectroscopy.

Understanding meat quality attribute changes during ageing by using non-destructive techniques is an emergent pursuit in the agroindustry research field. Using beef certified samples from the protected geographical indication (PGI) "Ternera de Navarra", the primary goal of this study was to use Fourier transform infrared spectroscopy on the middle infrared region (FTIR-MIR) as a tool for the examination of meat tenderness evolution throughout ageing. Samples of the longissimus dorsi muscle of twenty young bulls were aged for 4, 6, 11, or 18 days at 4 °C. Animal carcass classification and sample proximate analysis were performed to check sample homogeneity. Raw aged steaks were analyzed by FTIR-MIR spectroscopy (4000-400 cm-1) to record the vibrational spectrum. Texture profile analysis was performed using a multiple compression test (compression rates of 20%, 80%, and 100%). Compression values were found to decrease notably between the fourth and sixth day of ageing for the three compression rates studied. This tendency continued until the 18th day for C20. For C80 and C100, there was not a clear change in the 11th and 18th days of the study. Regarding FTIR-MIR as a prediction method, it achieved an R2 lower than 40%. Using principal component analysis (PCA) of the results, the whole spectrum fingerprint was used in the discrimination of the starting and final ageing days with correct maturing time classifications. Combining the PCA treatment together with the discriminant analysis of spectral data allowed us to differentiate the samples between the initial and the final ageing points, but it did not single out the intermediate points.

In the trail of “Maçã de Alcobaça” protected geographical indication (PGI): Multielement chemometrics as a security and anti-fraud tool to depict clones, cultivars and geographical origins and nutritional value

Food fraud associated with the intentional mislabelling of non-Protected Geographical Indication (PGI) is a concern for consumers. “Maçã de Alcobaça” (Alcobaça apple) is one of the oldest Portuguese PGI products, characteristic of the main apple-growing regions in the country, being of utmost importance to develop traceability and authenticity tools to depict the PGI certification status of these products. Pulp multielement signatures were able to discriminate with moderate accuracy (65.7 %) different Royal Gala clones, grown within the same cultivation area. Moreover, Variable Importance in Projection Partial Least-Squares Discriminant Analysis (VIP-PLS-DA) allowed the discrimination of the Royal Gala samples from different PGI producers with 70.0 % accuracy. Apple PGI cultivars were also discriminated accurately (82.0 %). Expanding the approach to non-PGI production areas, several cultivars could be distinguished, according to their provenance with high accuracy, namely Starking (100.0 % accuracy), Granny Smith (100.0 % accuracy), Fuji (100.0 % accuracy), Royal Gala (86.7 % accuracy) and Reineta (90.3 % accuracy). The PGI fruit's microelement nutritional traits highlighted their higher nutritional value, an important trait for food fraud reduction, informing the consumer of the product authenticity, and providing insights on the nutritional value of these high-value market products.

Nutrient content prediction and geographical origin identification of red raspberry fruits by combining hyperspectral imaging with chemometrics

The geographical origin and the important nutrient contents greatly affect the quality of red raspberry (RRB, Rubus idaeus L.), a popular fruit with various health benefits. In this study, a chemometrics-assisted hyperspectral imaging (HSI) method was developed for predicting the nutrient contents, including pectin polysaccharides (PPS), reducing sugars (RS), total flavonoids (TF) and total phenolics (TP), and identifying the geographical origin of RRB fruits. The results showed that these nutrient contents in RRB fruits had significant differences between regions (P < 0.05) and could be well predicted based on the HSI full or effective wavelengths selected through competitive adaptive reweighted sampling (CARS) and variable iterative space shrinkage approach (VISSA). The best prediction results of PPS, RS, TF, and TP contents were achieved with the highest residual predictive deviation (RPD) values of 3.66, 3.95, 2.85, and 4.85, respectively. The RRB fruits from multi-regions in China were effectively distinguished by using the first derivative-partial least squares discriminant analysis (DER-PLSDA) model, with an accuracy of above 97%. Meanwhile, the fruits from three protected geographical indication (PGI) regions were successfully classified by using the orthogonal partial least squares discrimination analysis (OPLSDA) model, with an accuracy of above 98%. The study results indicate that HSI assisted with chemometrics is a promising method for predicting the important nutrient contents and identifying the geographical origin of red raspberry fruits.

