Prediction of coffee sensory attributes using near-infrared spectroscopy
DOI:
https://doi.org/10.25186/.v20i.2369Abstract
Cup tasting is the traditional method for evaluating coffee beverage quality. However, sensory analysis has several limitations, including subjectivity, high costs and the challenge of establishing desirable limits for different quality attributes. Therefore, this study aimed to predict coffee sensory attributes based on near-infrared (NIR) spectra of roasted and ground coffee samples. For that, an experiment was conducted during the 2020-2021 harvest season in the Zona da Mata region of Minas Gerais State, Southeastern Brazil, involving seven arabica coffee fields. A total of 180 coffee samples were harvested, processed, and evaluated through sensory analysis following the Specialty Coffee Association protocol. Subsequently, regression models using NIR spectra (1000 to 2500 nm) coupled with Partial least squares (PLS) and PLS-OPS (ordered predictors selection) were developed. The PLS-OPS models yielded the best results, with correlation coefficients (rP) ranging from 0.78 to 0.82 and prediction errors (RMSEP) between 0.15 and 0.13 for aftertaste, overall
perception, body, and balance. While predictions for aroma, flavor, and acidity require further improvement, the other attributes showed performance comparable to more complex analytical techniques. These findings demonstrate that NIR spectroscopy, combined with advanced chemometric modeling, offers a promising, cost-effective alternative for predicting coffee sensory quality.
Key words: Coffea arabica L.; cup quality analysis; digital agriculture; proximal sensing.
References
ABADI, M. et al. TensorFlow: Large-scale machine learning on heterogeneous systems, Available in: https://arxiv.org/abs/1603.04467 [Preprint] 2015.
AGNOLETTI, B. Z. et al. Multivariate calibration applied to study of volatile predictors of arabica coffee quality. Food Chemistry, 367:130679, 2022.
ALVARES, C. A. et al. Köppen’s climate classification map for Brazil. Meteorologische Zeitschrift, 22(6):711-728, 2013.
ASSIS, C. et al. Prediction of lignin content in different parts of sugarcane using near-infrared spectroscopy (NIR), ordered predictors selection (OPS), and partial least squares (PLS). Applied Spectroscopy, 71(8):2001-2012, 2017.
BAQUETA, M. R. et al. Brazilian Canephora coffee evaluation using NIR spectroscopy and discriminant chemometric techniques. Journal of Food Composition and Analysis, 116:105065, 2023.
BAQUETA, M. R.; COQUEIRO, A.; VALDERRAMA, P. Brazilian coffee blends: A simple and fast method by near‐infrared spectroscopy for the determination of the sensory attributes elicited in professional coffee cupping. Journal of Food Science, 84(6):1247-1255, 2019.
BARBIN, D. F. et al. Application of infrared spectral techniques on quality and compositional attributes of coffee: An overview. Food Research International, 61:23-32, 2014.
BELCHIOR, V. et al. Attenuated total reflectance fourier transform spectroscopy (ATR-FTIR) and chemometrics for discrimination of espresso coffees with different sensory characteristics. Food Chemistry, 273:178-185, 2019.
BELCHIOR, V. et al. FTIR and chemometrics as effective tools in predicting the quality of specialty coffees. Food Analytical Methods, 13(1):275-283, 2020.
BELCHIOR, V.; BOTELHO, B. G.; FRANCA, A. S. Comparison of spectroscopy-based methods and chemometrics to confirm classification of specialty coffees. Foods, v. 11(11):1655, 2022.
BERTONE, E. et al. Simultaneous determination by NIR spectroscopy of the roasting degree and Arabica/Robusta ratio in roasted and ground coffee. Food Control, 59:683-689, 2016.
BOAVENTURA, P. S. M. et al. Value co-creation in the specialty coffee value chain: The third-wave coffee movement. Revista de Administração de Empresas, 58(3):254-266. 2018.
CAPORASO, N. et al. Non-destructive analysis of sucrose, caffeine and trigonelline on single green coffee beans by hyperspectral imaging. Food Research International, 106(12):193-203, 2018.
CATELANI, T. A. et al. Real-time monitoring of a coffee roasting process with near infrared spectroscopy using multivariate statistical analysis: A feasibility study. Talanta, 179:292-299, 2018.
CHENG, B. et al. Influence of genotype and environment on coffee quality. Trends in Food Science & Technology, 57:20-30, 2016.
