Viticulture, spanning over 7.3 million hectares worldwide, is a key economic sector that is increasingly challenged by labor shortages, rising production costs, market competition, and climate change. Addressing these issues requires monitoring the spatial and temporal variability in vineyard productivity. Traditional ground-based observations, though accurate, are time-consuming and limited in scope. Precision viticulture offers efficient, nondestructive monitoring tools by leveraging technologies such as GPS, remote sensing, and artificial intelligence. This study aims to develop and test a technological workflow using the mobile app DIGIVIT, integrated with the AgroSat platform, to estimate yield variability in vineyards. The workflow was performed during the 2023 and 2024 growing seasons in a series of vineyards near Siena (Italy) and involved two main steps: (1) spatial variability characterization using AgroSat and (2) yield estimation using the mobile DIGIVIT app. AgroSat processed Sentinel-2 NDVI data to identify homogeneous zones, while DIGIVIT used smartphone images of grape clusters to estimate the yield. Field campaigns were conducted 3 weeks before harvest to monitor representative vines within the identified zones and upload georeferenced images for cluster segmentation analysis. Validation of yield estimates against measured weights revealed a strong linear correlation (R2 = 0.91, RMSE = 41.18 g), which improved following the exclusion of a single outlier (R2 = 0.95, RMSE = 29.97 g). Vineyard-level yield predictions were compared with harvest data, resulting in overall error of 13.77% (2023) and 14.69% (2024), aligning with previously reported methods. The study demonstrates that the DIGIVIT app provides accurate, timely yield prediction, supporting farmers in harvest planning and winemaking management. The user-friendly mobile app approach facilitates a broader adoption of precision viticulture technologies among farmers, overcoming barriers related to technical expertise.

A Free Precision Viticulture Tool for Identifying Representative Sampling Zones and Estimating Yield Using Smartphone

Salvatore Filippo Di Gennaro;Riccardo Dainelli
;
Leandro Rocchi;Piero Toscano;Giorgia Orlandi;Luca Pietrantuono;Najwane Hamie;Alessandro Matese
2026

Abstract

Viticulture, spanning over 7.3 million hectares worldwide, is a key economic sector that is increasingly challenged by labor shortages, rising production costs, market competition, and climate change. Addressing these issues requires monitoring the spatial and temporal variability in vineyard productivity. Traditional ground-based observations, though accurate, are time-consuming and limited in scope. Precision viticulture offers efficient, nondestructive monitoring tools by leveraging technologies such as GPS, remote sensing, and artificial intelligence. This study aims to develop and test a technological workflow using the mobile app DIGIVIT, integrated with the AgroSat platform, to estimate yield variability in vineyards. The workflow was performed during the 2023 and 2024 growing seasons in a series of vineyards near Siena (Italy) and involved two main steps: (1) spatial variability characterization using AgroSat and (2) yield estimation using the mobile DIGIVIT app. AgroSat processed Sentinel-2 NDVI data to identify homogeneous zones, while DIGIVIT used smartphone images of grape clusters to estimate the yield. Field campaigns were conducted 3 weeks before harvest to monitor representative vines within the identified zones and upload georeferenced images for cluster segmentation analysis. Validation of yield estimates against measured weights revealed a strong linear correlation (R2 = 0.91, RMSE = 41.18 g), which improved following the exclusion of a single outlier (R2 = 0.95, RMSE = 29.97 g). Vineyard-level yield predictions were compared with harvest data, resulting in overall error of 13.77% (2023) and 14.69% (2024), aligning with previously reported methods. The study demonstrates that the DIGIVIT app provides accurate, timely yield prediction, supporting farmers in harvest planning and winemaking management. The user-friendly mobile app approach facilitates a broader adoption of precision viticulture technologies among farmers, overcoming barriers related to technical expertise.
2026
Istituto per la BioEconomia - IBE
cluster segmentation
image analysis
sampling optimization
sentinel-2
spatial variability
yield mapping
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/20.500.14243/592721
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact