Abstract

The Chilean wine industry has evolved over decades, propelling Chile to become the leading exporter in Latin America and fourth globally, with revenues exceeding USD 2 billion annually. There are over 130,000 hectares dedicated to vine cultivation, yielding an annual wine production of 13 million hectoliters. Moreover, this industry contributes 0.5% to the GDP and generates over 100,000 direct jobs. However, the decrease in global wine consumption and the sustained increase in production costs in Chile have affected the profitability of this industry and have prioritized the control and reduction of operational costs.

The final filtration of wine is one of the most critical stages within the production process, as it ensures the quality and microbiological stability of the wine during the bottling process. This stage is characterized by high uncertainty due to the nature, type, and concentration of particles that the wine may contain.      

To evaluate the particle content and its impact, comprehensive indicators are used based on physical analysis of samples through filtration tests on a laboratory scale, which requires trained technicians dedicated to conducting these analyses. Additionally, the high solids content in the wine during its elaboration only allows these methods to be used once the wine is clarified and ready for bottling. This does not allow for early production planning or may result in differences in productivity and costs compared to what was planned.

This research aims to contribute to operational decision-making by using comprehensive indicators in the final wine filtration stage. To achieve this, the level of adoption of these methods in the Chilean industry is studied, the importance of their use for decision-makers is characterized, and a machine learning model is proposed to estimate their value throughout the production process.