Tomography-like for hyperspectral bi-directional grape tissue reconstruction based on machine learning: Implications for diagnosis composition and precision maturation monitoring

¹ Department of Geosciences, Environment and Spatial Planning, Faculty of Sciences of the University of Porto, Rua do Campo Alegre, S/N, 4169-007 Porto, Portugal
² INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Campus da Faculdade de Engenharia da Universidade do Porto, Rua Dr. Roberto Frias, S/N, 4200-465 Porto, Portugal

Abstract

This study used a tomography-like analysis to reconstruct the hyperspectral data from different tissues of the grapes: skin, pulp, and seeds. The dataset included 216 grapes of Loureiro (VIVC 25085) and 205 Vinhão (VIVC 13100) at various dates from the veraison until the harvest. A more comprehensive spectral data analysis identified how the internal tissues are related to the total grape spectra. Each tissue was reconstructed separately by decomposing the whole grapevine hyperspectral information. The results showed that the spectral reconstruction was more successful for Loureiro than Vinhão, with a mean absolute error of 6.08% and 33.32%, respectively. Partial least squares (PLS) regression models were developed for both cultivars using the reconstructed spectral data, enabling the modelling of ºBrix, puncture force (N), chlorophyll (a.u.), and anthocyanin content (a.u.). These models exhibited strong performance, with R² > 0.8 and mean absolute percentage errors (MAPE) below 37%. This study emphasises the critical role of considering the grape’s internal tissue in assessing its maturation process. The findings introduce an innovative methodology for efficiently evaluating grape maturation dynamics and inner tissue characteristics. By highlighting the importance of internal tissue analysis, this research paves the way for expedited and accurate monitoring of grape maturation, offering valuable insights into physiological-based viticultural practices and grape quality assessment.