A Comparative Analysis of XGBoost and Neural Network Models for Predicting Some Tomato Fruit Quality Traits from Environmental and Meteorological Data.

The tomato as a raw material for processing is globally important and is pivotal in dietary and agronomic research due to its nutritional, economic, and health significance. This study explored the potential of machine learning (ML) for predicting tomato quality, utilizing data from 48 cultivars and 28 locations in Hungary over 5 seasons. It focused on °Brix, lycopene content, and colour (a/b ratio) using extreme gradient boosting (XGBoost) and artificial neural network (ANN) models. The results revealed that XGBoost consistently outperformed ANN, achieving high accuracy in predicting °Brix (R² = 0.98, RMSE = 0.07) and lycopene content (R² = 0.87, RMSE = 0.61), and excelling in colour prediction (a/b ratio) with a R² of 0.93 and RMSE of 0.03. ANN lagged behind particularly in colour prediction, showing a negative R² value of -0.35. Shapley additive explanation's (SHAP) summary plot analysis indicated that both models are effective in predicting °Brix and lycopene content in tomatoes, highlighting different aspects of the data. SHAP analysis highlighted the models' efficiency (especially in °Brix and lycopene predictions) and underscored the significant influence of cultivar choice and environmental factors like climate and soil. These findings emphasize the importance of selecting and fine-tuning the appropriate ML model for enhancing precision agriculture, underlining XGBoost's superiority in handling complex agronomic data for quality assessment.

Prediction of Soluble Solids and Lycopene Content of Processing Tomato Cultivars by Vis-NIR Spectroscopy.

Tomato-based products are significant components of vegetable consumption. The processing tomato industry is unquestionably in need of a rapid definition method for measuring soluble solids content (SSC) and lycopene content. The objective was to find the best chemometric method for the estimation of SSC and lycopene content from visible and near-infrared (Vis-NIR) absorbance and reflectance data so that they could be determined without the use of chemicals in the process. A total of 326 Vis-NIR absorbance and reflectance spectra and reference measurements were available to calibrate and validate prediction models. The obtained spectra can be manipulated using different preprocessing methods and multivariate data analysis techniques to develop prediction models for these two main quality attributes of tomato fruits. Eight different method combinations were compared in homogenized and intact fruit samples. For SSC prediction, the results showed that the best root mean squared error of cross-validation (RMSECV) originated from raw absorbance (0.58) data and with multiplicative scatter correction (MSC) (0.59) of intact fruit in Vis-NIR, and first derivatives of reflectance (R 2 = 0.41) for homogenate in the short-wave infrared (SWIR) region. The best predictive ability for lycopene content of homogenate in the SWIR range (R 2 = 0.47; RMSECV = 17.95 mg kg-1) was slightly lower than that of Vis-NIR (R 2 = 0.68; 15.07 mg kg-1). This study reports the suitability of two Vis-NIR spectrometers, absorbance/reflectance spectra, preprocessing methods, and partial least square (PLS) regression to predict SSC and lycopene content of intact tomato fruit and its homogenate.

Efficient HPLC Separation on a Core-C30 Column with MS2 Characterization of Isomers, Derivatives and Unusual Carotenoids from Tomato Products.

An efficient and rapid liquid chromatographic method was developed for the separation of carotenoids and their geometrical isomers in tomato products using a core C30 column of 2.6 µm particles with gradient elution of tert-butyl-methyl-ether in 2% water in methanol. Excellent separation of the major carotenoids such as lycopene, ß-carotene and lutein as well as their geometrical isomers and oxygen-containing derivatives with resolution factors ranging between 0.78 and 4.0 and selectivity of 1.01-1.63 was achieved. Validation of the developed method met the acceptance criteria concerning linearity, recovery, precision and limit of detection and quantification. Calibrations were linear with correlation coefficient (R2) values between 0.9966 and 0.9999. The limit of detection and quantification values were found to be 0.008 and 0.017 and 0.029 and 0.056 µg/mL, respectively. Recovery of 94.3-99.9%, intraday precision of 1.81-4.45% and interday precision of 3.13-6.86% were obtained. The hyphenation of liquid chromatography with diode-array and mass spectrometry was helpful in the identification of the separated carotenoids particularly the unusual di-hydroxy cyclolycopene adduct and di-methoxy lycopene determined for the first time in tomato products. Commercially available kinds of tomato juice and ketchup were evaluated based on their carotenoid content.

HPLC determination of capsaicinoids with cross-linked C18 column and buffer-free eluent.

A simple and efficient high-performance liquid chromatographic method was developed and validated for the separation and determination of capsaicin and its major dihydro- and homoderivatives in spice paprika products in 20 min with fluorescent and 35 min with mass-spectrometric detection. The separation was performed on reversed-phase chromatographic adsorbent of cross-linked endcapping with eluent consisting of 1:1 acetonitrile-water or acetonitrile-0.1% formic acid under isocratic conditions. Excellent separation of all the major and minor capsaicinoids with resolution index between 1.08 and 7.34 was achieved. The detection and quantification limits of capsaicinoids in standard material solutions were between 2 and 10 ng/mL. The lowest detectable amount of capsaicin, with fluorescent detection, was found to be <1 µg/g non-pungent spice paprika powder. The naturally occurring capsaicinoids could be distinguished from the non-capsaicinoids compounds appeared on liquid chromatography-fluorescence profile of extract from drastically processed paprika by applying mass spectroscopic detection. Hungarian spice paprika were evaluated as mild to very hot (capsaicinoid content: 334-1,660 µg/g) and chili products as very or extremely hot products (1,543-2,818 µg/g).

HPLC analysis of carotenoids from tomatoes using cross-linked C18 column and MS detection.

This study was conducted to analyze carotenoids from tomatoes by high-performance liquid chromatography using reversed-phase C18 silica having cross-linked end-capping with diode array and mass spectrometric detection. An efficient gradient elution system was developed to achieve good and reliable separation of both major and minor carotenoids as well as their isomers. Resolution of lycopene, ß-carotene and their isomers was 0.91-3.97 and 1.02-2.86 with cross-linked and conventional C18 column, respectively. The % recovery for zeaxanthin, lycopene and ß-carotene was found to be in the range of 89-97%. Limits of detection and quantification of 19.44 and 64.79 ng/mL for zeaxanthin, 15.6 and 52.4 ng/mL for lycopene and 8.28 and 27.61 ng/mL for ß-carotene were determined. More carotenoid compounds could be separated and detected with the new method as compared with conventional C18 column. Hyphenation of HPLC with photodiode array and mass spectrometry detectors assisted in detection of tetra-dehydrocarotenoid and fatty acid diesters of xanthophylls in tomato products. Content of all-trans-lycopene, ß-carotene and total carotenoid in different industrial tomatoes tested was found to range between 41.87 and 84.65, 0.89 and 1.50 and 53.22 and 112.60 µg/g fresh weight, respectively.