CORRÊDO, L. P. et al. Near-infrared spectroscopy as a tool for monitoring the spatial variability of sugarcane quality in the fields. Biosystems Engineering, 206:150-161, 2021.
CORREIA, R. M. et al. Portable near infrared spectroscopy applied to quality control of Brazilian coffee. Talanta, 176(6):59-68, 2018.
CRAIG, A. P. et al. Application of elastic net and infrared spectroscopy in the discrimination between defective and non-defective roasted coffees. Talanta, 128:393-400, 2014.
CRAIG, A. P. et al. Mid infrared spectroscopy and chemometrics as tools for the classification of roasted coffees by cup quality. Food Chemistry, 245(11):1052-1061, 2018.
DE ARAÚJO, T. K. L. et al. Non-destructive authentication of Gourmet ground roasted coffees using NIR spectroscopy and digital images. Food Chemistry, 364:130452, 2021.
DE PAULO, E. H. et al. Study of coffee sensory attributes by ordered predictors selection applied to 1H NMR spectroscopy. Microchemical Journal, 190:108739, 2023.
DECAZY, F. et al. Quality of different honduran coffees in relation to several environments. Journal of Food Science, 68(7):2356-2361. 2003.
DI DONFRANCESCO, B.; GUTIERREZ GUZMAN, N.; CHAMBERS, E. Comparison of results from cupping and descriptive sensory analysis of colombian brewed coffee. Journal of Sensory Studies, 29(4):301-311, 2014.
ESTEBAN-DÍEZ, I.; GONZÁLEZ-SÁIZ, J. M.; PIZARRO, C. Prediction of sensory properties of espresso from roasted coffee samples by near-infrared spectroscopy. Analytica Chimica Acta, 525(2):171-182, 2004.
FERIA-MORALES, A. M. Examining the case of green coffee to illustrate the limitations of grading systems/expert tasters in sensory evaluation for quality control. Food Quality and Preference, 13(6):355-367, 2002.
FORINA, M. et al. Selection of useful predictors in multivariate calibration. Analytical and Bioanalytical Chemistry, 380:397-418, 2004.
GUIMARÃES, E. R. et al. The brand new Brazilian specialty coffee market. Journal of Food Products Marketing, 25(1):49-71, 2019.
GUIMARÃES, E. R.; GONZAGA DE CASTRO JÚNIOR, L.; CARVALHO DE ANDRADE, H. C. A terceira onda do café em Minas Gerais. Organizações Rurais e Agroindustriais, 18(3):214-227. 2016.
KENNARD, R.; STONE, L. Computer aided design of experiments. Technometrics, 11(1):137-148, 1969.
LÄDERACH, P. et al. Systematic agronomic farm management for improved coffee quality. Field Crops Research, 120(3):321-329, 2011.
LEVATE MACEDO, L. et al. Evaluation of chemical properties of intact green coffee beans using near‐infrared spectroscopy. Journal of the Science of Food and Agriculture, 10(8):3500-3507, 2021.
MEDINA, J. et al. Comparison of attenuated total reflectance mid-infrared, near infrared, and 1 h-nuclear magnetic resonance spectroscopies for the determination of coffee’s geographical origin. International Journal of Analytical Chemistry, Article ID 7210463, 8 pages, 2017.
MUTZ, Y. S. et al. Feasibility of NIR spectroscopy coupled with chemometrics for classification of Brazilian specialty coffee. Food Control, 149:109696, 2023.
NICOLAÏ, B. M. et al. Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review. Postharvest Biology and Technology, 46(2):99-118, 2007.
OLIVEIRA APARECIDO, L. E. et al. Maturation periods for Coffea arabica cultivars and their implications for yield and quality in Brazil. Journal of the Science of Food and Agriculture, 98(10):3880-3891, 2018.
OLIVERI, P. et al. The impact of signal pre-processing on the final interpretation of analytical outcomes - A tutorial. Analytica Chimica Acta, 1058:9-17, 2019.
PEREIRA, L. L. et al. New propositions about coffee wet processing: Chemical and sensory perspectives. Food Chemistry, 310:125943, 2020.
PIZARRO, C. et al. Use of near-infrared spectroscopy and feature selection techniques for predicting the caffeine content and roasting color in roasted coffees. Journal of Agricultural and Food Chemistry, 55(18):7477-7488, 2007.
RIBEIRO, J. S.; FERREIRA, M. M. C.; SALVA, T. J. G. Chemometric models for the quantitative descriptive sensory analysis of Arabica coffee beverages using near infrared spectroscopy. Talanta, 83(5):1352-1358, 2011.
