Prediction of specialty coffee flavors based on near-infrared spectra using machine- and deep-learning methods

Models for predicting coffee yield from chemical characteristics of soil and leaves using machine learning

BACKGROUND

Coffee farming constitutes a substantial economic resource, representing a source of income for several countries due to the high consumption of coffee worldwide. Precise management of coffee crops involves collecting crop attributes (characteristics of the soil and the plant), mapping, and applying inputs according to the plants' needs. This differentiated management is precision coffee growing and it stands out for its increased yield and sustainability.

RESULTS

This research aimed to predict yield in coffee plantations by applying machine learning methodologies to soil and plant attributes. The data were obtained in a field of 54.6 ha during two consecutive seasons, applying varied fertilization rates in accordance with the recommendations of soil attribute maps. Leaf analysis maps also were monitored with the aim of establishing a correlation between input parameters and yield prediction. The machine-learning models obtained from these data predicted coffee yield efficiently. The best model demonstrated predictive fit results with a Pearson correlation of 0.86. Soil chemical attributes did not interfere with the prediction models, indicating that this analysis can be dispensed with when applying these models.

CONCLUSION

These findings have important implications for optimizing coffee management and cultivation, providing valuable insights for producers and researchers interested in maximizing yield using precision agriculture. © 2024 Society of Chemical Industry.

The Potential of NIR Spectroscopy and Chemometrics to Discriminate Roast Degrees and Predict Volatiles in Coffee

This study aimed to establish a rapid and practical method for monitoring and predicting volatile compounds during coffee roasting using near-infrared (NIR) spectroscopy coupled with chemometrics. Washed Arabica coffee beans from Ethiopia and Congo were roasted to industry-validated light, medium, and dark degrees. Concurrent analysis of the samples was performed using gas chromatography-mass spectrometry (GC-MS) and NIR spectroscopy, generating datasets for partial least squares (PLS) regression analysis. The results showed that NIR spectroscopy successfully differentiated the differently roasted samples, similar to the discrimination achieved by GC-MS. This finding highlights the potential of NIR spectroscopy as a rapid tool for monitoring and standardizing the degree of coffee roasting in the industry. A PLS regression model was developed using Ethiopian samples to explore the feasibility of NIR spectroscopy to indirectly measure the volatiles that are important in classifying the roast degree. For PLSR, the data underwent autoscaling as a preprocessing step, and the optimal number of latent variables (LVs) was determined through cross-validation, utilizing the root mean squared error (RMSE). The model was further validated using Congo samples and successfully predicted (with R2 values > 0.75 and low error) over 20 volatile compounds, including furans, ketones, phenols, and pyridines. Overall, this study demonstrates the potential of NIR spectroscopy as a practical and rapid method to complement current techniques for monitoring and predicting volatile compounds during the coffee roasting process.

A Vis/NIR spectra-based approach for identifying bananas infected with Colletotrichum musae

Introduction

Anthracnose of banana caused by Colletotrichum species is one of the most serious post-harvest diseases, which can cause significant yield losses. Clarifying the infection mechanism of the fungi using non-destructive methods is crucial for timely discriminating infected bananas and taking preventive and control measures.

Methods

This study presented an approach for tracking growth and identifying different infection stages of the C. musae in bananas using Vis/NIR spectroscopy. A total of 330 banana reflectance spectra were collected over ten consecutive days after inoculation, with a sampling rate of 24 h. The four-class and five-class discriminant patterns were designed to examine the capability of NIR spectra in discriminating bananas infected at different levels (control, acceptable, moldy, and highly moldy), and different time at early stage (control and days 1-4). Three traditional feature extraction methods, i.e. PC loading coefficient (PCA), competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA), combining with two machine learning methods, i.e. partial least squares discriminant analysis (PLSDA) and support vector machine (SVM), were employed to build discriminant models. One-dimensional convolutional neural network (1D-CNN) without manually extracted feature parameters was also introduced for comparison.

