Chemometric models play a critical role in the spectroscopic analysis of food, particularly with near‐infrared spectroscopy (NIRS), enabling the accurate prediction and monitoring of physicochemical properties. Although chemometric methods have proven to be useful tools in NIRS analysis, their reliability depends on rigorous validation to ensure the rigour of their predictions and their applicability. This systematic review examines validation strategies applied to regression models in NIRS‐based food analysis, emphasising the use of cross‐validation, external validation and figures of merit (FoM) as key evaluation tools. This comprehensive literature search identified trends in validation methodologies, highlighting frequent reliance on partial least squares (PLS) regression and common flaws in validation methodologies and their reporting. While external validation is considered the best approach, many studies lack it and employ cross‐validation methods solely, which may lead to overoptimistic model performance estimates. Furthermore, inconsistencies in the selection and definition of FoM hinder direct comparison across studies. This review underscores the need for increased methodological transparency and rigour in the validation of chemometric models to enhance their reliability.

Spatially offset Raman spectroscopy (SORS) is a non-invasive analytical technique that allows the analysis of samples through a container. This makes it an effective tool for studying food and beverage products, as it can measure the sample without being affected by the packaging or the container. In this study, a portable SORS equipment was used for the first time to analyse the alcoholic fermentation process of white wine. Different sample measurement arrangements were tested in order to determine the most effective method for monitoring the fermentation process and predicting key oenological parameters. The best results were obtained when the sample was directly measured through the glass container in which the fermentation was occurring. This allowed for the accurate monitoring of the process and the prediction of density and pH with a root mean square error of cross-validation (RMSECV) of 0.0029 g·L⁻¹ and 0.04, respectively, and R² values of 0.993 and 0.961 for density and pH, respectively. Additionally, the sources of variability depending on the measurement arrangements were studied using ANOVA-Simultaneous Component Analysis (ASCA).

Digital images are commonly used to monitor processes that are based on colour changes due to their simplicity and easy capture. Colour information in these images can be analysed objectively and accurately using colour histograms. One such process is olive ripening, which is characterized by changes in chemical composition, sensory properties and can be followed by changes in physical appearance, mainly colour. The reference method to quantify the ripeness of olives is the Maturity Index (MI), which is determined by trained experts assigning individual olives into a colour scale through visual inspection. Instead, this study proposes a methodology based on Chemometrics Assisted Colour Histogram-based Analytical Systems (CACHAS) to automatically assess the MI of olives based on R, G, and B colour histograms derived from digital images. The methodology was shown to be easily transferable for routine analysis and capable of controlling the ripening of olives. The study also confirms the high potential of digital images to understand the ripening process of olives (and potentially other fruits) and to predict the MI with satisfactory accuracy, providing an objective and reproducible alternative to visual inspection of trained experts.

This study explores the application of Near-Infrared Hyperspectral Imaging (NIR-HSI) as a non-destructive method for monitoring the oxidation of hazelnuts (Corylus avellana) stored under different atmospheric conditions (air, nitrogen, and vacuum) and light exposures, directly inside plastic bags, without the need for packaging removal nor sample preparation. Hazelnuts were imaged over a 78-day storage period, and data were analysed using ANOVA-Simultaneous Component Analysis (ASCA) to quantify the effects of time, atmosphere, and light on oxidation. Individual hazelnuts within each bag were segmented for analysis to study inter-hazelnut variability. Images were studied individually to detect oxidation patterns on the surface. Results indicate that time is the primary driver of oxidation, as expected, with atmosphere and light significantly impacting oxidation rates. Vacuum storage was most effective at reducing oxidation, while light exposure under ambient conditions accelerated oxidation via photooxidation. Sensory analysis confirmed that spectroscopic indicators of oxidation corresponded to perceptible sensory changes, validating NIR-HSI as a reliable tool for assessing hazelnut quality. This study underscores the potential of NIR-HSI and chemometrics for quality control and shelf-life assessment in hazelnuts and other oxidation-prone food products.