Machine learning models for terroir classification and blend similarity prediction: A proof-of-concept to enhance cocoa quality evaluation

Abstract

Flavour is a key quality attribute of cocoa, essential for industry standards and consumer preferences. Automated methods for assessing flavour quality support industrial laboratories in achieving high sample throughput. Targeted and untargeted HS-SPME-GC–MS chromatographic fingerprints of cocoa volatiles from fermented beans and liquors, combined with machine learning (ML), are used for terroir qualification, enabling effective origin classification with both approaches. The targeted method, which aims to identify chemical patterns associated with sensory attributes is used for flavour comparison of origin with a reference. The similarity analysis successfully identified the most suitable origin to create new blends with a similar flavour to the industry standard. The resulting ML, model based on odorants distribution, enabled the prediction of similarity of blends to the industrial reference with an accuracy of 88 %, a sensitivity of 90 % and a specificity of 84 %.