Results

The PCA-SVM and·SPA-SVM models had good performance with identification accuracies of 93.98% and 91.57%, 94.47% and 89.47% in validation sets for the four- and five-class patterns, respectively. While the 1D-CNN models performed the best, achieving an accuracy of 95.18% and 97.37% for identifying infected bananas at different levels and time, respectively.

Discussion

These results indicate the feasibility of identifying banana fruit infected with C. musae using Vis/NIR spectra, and the resolution can be accurate to one day.

Quality Assessment of Ground Coffee Samples from Greek Market Using Various Instrumental Analytical Methods, In Silico Studies and Chemometrics

Coffee is one of the most widely consumed beverages worldwide due to its sensory and potential health-related properties. In the present comparative study, a preparation known as Greek or Turkish coffee, made with different types/varieties of coffee, has been investigated for its physicochemical attributes (i.e., color), antioxidant/antiradical properties, phytochemical profile, and potential biological activities by combining high-throughput analytical techniques, such as infrared spectroscopy (ATR-FTIR), liquid chromatography-tandem mass spectrometry (LC-MS/MS), and in silico methodologies. The results of the current study revealed that roasting degree emerged as the most critical factor affecting these parameters. In particular, the L* color parameter and total phenolic content were higher in light-roasted coffees, while decaffeinated coffees contained more phenolics. The ATR-FTIR pinpointed caffeine, chlorogenic acid, diterpenes, and quinic esters as characteristic compounds in the studied coffees, while the LC-MS/MS analysis elucidated various tentative phytochemicals (i.e., phenolic acids, diterpenes, hydroxycinnamate, and fatty acids derivatives). Among them, chlorogenic and coumaric acids showed promising activity against human acetylcholinesterase and alpha-glucosidase enzymes based on molecular docking studies. Therefore, the outcomes of the current study provide a comprehensive overview of this kind of coffee preparation in terms of color parameters, antioxidant, antiradical and phytochemical profiling, as well as its putative bioactivity.

Near-infrared spectroscopy as a green technology to monitor coffee roasting

Wet chemistry methods are traditionally used to evaluate the quality of a coffee beverage and its chemical characteristics. These old methods need to be replaced with more rapid, objective, and simple analytical methods for routine analysis. Near-infrared spectroscopy is an increasingly popular technique for nondestructive quality evaluation called a green technology. Our study aimed to apply near-infrared spectroscopy to evaluate the quality of coffee samples of different origin (Brazil, Guatemala, Peru, and Kongo). Particularly, we analyzed the roasting time and its effect on the quality of coffee. The colorimetric method determined a relation between the coffee color and the time of roasting. Partial least squares regression analysis assessed a possibility of predicting the roasting conditions from the near-infrared spectra. The regression results confirmed the possibility of applying near-infrared spectra to estimate the roasting conditions. The correlation between the spectra and the roasting time had R2 values of 0.96 and 0.95 for calibration and validation, respectively. The root mean square errors of prediction were low – 0.92 and 1.05 for calibration and validation, respectively. We also found a linear relation between the spectra and the roasting power. The quality of the models differed depending on the coffee origin and sub-region. All the coffee samples showed a good correlation between the spectra and the brightness (L* parameter), with R2 values of 0.96 and 0.95 for the calibration and validation curves, respectively. According to the results, near-infrared spectroscopy can be used together with the chemometric analysis as a green technology to assess the quality of coffee.

Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques

The quality control for fruit maturity inspection is a key issue in fruit packaging and international trade. The quantification of Soluble Solids (SS) in fruits gives a good approximation of the total sugar concentration at the ripe stage, and on the other hand, SS alone or in combination with acidity is highly related to the acceptability of the fruit by consumers. The non-destructive analysis based on Visible (VIS) and Near-Infrared (NIR) spectroscopy has become a popular technique for the assessment of fruit quality. To improve the accuracy of fruit maturity inspection, VIS−NIR spectra models based on machine learning techniques are proposed for the non-destructive evaluation of soluble solids in considering a range of variations associated with varieties of stones fruit species (peach, nectarine, and plum). In this work, we propose a novel approach based on a Convolutional Neural Network (CNN) for the classification of the fruits into species and then a Feedforward Neural Network (FNN) to extract the information of VIS−NIR spectra to estimate the SS content of the fruit associated to several varieties. A classification accuracy of 98.9% was obtained for the CNN classification model and a correlation coefficient of Rc>0.7109 for the SS estimation of the FNN models was obtained. The results reported show the potential of this method for a fast and on-line classification of fruits and estimation of SS concentration.

Does Coffee Have Terroir and How Should It Be Assessed?

The terroir of coffee is defined as the unique sensory experience derived from a single origin roasted coffee that embodies its source. Environmental conditions such as temperature, altitude, shade cover, rainfall, and agronomy are considered the major parameters that define coffee terroir. However, many other parameters such as post-harvest processing, roasting, grinding, and brewing can combine to influence the perception of terroir. In this review, we discuss the contribution of these parameters and their influence on coffee terroir. Assessment of terroir requires defined sensory descriptors, as provided by the World Coffee Research Lexicon, and standardized roast level, grind size, and brew method. The choice of the post-harvest processing method is often environmentally dependent, suggesting that an inclusion into the coffee terroir definition is warranted. Coffee terroir is often not intentionally created but results from the contributions of the Coffea species and variety planted, environmental and agricultural parameters, and both the harvest and post-harvest method used. The unique combination of these parameters gives the consumer a unique cup of coffee, reminiscent of the place the coffee was produced.

Prediction of coffee aroma from single roasted coffee beans by hyperspectral imaging

•

This paper applied hyperspectral imaging (HSI) to predict roasted coffee aroma profile.

•

Individual roast coffee beans were analysed by HSI and aroma by GC–MS.

•

PLS models successfully predicted volatile aroma compounds in single coffee beans.

•

Beans were successfully segregated into two batches with different aroma profiles.

Coffee aroma is critical for consumer liking and enables price differentiation of coffee. This study applied hyperspectral imaging (1000–2500 nm) to predict volatile compounds in single roasted coffee beans, as measured by Solid Phase Micro Extraction-Gas Chromatography-Mass Spectrometry and Gas Chromatography-Olfactometry. Partial least square (PLS) regression models were built for individual volatile compounds and chemical classes. Selected key aroma compounds were predicted well enough to allow rapid screening (R² greater than 0.7, Ratio to Performance Deviation (RPD) greater than 1.5), and improved predictions were achieved for classes of compounds - e.g. aldehydes and pyrazines (R² ∼ 0.8, RPD ∼ 1.9). To demonstrate the approach, beans were successfully segregated by HSI into prototype batches with different levels of pyrazines (smoky) or aldehydes (sweet). This is industrially relevant as it will provide new rapid tools for quality evaluation, opportunities to understand and minimise heterogeneity during production and roasting and ultimately provide the tools to define and achieve new coffee flavour profiles.

Non-destructive prediction of the hotness of fresh pepper with a single scan using portable near infrared spectroscopy and a variable selection strategy

There has been no study on using near-infrared spectroscopy (NIRS) to predict the hotness of fresh pepper. This study is aimed at developing a non-destructive and accurate method for determining the hotness of fresh peppers using portable NIRS and the variable selection strategy. Spectra from different locations on samples were obtained non-destructively with a single scan. Quantitative models were established using partial least squares (PLS) with a variable selection method or fusion method. The results showed that near-stalk was the best spectral acquisition location for quantitative analysis. The variable selection strategy allows the selection of targeted characteristic variables and improves the results. A fusion method, namely variable adaptive boosting partial least squares (VABPLS), was selected for optimal prediction of the performance. In the optimized model, the root mean square errors of prediction for the validation set (RMSEPvs) of capsaicin, dihydrocapsaicin and pungency degree were 0.295, 0.143 and 47.770, respectively, while the root mean square errors of prediction for the prediction set (RMSEPps) collected one month later were 0.273, 0.346 and 75.524, respectively.

The Potential of Spectroscopic Techniques in Coffee Analysis—A Review

This review provides an overview of recent studies on the potential of spectroscopy techniques (mid-infrared, near infrared, Raman, and fluorescence spectroscopy) used in coffee analysis. It specifically covers their applications in coffee roasting supervision, adulterants and defective beans detection, prediction of specialty coffee quality and coffees’ sensory attributes, discrimination of coffee based on variety, species, and geographical origin, and prediction of coffees chemical composition. These are important aspects that significantly affect the overall quality of coffee and consequently its market price and finally quality of the brew. From the reviewed literature, spectroscopic methods could be used to evaluate coffee for different parameters along the production process as evidenced by reported robust prediction models. Nevertheless, some techniques have received little attention including Raman and fluorescence spectroscopy, which should be further studied considering their great potential in providing important information. There is more focus on the use of near infrared spectroscopy; however, few multivariate analysis techniques have been explored. With the growing demand for fast, robust, and accurate analytical methods for coffee quality assessment and its authentication, there are other areas to be studied and the field of coffee spectroscopy provides a vast opportunity for scientific investigation.

Vibrational Spectroscopy in Assessment of Early Osteoarthritis-A Narrative Review

Osteoarthritis (OA) is a degenerative disease, and there is currently no effective medicine to cure it. Early prevention and treatment can effectively reduce the pain of OA patients and save costs. Therefore, it is necessary to diagnose OA at an early stage. There are various diagnostic methods for OA, but the methods applied to early diagnosis are limited. Ordinary optical diagnosis is confined to the surface, while laboratory tests, such as rheumatoid factor inspection and physical arthritis checks, are too trivial or time-consuming. Evidently, there is an urgent need to develop a rapid nondestructive detection method for the early diagnosis of OA. Vibrational spectroscopy is a rapid and nondestructive technique that has attracted much attention. In this review, near-infrared (NIR), infrared, (IR) and Raman spectroscopy were introduced to show their potential in early OA diagnosis. The basic principles were discussed first, and then the research progress to date was discussed, as well as its limitations and the direction of development. Finally, all methods were compared, and vibrational spectroscopy was demonstrated that it could be used as a promising tool for early OA diagnosis. This review provides theoretical support for the application and development of vibrational spectroscopy technology in OA diagnosis, providing a new strategy for the nondestructive and rapid diagnosis of arthritis and promoting the development and clinical application of a component-based molecular spectrum detection technology.

Chromatographic Fingerprinting Strategy to Delineate Chemical Patterns Correlated to Coffee Odor and Taste Attributes

Coffee cupping includes both aroma and taste, and its evaluation considers several different attributes simultaneously to define flavor quality and therefore requires complementary data from aroma and taste. This study investigates the potential and limits of a data-driven approach to describe the sensory quality of coffee using complementary analytical techniques usually available in routine quality control laboratories. Coffee flavor chemical data from 155 samples were obtained by analyzing volatile (headspace-solid-phase microextraction-gas chromatography-mass spectrometry (HS-SPME-GC-MS)) and nonvolatile (liquid chromatography-ultraviolet/diode array detector (LC-UV/DAD)) fractions, as well as from sensory data. Chemometric tools were used to explore the data sets, select relevant features, predict sensory scores, and investigate the networks between features. A comparison of the Q model parameter and root-mean-squared error prediction (RMSEP) highlights the variable influence that the nonvolatile fraction has on prediction, showing that it has a higher impact on describing acid, bitter, and woody notes than on flowery and fruity. The data fusion emphasized the aroma contribution to driving sensory perceptions, although the correlative networks highlighted from the volatile and nonvolatile data deserve a thorough investigation to verify the potential of odor-taste integration.