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…

Variations of soil attributes in vineyards influence their reflectance spectra

Knowledge on the reflectance spectrum of soil is potentially useful since it carries information on soil chemical composition that can be used to the planning of agricultural practices. If compared with analytical methods such as conventional chemical analysis, reflectance measurement provides non-destructive, economic, near real-time data. This paper reports results from reflectance measurements performed by spectroradiometry on soils from two vineyards in south Brazil. The vineyards are close to each other, are on different geological formations, but were subjected to the same management. The objective was to detect spectral differences between the two areas, correlating these differences to variations in their chemical composition, to assess the technique’s potential to predict soil attributes from reflectance data.To that end, soil samples were collected from ten selected vine parcels. Chemical analysis yield data on concentration of twenty-one soil attributes, and spectroradiometry was performed on samples. Chemical differences significant to a 95% confidence level between the two studied areas were found for six soil attributes, and the average reflectance spectra were separated by this same level along most of the observed spectral domain. Correlations between soil reflectance and concentrations of soil attributes were looked for, and for ten soil traits it was possible to define wavelength domains were reflectance and concentrations are correlated to confidence levels from 95% to 99%. Partial Least Squares Regression (PLSR) analyses were performed comparing measured and predicted concentrations, and for fifteen out of 21 soil traits we found Pearson correlation coefficients r > 0.8. These preliminary results, which have to be validated, suggest that variations of concentration in the investigated soil attributes induce differences in reflectance that can be detected by spectroradiometry. Applications of these observations include the assessment of the chemical content of soils by spectroradiometry as a fast, low-cost alternative to chemical analytical methods.

Assessing the relationship between cordon strangulation, dieback, and fungal trunk disease symptom expression

Grapevine trunk diseases including Eutypa dieback are a major factor in the decline of vineyards and may lead to loss of productivity, reduced income, and premature reworking or replanting. Several studies have yielded results indicating that vines may be more likely to express symptoms of vascular disease if their health is already compromised by stress. In Australia and many other wine-growing regions it is a common practice for canes to be wrapped tightly around the cordon wire during the establishment of permanent cordon arms. It is likely that this practice may have a negative effect on health and longevity, as older cordons that have been trained in this manner often display signs of decay and dieback, with the wire often visibly embedded within the wood of the cordon. It is possible that adopting a training method which avoids constriction of the vasculature of the cordon may help to limit the onset of vascular disease symptom expression. A survey was conducted during the spring of two consecutive growing seasons on vineyards in South Australia displaying symptoms of Eutypa lata infection when symptomless shoots were 50–100 cm long. Vines were assessed as follows: (i) the proportion of cordon exhibiting dieback was rated using a 0–100% scale; (ii) the proportion of canopy exhibiting foliar symptoms of Eutypa dieback was rated using a 0–100% scale; (iii) the severity of strangulation was rated using a 0–4 point scale. Images were also taken of each vine for the purpose of measuring plant area index (PAI) using the VitiCanopy App. The goal of the survey was to determine if and to what extent any correlation exists between severity of strangulation and cordon dieback, in addition to Eutypa dieback foliar symptom expression.

Genotypic variability in root architectural traits and putative implications for water uptake in grafted grapevine

Root system architecture (RSA) is important for soil exploration and edaphic resources acquisition by the plant, and thus contributes largely to its productivity and adaptation to environmental stresses, particularly soil water deficit. In grafted grapevine, while the degree of drought tolerance induced by the rootstock has been well documented in the vineyard, information about the underlying physiological processes, particularly at the root level, is scarce, due to the inherent difficulties in observing large root systems in situ. The objectives of this study were to determine genetic differences in the root architectural traits and their relationships to water uptake in two Vitis rootstocks genotypes (RGM, 140Ru) differing in their adaptation to drought. Young rootstocks grafted upon the Riesling variety were transplanted into cylindrical tubes and in 2D rhizotrons under two conditions, well watered and moderate water stress. Root traits were analyzed by digital imaging and the amount of transpired water was measured gravimetrically twice a week. Root phenotyping after 30 days reveal substantial variation in RSA traits between genotypes despite similar total root mass; the drought-tolerant 140Ru showed higher root length density in the deep layer, while the drought-sensitive RGM was characterised by shallow-angled root system development with more basal roots and a larger proportion of fine roots in the upper half of the tube. Water deficit affected canopy size and shoot mass to a greater extent than root development and architectural-related traits for both 140Ru and RGM, suggesting vertical distribution of roots was controlled by genotype rather than plasticity to soil water regime. The deeper root system of 140Ru as compared to RGM correlated with greater daily water uptake and sustained stomata opening under water-limited conditions but had little effect on above-ground growth. Our results highlight that grapevine rootstocks have constitutively distinct RSA phenotypes and that, in the context of climate change, those that develop an extensive root network at depth may provide a desirable advantage to the plant in coping with reduced water resources.

‘Cabernet Sauvignon’ (Vitis vinifera L.) berry skin flavonol and anthocyanin composition is affected by trellis systems and applied water amounts

Trellis systems are selected in wine grape vineyards to mainly maximize vineyard yield and maintain berry quality. This study was conducted in 2020 and 2021 to evaluate six commonly utilized trellis systems including a vertical shoot positioning (VSP), two relaxed VSPs (VSP60 and VSP80), a single high wire (SH), a high quadrilateral (HQ), and a guyot (GY), combined with three levels of irrigation regimes based on different crop evapotranspiration (ETc) replacements, including a 25% ETc, 50% ETc, and 100% ETc. The results indicated SH yielded the most fruits and accumulated the most total soluble solids (TSS) at harvest in 2020, however, it showed the lowest TSS in the second season. In 2020, SH and HQ showed higher concentrations in most of the anthocyanin derivatives compared to the VSPs. Similar comparisons were noticed in 2021 as well. SH and HQ also accumulated more flavonols in both years compared to other trellis systems. Overall, this study provides information on the efficacy of trellis systems on grapevine yield and berry flavonoid accumulation in a currently warming climate.

The rootstock, the neglected player in the scion transpiration even during the night

Water is the main limiting factor for yield in viticulture. Improving drought adaptation in viticulture will be an increasingly important issue under climate change. Genetic variability of water deficit responses in grapevine partly results from the rootstocks, making them an attractive and relevant mean to achieve adaptation without changing the scion genotype. The objective of this work was to characterize the rootstock effect on the diurnal regulation of scion transpiration. A large panel of 55 commercial genotypes were grafted onto Cabernet Sauvignon. Three biological repetitions per genotype were analyzed. Potted plants were phenotyped on a greenhouse balance platform capable of assessing real-time water use and maintaining a targeted water deficit intensity. After a 10 days well-watered baseline period, an increasing water deficit was applied for 10 days, followed by a stable water deficit stress for 7 days. Pruning weight, root and aerial dry weight and transpiration were recorded and the experiment was repeated during two years. Transpiration efficiency (ratio between aerial biomass and transpiration) was calculated and δ13C was measured in leaves for the baseline and stable water deficit periods. A large genetic variability was observed within the panel. The rootstock had a significant impact on nocturnal transpiration which was also strongly and positively correlated with maximum daytime transpiration. The correlations with growth and water use efficiency related traits will be discussed. Transpiration data were also related with VPD and soil water content demonstrating the influence of environmental conditions on transpiration. These results highlighted the role of the rootstock in modulating water deficit responses and give insights for rootstock breeding programs aimed at identifying drought tolerant rootstocks. It was also helpful to better define the mechanisms on which the drought tolerance in grapevine rootstocks is based on.