Context and purpose of the study. Current remote sensing strategies rely heavily on reflectance data and energy balance modelling using thermal imagery to estimate crop water use and stress.

Valpolicella is a famous wine producing region in the province of Verona owing its fame above all to the production of two Protected Designation of Origins (PDOs) withered wines: Amarone and Recioto. In recent years, however, the wineries have been interested in the enhancement and qualitative increase of another PDO, Valpolicella Superiore. All the Valpolicella PDOs wines are produced with a unique grape blend, mainly Corvina, Corvinone, Rondinella and a range of other minor varieties.From 2019 Valpolicella product regulation has changed the grape proportion of the blend allowing new composition parameters of wines. For this reason, studying the volatile chemical profiles to support wine makers in the effort to produce high quality wines represents a field of great interest.

Winegrowing is still characterized by the extensive use of chemical fertilizers and plant protection products, despite strong recommendations to limit these practices. A part of these xenobiotics and metals are then found in grape juice and wine, causing a major health concern, as well as negatively affecting the fermentation process. In recent years, there has been renewed interest in non-Saccharomyces yeasts. These species have a wide phenotypic diversity, which would be exploited to broaden the aromatic palette of wines.

A study of « terroirs » was achieved from 2003 to 2005 in the whole vineyard of the Ré island (17, France). Over more than 1,990 ha, a cartography at the 1/10.000 scale, including characterization of climatic, pedological, geological and hydrogeological components of « Basic Terroir Units » (B.T.U.) was made. Also, a survey among wine growers was conducted. All data were treated together in a G.I.S. connected to a data base. 22 kinds of map were built (B.T.U. and components, soil water reserve, vine functioning potentials, varieties, rootstocks, viticultural practices and soil management).

It is fundamental for wineries to know the potential yield of their vineyards as soon as possible for future planning of winery logistics. As such, non-invasive image-based methods are being investigated for early yield prediction. Many of these techniques have limitations that make it difficult to implement for practical use commercially. The aim of this study was to assess whether yield can be estimated using images taken in-field with a smartphone at different phenological stages.