Skip navigation

Evolutionary optimisation of beer organoleptic properties: a simulation framework

Evolutionary optimisation of beer organoleptic properties: a simulation framework

Al-Rifaie, Mohammad Majid ORCID: 0000-0002-1798-9615 and Cavazza, Marc ORCID: 0000-0001-6113-9696 (2022) Evolutionary optimisation of beer organoleptic properties: a simulation framework. Foods, 11 (3):351. ISSN 2304-8158 (Online) (doi:

PDF (Publisher Version of Record)
35100_AL-RIFAIE_Evolutionary_optimisation_of_beer.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview


Modern computational techniques offer new perspectives for the personalisation of food properties through the optimisation of their production process. This paper addresses the personalisation of beer properties in the specific case of craft beers where the production process is more flexible. Furthermore, this work presents a solution discovery method that could be suitable for more complex, industrial setups. An evolutionary computation technique was used to map brewers’ desired organoleptic properties to their constrained ingredients to design novel recipes tailored for specific brews. While there exist several mathematical tools, using the original mathematical and chemistry formulas, or machine learning models that deal with the process of determining beer properties based on the predetermined quantities of ingredients, this work investigates an automated quantitative ingredient-selection approach. The process, which was applied to this problem for the first time, was investigated in a number of simulations by “cloning” several commercial brands with diverse properties. Additional experiments were conducted, demonstrating the system’s ability to deal with on-the-fly changes to users’ preferences during the optimisation process. The results of the experiments pave the way for the discovery of new recipes under varying preferences, therefore facilitating the personalisation and alternative high-fidelity reproduction of existing and new products.

Item Type: Article
Uncontrolled Keywords: food personalisation; beer optimisation; recipe discovery; dispersive flies optimisation
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QD Chemistry
Faculty / School / Research Centre / Research Group: Faculty of Engineering & Science
Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Related URLs:
Last Modified: 04 Mar 2022 13:06

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics