Applying infrared radiation and machine learning to optimize wine production Wine AI

Institutional research project

Area

STEM

Duration

48 months

Total funds

104,000.00 EUR

Abstract

The WineAI project deals with the development of innovative digital solutions for the optimization of wine production using infrared spectroscopy and artificial intelligence algorithms.

The focus is on the development of a prototype of an innovative spectrometric device for the analysis of oenological parameters. The prototype uses specific wavelengths to detect chemical parameters of wine, such as sugar content, alcohol and potentially other important wine parameters, and their processing using machine learning for precise product characterization.

Using an FTIR spectrometer, the most important wavelengths for a particular wine from a particular winemaker will be identified, based on which an innovative prototype of an optoelectronic system with LED emitters and photodetectors will be developed, enabling selective measurement of light absorption at specific wavelengths.

The project includes the creation of a centralized, open-access digital platform for real-time data collection and analysis, the development of algorithms for automated decision-making, and the application of computer vision for visual quantification of parameters such as wine color and pH value.

All collected data will be stored in a structured database and used for further scientific processing, while the project will also include a series of educational activities aimed at transferring knowledge.

The WineAI project responds to the wine industry’s need to increase efficiency through digital transformation, with an emphasis on the availability of technology to smaller producers. The project lasts 48 months and brings together a team of experts from FERIT.

Main objectives

Strategic goal 1.

Raising scientific excellence

Specific objective 1.1.

Increasing the participation of public higher education institutions and public scientific institutes in competitive project financing

Specific objectives

The WineAI project directly contributes to the achievement of strategic objective 1. Increasing scientific excellence through a multidisciplinary approach that combines the application of advanced digital technologies, artificial intelligence and sensor systems in the context of oenological production.

Specific objective 1.1., Increasing the participation of public higher education institutions and public scientific institutes in competitive project financing, is achieved by applying and implementing this research project within a competitive institutional tender, thereby actively positioning FERIT as a relevant research component in the national scientific space.

The project team plans to publish at least three scientific papers in journals indexed in the SCOPUS and WoS databases, including A1 journals, as well as seven scientific papers in internationally reviewed proceedings of scientific conferences.

This directly achieves an indicator of success, and also contributes to the expansion of the scientific knowledge base in the field of digital oenology and smart agriculture.

The content, objectives and methodology of the project are fully aligned with the Strategy of the Faculty of Electrical Engineering, Computing and Information Technologies Osijek, which emphasizes the importance of digital transformation, applied research, interdisciplinarity and internationalization of scientific work.

Research team

Funded by the European Union - Next Generation EU. However, the views and opinions expressed are solely those of the author(s) and do not necessarily reflect those of the European Union or the European Commission. Neither the European Union nor the European Commission can be held responsible for them.