Anatomy of Traditional Specialities Guaranteed: Analysis of the Functioning, Limitations and (Possible) Future of the Forgotten EU Quality Scheme

Abstract This article focuses on traditional specialities guaranteed (TSGs), the least researched of the EU quality schemes that also include the better known protected designation of origin (PDO) and protected geographical indication (PGI). Firstly, this contribution presents a historical account of the evolution of this quality label. Secondly, it illustrates the results of the first empirical analysis of the contents of the Single Documents for all the TSGs registered, thus providing an unprecedented view of their nature. Thirdly, it divides TSGs into six categories, which will be called ‘profiles’, in order to provide a nuanced picture of what is protected by this quality scheme and how. Finally, this work reflects on why this label has always been essentially unsuccessful in terms of number of registrations, and what could be done to revive it. It concludes that, because of the residual nature of TSGs compared with PDOs/PGIs, it is highly unlikely that TSGs will acquire more importance as market-related labels. Hence, from this point of view, discontinuing them might lead to a simplification and clarification of the EU quality schemes. However, the fact that they are residual does not mean that they are superfluous. They may nonetheless play a meaningful role as tools aimed at connecting the names of traditional products with their original recipes, thus contributing to the preservation of relevant pieces of European gastronomic heritage that would otherwise be denied any form of recognition and protection.

Consumers’ Perception and Behavior towards Geographical Indication Products: The Case of Traditional Pestil from Gümüşhane, Turkey

The main objective of this study is to assess the relationship between the level of consumers' perception of products with geographical indication (GI) and their consumption of products with GI labels. Geographically indicated products were examined within the scope of Gümüşhane fruit pulp (mulberry pestil), which was registered as a Protected Geographical Indication (PGI) in 2004. This research conducted an online survey of 166 consumers living in Gümüşhane province in Turkey. Binary logistic regression analysis method was used to identify the factors affecting the probability of consuming products with GI labels. The model results show that middle-aged, married, middle-income and consumers who correctly perceive the concept of geographical indication products are more likely to consume products with GI labels. According to the logistic regression results, the increase in consumers' level of correct perception of the product notion with GI label increases the probability of consuming products with GI label 2.5 times. The results of this study also tell us that the market share of these products can be increased by improving the consumer perception towards geographically indicated products. Policymakers can also take advantage of these insights to improve lucid understanding of how labels are actually interpreted by consumers.

Development of two-level Design of Experiments for the optimization of a HS-SPME-GC-MS method to study Greek monovarietal PDO and PGI wines

Aroma is a key element in the description of wine's hedonistic character and commercial value. The volatile compounds that compose a wine's aroma belong to various very different chemical groups and their concentration varies from ppt to ppm. Therefore, the development of an analytical method able to cover such variability is a challenging task. In the present work, arduous method development was applied to reach optimal headspace solid-phase microextraction (HS-SPME) conditions, for the characterization of wine volatilome, by using a two-level screening-to-modelling Design of Experiments (DoE) approach. The optimized and comprehensive HS-SPME-GC-MS protocol was then used for the analysis of seventy wine samples of six monovarietal Greek Protected Designation of Origin (PDO) and Protected Geographical Indication (PGI) white and red wine cultivars (Moschofilero, Assyrtiko, Savvatiano, Malagouzia, Agiorgitiko and Xinomavro). One hundred volatile metabolites were identified and semi-quantified in several concentration ranges according to variety. Fatty acids and their corresponding ethyl esters were found in higher concentrations in the white wines, while higher alcohols were characteristic for the red wines. Differences between the cultivars were evaluated through multivariate statistical analysis and PCA and OPLS-DA models. The results demonstrated that Moschofilero is a very aromatic and floral variety, as it is very rich in terpenic compounds, while Malagouzia and Agiorgitiko were characterized by isoamyl alcohol and ho-trienol, respectively.

Enhancing the Production of the Phenolic Extracts of Asparagus Using an Advanced Green Process.

