Non-destructive sensing technologies are gaining increasing relevance in precision viticulture for continuous monitoring of grape ripening. Among these approaches, gas-sensing and image-based phenotyping provide promising alternatives to conventional destructive laboratory analyses used to assess total soluble solids (°Bx), pH, and acidity. This preliminary methodological study presents a multi-modal framework that, under controlled laboratory conditions, integrates measurements of CO2 respiration rate with vision-derived color and morphological features to estimate key maturity indices in four red wine grape cultivars (Aglianico, Malvasia, Negroamaro, Primitivo) monitored throughout the 2025 growing season. Data were collected on six sampling dates from veraison to harvest during the 2025 growing season, resulting in 24 independent cultivar-by-date datasets (four cultivars x six sampling dates). Each dataset comprised measurements obtained from 40 to 100 berries collected from different bunches of the same cultivar. The non-destructive predictors are preprocessed via principal components analysis, and a regression model was developed using the first two principal components and cross-validated via Leave-One-Out-Cross-Validation. The results reveal strong inter-correlation among sensing modalities and demonstrate high predictive accuracy for °Bx, pH, and acidity (R2>=0.93). These findings demonstrate the feasibility of combining respiration sensing and vision as a non-destructive proxy for conventional maturity indices, and motivate future validation and adaptation of the approach under in-vineyard conditions. The present study is limited to a single growing season and vineyard site, with image and respiration measurements acquired under controlled laboratory conditions. Consequently, validation using larger datasets collected across multiple seasons, vineyard sites, and in-field conditions will be required to assess the robustness and practical applicability of the proposed approach.

Integrating respiration sensing and vision for non-destructive assessment of grapevine ripening: a preliminary methodological study

Annalisa Milella;Arianna Rana;
2026

Abstract

Non-destructive sensing technologies are gaining increasing relevance in precision viticulture for continuous monitoring of grape ripening. Among these approaches, gas-sensing and image-based phenotyping provide promising alternatives to conventional destructive laboratory analyses used to assess total soluble solids (°Bx), pH, and acidity. This preliminary methodological study presents a multi-modal framework that, under controlled laboratory conditions, integrates measurements of CO2 respiration rate with vision-derived color and morphological features to estimate key maturity indices in four red wine grape cultivars (Aglianico, Malvasia, Negroamaro, Primitivo) monitored throughout the 2025 growing season. Data were collected on six sampling dates from veraison to harvest during the 2025 growing season, resulting in 24 independent cultivar-by-date datasets (four cultivars x six sampling dates). Each dataset comprised measurements obtained from 40 to 100 berries collected from different bunches of the same cultivar. The non-destructive predictors are preprocessed via principal components analysis, and a regression model was developed using the first two principal components and cross-validated via Leave-One-Out-Cross-Validation. The results reveal strong inter-correlation among sensing modalities and demonstrate high predictive accuracy for °Bx, pH, and acidity (R2>=0.93). These findings demonstrate the feasibility of combining respiration sensing and vision as a non-destructive proxy for conventional maturity indices, and motivate future validation and adaptation of the approach under in-vineyard conditions. The present study is limited to a single growing season and vineyard site, with image and respiration measurements acquired under controlled laboratory conditions. Consequently, validation using larger datasets collected across multiple seasons, vineyard sites, and in-field conditions will be required to assess the robustness and practical applicability of the proposed approach.
2026
Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato - STIIMA (ex ITIA) Sede Secondaria Bari
Agricultural robotics, Grape ripening, Precision viticulture, Non-destructive sensing, CO2 respiration, RGB–D imaging, Color Index for Red Grapes (CIRG), Multimodal sensor fusion
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/607765
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ente

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact