Macrowine 2021
IVES 9 IVES Conference Series 9 Neural networks and ft-ir spectroscopy for the discrimination of single varietal and blended wines. A preliminary study.

Neural networks and ft-ir spectroscopy for the discrimination of single varietal and blended wines. A preliminary study.


Blending wines from different grape varieties is often used in order to increase wine complexity and balance. Due to their popularity, several types of blends such as the Bordeaux blend, are protected by PDO legislation. In the case of monovarietal wines blending is forbidden, however there is no method to authenticate their status, and for this reason adulteration can are difficult to identify. Fourier Transform Infrared Spectroscopy (FT-IR) has proven successful for the discrimination of wines based on several parameters such as geographical origin and type of aging[1], while the use of Neural Networks is now used more often for the development of prediction models. FT-IR spectroscopy coupled with Neural Networks have been used to develop a prediction model for the discrimination of single varietal and blended wines. Generalized RSquare for the training set was 0,9011 and 0,689 for the validation set, while the -Loglikelihood was 3,918 for the training and 0,111 for the validation set. The misclassified rate was 0,03 for the training set and 0,11 for the validation set, showing very good potential for the use of IR spectroscopy for the authentication of single varietal and blended wines.


Publication date: September 10, 2021

Issue: Macrowine 2021

Type: Article


Marianthi Basalekou

University of West Attica,Christos, PAPPAS, Agricultural University of Athens Petros, TARANTILIS, Agricultural University of Athens Anna, Georgoulaki, University of West Attica Anna, STEFOU, University of West Attica

Contact the author


ftir, wine, blend, neural networks


Related articles…

Berry carbon (δ13C) and nitrogen (δ15N) isotopic ratio reflects within farm terroir diffferences

ÂThe natural abundance of carbon stable isotopes has been reported to be related to water availability in grapevines quite widely. In the case of nitrogen, the natural abundance of its stable isotopes is mainly affected by the nature of the source of nitrogen (organic vs. inorganic) used by the plant, though the bibliography available for grapevine is very scarce.

Quantification of Eugenol in various matrixes from hybrids vines. Case study of Armagnac white spirits production

Nowadays, winemaking is dealing with great challenges, notably climate change, disease resistance and low pesticide inputs, desire for more sustainable agricultural productions and permanent changing of consumer preference.

The vineyard of the future: producing more with less  

similar to other agricultural producers, grape growers face increasing pressure to improve productivity and production efficiency while reducing their environmental impact. Threats due to extreme climate events, as well as the uncertainty of available water and labor, provide significant challenges to the future of grape production. This presentation will provide an integrated overview of the tools and technologies being developed to address these issues and to help growers manage vineyards in the future, including vineyard design, remote and proximal sensing, automation, data management and decision support systems, and germplsm improvement. The potential impact of these advancements on vineyard productivity, fruit quality, and sustainability will be discussed.

Impacts on water availability for vitiviniculture worldwide using different potential evapotranspiration methods

Beyond the sole warming globally perceived and monitored, climate change impacts water availability. Increasing heatwaves frequency observed during the last decades

Mitigating the effects of climate change on berry composition by canopy management

Primary and secondary metabolites are major components of grape composition and their balances define wine typicality