Learning-based Spectral Regression for Cocoa Bean Physicochemical Property Prediction

TL;DR

This paper presents a scalable, non-invasive spectral regression method using VIS-NIR spectroscopy and machine learning to accurately predict key physicochemical properties of cocoa beans, offering a rapid alternative to traditional laboratory analysis.

Contribution

It introduces a learning-based spectral regression approach combined with a conveyor belt VIS-NIR system for cocoa quality assessment, validated across different regions.

Findings

Achieved R2 scores over 0.98 for all properties.

Reached 0.96 accuracy on independent samples.

Demonstrated high generalization across regions.

Abstract

Cocoa bean quality assessment is essential for ensuring compliance with commercial standards, protecting consumer health, and increasing the market value of the cocoa product. The quality assessment estimates key physicochemical properties, such as fermentation level, moisture content, polyphenol concentration, and cadmium content, among others. This assessment has traditionally relied on the accurate estimation of these properties via visual or sensory evaluation, jointly with laboratory-based physicochemical analyses, which are often time-consuming, destructive, and difficult to scale. This creates the need for rapid, reliable, and noninvasive alternatives. Spectroscopy, particularly in the visible and near-infrared ranges, offers a non-invasive alternative by capturing the molecular signatures associated with these properties. Therefore, this work introduces a scalable methodology for evaluating the quality of cocoa beans by predicting key physicochemical properties from the spectral signatures of cocoa beans. This approach utilizes a conveyor belt system integrated with a VIS-NIR spectrometer, coupled with learning-based regression models. Furthermore, a dataset is built using cocoa bean batches from Santander, Colombia. Ground-truth reference values were obtained through standardized laboratory analyses and following commercial cocoa quality regulations. To further evaluate the proposed methodology's generalization, performance is tested on samples collected from other Colombian regions and from Cusco, Peru. Experimental results show that the proposed models achieved R2 scores exceeding 0.98 across all physicochemical properties, and reached 0.96 accuracy on geographically independent samples. This non-destructive approach represents a suitable and scalable alternative to conventional laboratory methods for quality assessment across the cocoa production chain.