Asparagus officinalis L. is a common vegetable widely consumed due to its high consumer acceptance. In addition to its flavor, green asparagus contains a high amount of bioactive compounds with health-promoting effects. In this sense, the growing concern of the public health system to promote a diet with a higher consumption of vegetables makes research on phytochemicals from this food of interest. In order to study the content of bioactive compounds from plant matrices, the combination of advanced extraction and analytical techniques within the context of green chemistry is an indispensable working model in today’s research. In the present experimental work, the composition of the phytochemicals of green asparagus from the Protected Geographical Indication (PGI) located in Huétor Tájar, Granada (Spain), was evaluated by environmentally friendly extraction techniques. In order to carry out this work, the recovery of bioactive compounds was evaluated by pressurized liquid extraction (PLE) using GRAS (Generally Recognized As Safe) solvents (mixtures of water and ethanol). The extraction was optimized using a Response Surface Methodology (RSM) based on a 24 factorial Central Composite Design (CCD). The experimental model was followed by high-performance liquid chromatography coupled to electrospray ionization time-of-flight mass spectrometry (HPLC–ESI-TOF-MS) analytical methodology for a comprehensive characterization. The optimized methodology was compared with conventional solid–liquid extraction protocols using ethanol and water. The results highlighted the potential of advanced PLE techniques compared to conventional systems for the recovery of green asparagus phytochemicals. Moreover, the analytical characterization allowed the identification and quantitation of major phenolic compounds belonging to phenolic acids and flavonoids families. Therefore, an easy, fast, and novel methodology to optimize the extraction of bioactive compounds from green asparagus has been optimized, using Green and GRAS methodology, which enables a better understanding of the bioactive composition of this widely consumed food.

Wine Tourism—A Sustainable Management Tool for Rural Development and Vineyards: Cross-Cultural Analysis of the Consumer Profile from Romania and Moldova

In recent years, tourism products and services have been oriented to offer more experiences than those of classical leisure activities for tourists. More, the COVID-19 pandemic drew a new trend in travel: the tourists are now oriented to internal offers rather than the external ones, to rural regions instead of urban ones. Romania and Moldova are two well-known international countries that are both producers and exporters of Protected Designation of Origin (PDO) and Protected Geographical Indication (PGI) wine. The aim of the paper is to analyze (qualitative and quantitative) the motivation of tourists from Romania and Moldova for wine tourism, to model the motivation according to the socio-demographic characteristics of tourists and the specific elements for travel (accommodation, frequencies of visit, average stay). For quantitative analysis, an online questionnaire by convenience sampling was used to collect the data, and statistical methods were used for analysis. Even if these countries have cultural similarities, our results indicate statistically significant different motivations and different profiles of wine tourists. By using a co-occurrence link between the terms from WoS and Scopus scientific articles with VOSviewer software, our results indicate a link between wine tourism, rural and festivals tourism, and cultural heritage. Our research fills a gap in the literature, being the first comparative research on wine tourism in Romania and Moldova.

Application of hyperspectral imaging assisted with integrated deep learning approaches in identifying geographical origins and predicting nutrient contents of Coix seeds

Coix seed (CS, Coix lachryma-jobi L. var. ma-yuen (Roman.) Stapf) has rich nutrients, including starch, protein and oil. The geographical origin with a protected geographical indication and high levels of nutrient contents ensures the quality of CS, but non-destructive and rapid methods for predicting these quality indicators remain to be explored. This paper proposed hyperspectral imaging (HSI) assisted with the integrated deep learning models of attention mechanism (AM), convolutional neural networks, and long short-term memory. The method achieved the effective wavelengths selection, the highest prediction accuracy for production region discrimination and the lowest mean absolute error and root mean squared error for nutrient contents prediction. Moreover, the wavelengths selected via the AM model were explicable and reliable for predicting the geographical origins and nutrient contents. The proposed combination of HSI with integrated deep learning models has great potential in the quality evaluation of CS.

The use of European Union instruments for branding and labelling regional food products in Estonia

The article examines how European Union rural development measures and food quality schemes are used for creating added value to regional food products in Estonia. In order to understand these processes, national food and heritage policies are analysed to highlight a lack of national instruments that would protect and promote regional specialities. The emergence of regional brands (funded by the European Union LEADER measure) is an example of an initiative to increase the visibility of regional products and food culture on the domestic market and to brand the region. Another attempt for recognising and re-regionalising local specialities is the application for the European Union Protected Geographical Indications (PGI) label for a traditional cheese sõir in south-eastern Estonia.

Traceability of the local cultivar ‘Caaveiro’ in flour mixtures used to produce Galician bread by simple sequence repeats and droplet digital polymerase chain reaction technology

SummaryThe analysis of simple sequence repeats (SSRs) and of bulk ground samples by droplet digital polymerase chain reaction (ddPCR) was investigated as an alternative to individual kernel testing for assessing the presence of local cultivars in common wheat (Triticum aestivum L.) varietal blends. The recent Protected Geographical Indication (PGI) of ‘Pan Galego’ (Galician bread) requires that the flour comprise a minimum 25% local wheat cultivars. As a test for compliance with this minimum level, wheat flours were prepared by mixing commercial flours with 0%, 5%, 20%, 25% and 30% ‘Caaveiro’ and 100% ‘Caaveiro’ and 100% commercial flours were used as controls. A second analysis was performed with a second set of wheat flours with 5% and 25% ‘Caaveiro’. These were mixed with two different commercial flours to assess the potential ability of five SSRs to identify the percentage of ‘Caaveiro’, constituting the first reference of the use of SSRs in the traceability of specific autochthonous cultivars in flour blends. ddPCR using the QX200 system platform was used to the targeted proportions across the simulated range with two out of five SSRs, indicating that they can be used in the traceability of ‘Caaveiro’ in mixed flours and breads.

Differentiating Thai Hom Mali rice cultivated inside and outside the Thung Kula Rong-Hai Plain using stable isotopic data combined with multivariate analysis

Rice geographic authentication has become an important issue in promoting food quality assurance and protection of consumer rights. Thai Hom Mali (THM) rice cultivated inside the Thung Kula Rong-Hai Plain is registered under the European Protected Geographical Indication (PGI). Stable isotope ratio (δ13C, δ15N, and δ18O) fingerprinting of THM rice cultivated inside (PGI) and outside (non-PGI) the Thung Kula Rong-Hai Plain was combined with multivariate statistical analysis, principal component analysis (PCA) and linear discrimination analysis (LDA). The stable isotopic distributions of THM rice cultivated within each province (different districts) and between provinces located inside the Thung Kula Rong-Hai Plain were also presented. The stable isotopes combined with PCA and LDA were investigated for their ability to differentiate the geographical origin of PGI and non-PGI THM rice. Although the PCA explained 87.76% of the total variance, it could not successfully classify the geographical origins of THM rice. LDA could distinguish THM rice cultivated inside and outside the Thung Kula Rong-Hai Plain with a prediction accuracy greater than 93% correct classification and 90% cross-validation.

Predicting agri-food quality across space: A Machine Learning model for the acknowledgment of Geographical Indications

Geographical Indications (GIs), as Protected Designation of Origin (PDO)and Protected Geographical Indication (PGI), offer a unique protection scheme to preserve high-quality agri-food productions and support sustainable rural development at the territorial level. However, not all the areas with traditional agri-food products are acknowledged with a GI. Examining the Italian wine sector by a geo-referenced database and a machine learning framework, we show that municipalities which obtain a GI within the subsequent 10 year period (2002–2011) can be predicted using a large set of (lagged) municipality-level data (1981–2001). We find that the Random Forest algorithm is the best model to make out-of-sample predictions of municipalities which obtain GIs. Results show that there is a sort of optimal territorial condition characterized by the successful matching of wine-growing profession (vineyards), local actors involved (number of farmers), and physical dimension of farms (middle farms). Being in a vital economic system and the distance from major urban centers also emerges among the main relevant features in predicting the success of GIs. The methodology adopted and the evidence provided lead to policy reflections, in the light of the future Common Agricultural Policy (CAP) programming period and the scheduled reform of the GI’s quality scheme.