GiESCO 2019 banner
IVES 9 IVES Conference Series 9 GiESCO 9 GiESCO 2019 9 Hyperspectral imaging and cnn for on‐the‐go, non‐destructive assessment of grape composition in the vineyard

Hyperspectral imaging and cnn for on‐the‐go, non‐destructive assessment of grape composition in the vineyard

Abstract

Context and purpose of the study ‐ Knowledge of the spatial‐temporal variation of the grape composition within a vineyard may assist decision making regarding sampling and vineyard management, especially if selective harvest is aimed. To have a truthful picture of the spatial‐temporal dynamics of grape composition evolution during ripening in a vineyard, a huge amount of measurements at different timings and spatial positions are required. Unfortunately, the quick in‐field measurement of a vast number of samples is very hard for simple variables such as total soluble solids (TSS), and impossible in the case of analyzing secondary metabolites, like anthocyanin concentrations. The goal of this study was the in‐field assessment and mapping of the TSS, acidity parameters and anthocyanin concentrations in a Tempranillo (Vitis vinifera L.) vineyard, using non‐destructive, on‐the‐go hyperspectral imaging (HSI).

Material and methods ‐ HSI of grapevine canopies was carried out using a line‐scan hyperspectral camera working in the Vis‐NIR range (400‐1000 nm) installed in all‐terrain‐vehicle, moving at 5 km/h in a commercial Tempranillo (Vitis vinifera L.) vineyard, under natural illumination conditions. Measurements were carried out at several dates during the ripening period over two consecutive seasons in 2017 and 2018. TSS, titratable acidity (TA), pH and anthocyanin concentrations analyses were also performed using gold standard, wet chemistry methods for model building and validation purposes. Convolutional neural networks (CNN) were applied for the development of regression models. The prediction results from the regression models were used for mapping (using GIS software) the evolution and distribution of grape composition in time–several datesand space–the vineyard plot.

Results ‐ Prediction models were generated for the different grape composition parameters, yielding 2 determination coefficients (R ) above 0.85 for TSS and TA and ~0.70 for pH and anthocyanin concentrations respectively. The built maps illustrated the seasonal dynamics of TSS and anthocyanin accumulation in the studied vineyard. The obtained results evidenced the potential of hyperspectral imaging acquired on‐the‐go for the non‐destructive, robust and massive assessment of TSS and total anthocyanin contents in grape berries in the vineyard. HIS may become a useful tool for decision‐ making on harvest selection and berry fate for winemaking.

DOI:

Publication date: June 22, 2020

Issue: GiESCO 2019

Type: Article

Authors

Salvador GUTIÉRREZ (1), Juan FERNÁNDEZ‐NOVALES (1), Javier TARDÁGUILA (1), Maria Paz DIAGO (1)

(1) Instituto de Ciencias de la Vid y del Vino (Universidad de La Rioja, CSIC, Gobierno de La Rioja) Finca La Grajera, Ctra. Burgos Km 6. (26007) Logroño, La Rioja, Spain.

Contact the author

Keywords

spatial‐temporal variability, total soluble solids, berry anthocyanins, Vis‐NIR spectral range, acidity parameters, prediction models

Tags

GiESCO 2019 | IVES Conference Series

Citation

Related articles…

Effects of a new vacuum evaporation method on chemical and sensory properties of must and wine

A new process for vacuum evaporation was developed where evaporation takes place near the inner surface of a vortex produced by a rotor submerged in the liquid. Contrary to the state of the art the Vortex rotor process does not need a vacuum vessel but the rotating liquid creates a geometrically stable low pressure void surrounded by a vortex stabilized by the equilibrium between centrifugal forces and the pressure difference. First tests with water and sugar solutions at concentrations similar to grape must were conducted to verify the theoretical predictions, test the performance under different conditions and study the effect of various process parameters (Rösti et al 2015).

Tackling the 3D root system architecture of grapevines: a new phenotyping pipeline based on photogrammetry

Plant roots fulfil important functions as they are responsible for the acquisition of water and nutrients, for anchorage and stability, for interaction with symbionts and, in some cases, for the storage of carbohydrates. These functions are associated with the Root System Architecture (RSA, i.e. the form and the spatial arrangement of the roots in the soil). The RSA results from several biological processes (elongation, ramification, mortality…) genetically determined but with high structural plasticity.

Yield prediction assessment before bloom and at veraison in a cv. Airén high yielding vineyard in Toledo (La Mancha, Spain)

Anticipation in the possible responses of grapevines to environmental variations is key to adjust field work in view of a more effective management. This idea has been the driving force behind the current work, which seeks to understand the interaction patterns of the vine with its habitat throughout the growing cycle.

Effect of Yeast Derivative Products on Aroma compounds retention in model wine

For many years, enological research has developed commercial formulates of yeast derivatives as stabilizing agents and technological adjuvants in winemaking. These products are obtained from yeast by autolytic, plasmolytic, or hydrolytic processes that liberate many macromolecules from the yeast cell, principally polysaccharides and oligosaccharides and most specifically mannoproteins that are well known for their ability to improve tartaric stability and to reduce the occurrence of protein hazes (Ángeles Pozo-Bayón et al., 2009; Charpentier & Feuillat, 1992; Morata et al., 2018; Palomero et al., 2009).

The effects of cover cropping systems on vine physiology, berry and wine quality in a climate change scenario in Switzerland

Sustainable weed control with little detrimental effects on vine physiology, yield, berry quality, soil structure, health and biodiversity is a key factor in vineyard management. Few options are available to avoid herbicide utilization and minimize negative effects of frequent tillage on soil quality. The present project aims to investigate and develop different cover management strategies in a cool climate viticultural region in Switzerland. The impact of different treatments on vine, must and wine has been studied in an experimental vineyard in Changins, Switzerland for one year and will be continued over the next three years.