RIBEIRO, J. S.; SALVA, T. de J. G.; SILVAROLLA, M. B. Prediction of a wide range of compounds concentration in raw coffee beans using NIRS, PLS and variable selection. Food Control, 125:128866, 2021.
ROQUE, J. V. et al. Comprehensive new approaches for variable selection using ordered predictors selection. Analytica Chimica Acta, 1075:57-70, 2019.
SANTOS, D. A. dos et al. Multi-product multivariate calibration: determination of quality parameters in soybean industrialized juices. Acta Scientiarum. Technology, 41:e37382, 2019.
SANTOS, K. M. et al. Classification of Brazilian coffee using near-infrared spectroscopy and multivariate calibration. Analytical Letters, 45(7):774-781, 2012.
SILVA NETO, F. J. da. et al. Shade trees spatial distribution and its effect on grains and beverage quality of shaded coffee trees. Journal of Food Quality, Article ID 7909467, 8 pages, 2018.
SILVA OLIVEIRA, E. C. et al. Chemical and sensory discrimination of coffee: impacts of the planting altitude and fermentation. European Food Research and Technology, 248:659-669, 2021.
SILVA, S. de A. et al. Coffee quality and its relationship with Brix degree and colorimetric information of coffee cherries. Precision Agriculture, 15:543-554, 2014.
SILVEIRA, A. de S. et al. Sensory analysis of specialty coffee from different environmental conditions in the region of Matas de Minas, Minas Gerais, Brazil. Revista Ceres, 63(4):436-443, 2016.
SPECIALTY COFFEE ASSOCIATION – SCA. Protocols and Best Practices. [s.l: s.n.]. Available in: < https://www.scith.coffee/wp-content/uploads/2021/03/SCA-Protocols-_-Best-Practices.pdf>. Access in: October 24, 2025.
TEÓFILO, R. F.; MARTINS, J. P. A.; FERREIRA, M. M. C. Sorting variables by using informative vectors as a strategy for feature selection in multivariate regression. Journal of Chemometrics, 23(1):32-48, 2009.
TOLESSA, K. et al. Prediction of specialty coffee cup quality based on near infrared spectra of green coffee beans. Talanta, 150:367-374, 2016.
UNITED STATES DEPARTMENT OF AGRICULTURE - USDA. Coffee: World Markets and Trade. Coffee: World Markets and Trade, n. December, p. 1-9, 2023a. Available in: <https://www.fas.usda.gov/data/coffee-world-markets-and-trade-12202023>. Access in: October 24, 2025.
UNITED STATES DEPARTMENT OF AGRICULTURE - USDA. Coffee - Semi-annual report. Available in: <https://www.fas.usda.gov/data/brazil-coffee-semi-annual-8>. Access in: October 24, 2025.
VELOSO, T. G. R. et al. Effects of environmental factors on microbiota of fruits and soil of Coffea arabica in Brazil. Scientific Reports, 10:14692, 2020.
VIEIRA, L. S. et al. Building robust models for identification of adulteration in olive oil using FT-NIR, PLS-DA and variable selection. Food Chemistry, 345:128866, 2021.
WANG, H. et al. Fruit quality evaluation using spectroscopy technology: A review. Sensors, 15(5):11889-11927, 2015.
WANG, Z. et al. A novel variable selection method based on ordered predictors selection and successive projections algorithm for predicting gastrodin content in fresh gastrodia elata using fourier transform near-infrared spectroscopy and chemometrics. Foods, 12(24):4435, 2023.
WINKLER-MOSER, J. K. et al. Detection of corn adulteration in Brazilian Coffee (Coffea arabica) by tocopherol profiling and near-infrared (NIR) spectroscopy. Journal of Agricultural and Food Chemistry, 63(49):10662-10668, 2015.
WORKU, M. et al. Effect of altitude on biochemical composition and quality of green arabica coffee beans can be affected by shade and postharvest processing method. Food Research International, 105:278-285, 2018.
XU, S. et al. Comparison of multivariate methods for estimating selected soil properties from intact soil cores of paddy fields by Vis–NIR spectroscopy. Geoderma, 310:29-43, 2018.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Coffee Science - ISSN 1984-3909The copyright of the articles published in this journal belongs to the authors, with the journal holding the first publication rights. As the articles are published in this journal under open access, they may be freely used, with proper attribution, for educational and non-commercial purposes
