Development of a Dynamic Multi-Parameter Prediction Model for the Maturation Process of '<i>Ugni Blanc</i>' Grapes Using Visible and Near-Infrared Spectroscopy.

ABSTRACT: In this study, the non-destructive determination of pH, total soluble solids (TSS), total acidity (TA), reducing sugars (RS), seed total phenolic content (TPCD), and skin total phenolic content (TPCN) in Ugni Blanc grapes was performed using visible/near-infrared (Vis/NIR) spectroscopy coupled with chemometric quantitative analysis. Diffuse reflectance spectra in the 400-1507 nm range were measured using a handheld Vis-NIR spectrometer, after which the dataset was partitioned using the SPXY algorithm, accounting for joint X-Y distances. Six spectral preprocessing methods and three modeling algorithms, Partial Least Squares (PLS), Support Vector Machine Regression (SVR), and Convolutional Neural Network (CNN), were used to construct quantitative models based on full-wavelength and feature-w

SUBMITTER: Su C 

PROVIDER: S-EPMC12897312 | biostudies-literature | 2026 Jan

REPOSITORIES: biostudies-literature