Enoforum 2021
IVES 9 IVES Conference Series 9 Enoforum Web 9 Enoforum Web Conference 2021 9 A new AI-based system for early and accurate vineyard yield forecasting

A new AI-based system for early and accurate vineyard yield forecasting

Abstract

Vineyard yield forecasting is a key issue for vintage scheduling and optimization of winemaking operations. High errors in yield forecasting can be found in the wine industry, mainly due to the high spatial variability in vineyards, strong dependency on historical yield data, insufficient use of agroclimatic data and inadequate sampling methods. Today, errors can reach values within the range of 20%-30% per block. Thus, improved methodologies for early and accurate vineyard yield forecasting are needed. We proposed a new system for vineyard yield forecasting that integrates: systematic cluster counting, sampling and weight measurement; key agroclimatic parameters; vineyards spatial variability and the use of forecasting models based on artificial intelligence (AI). We carried out trials in high yield Cabernet Sauvignon (CS) vineyards located in Maule Valley (Chile), during seasons 2019 and 2020. We covered 13 blocks (66 ha) and two trellis systems (pergola and free-cordon). We characterized the spatial variability of blocks using Sentinel 2 images and NDVI analysis. We defined sampling units based on NDVI levels and we counted and sampled grape clusters and measured their weights during fruit-set and veraison. Key agroclimatic data were taken from public databases and we collected yield historical data from 2017 onwards. We trained and applied machine-learning models based on MARS, Random Forest and SVR algorithms. For the 2020 trial, in veraison, we obtained an average error of 7.6% per block against a 10.1% given by the traditional method (error is 23.5% for all the CS grapes of the company). Time dedicated to counting and sampling was significantly lower. As a result, we obtained a cost-efficient, early and accurate new system for vineyard yield forecasting.

DOI:

Publication date: April 23, 2021

Issue: Enoforum 2021

Type: Article

Authors

Cuevas-Valenzuela, José1*; Caris-Maldonado, Carlos1; Reyes-Suárez, José Antonio2; González-Rojas, Álvaro1

1 Center for Research and Innovation (CRI) Viña Concha y Toro, Ruta k-650 km 10, Pencahue, Maule, Chile
2 Bioinformatics Department, Faculty of Engineering, Universidad de Talca, Campus Lircay, Talca, Maule, Chile

Contact the author

Tags

Enoforum 2021 | IVES Conference Series

Citation

Related articles…

Exploring non-Saccharomyces wine yeasts native from Castilla-La Mancha (Spain) to enhance bioprotection and quality of wines

The current tendency to reduce SO2 in winemaking, due to its adverse effects in sensitive individuals [1], has led to the development of new techniques to mitigate SO2 absence and to exert the same antimicrobial and antioxidant effects.

Empreinte carbone et environnementale du vin en France : chiffres d’impact et bonnes pratiques à mettre en œuvre

Increasing concentrations of greenhouse gases (GHGs) in the atmosphere due to human activities are leading to a rise in the average temperature of the atmosphere. among the scenarios established by the un’s intergovernmental panel on climate change (IPCC), only two enable us to achieve the minimum objective of the paris agreements signed at cop 21 in 2015: staying below +2°c after 2050. both scenarios forecast a rapid reduction in GHG emissions as early as 2025, thanks to strong international cooperation, the priority given to sustainable development and responsible consumer choices.

Modeling from functioning of a grape berry to the whole plant

Grape quality is a complex trait that mainly refers to berry chemical composition, including sugars, organic acids, phenolics, aroma and aroma precursor compounds.

What do we know about the kerosene/petrol aroma in riesling wines?

1,1,6-Trimethyl-1,2-dihydronaphthalene (TDN) is a controversial aroma component found in Riesling wines. It belongs to the family of C13-norisoprenoids and is mainly associated with kerosene/petrol notes. TDN can add complexity to the wine aroma at medium – low concentrations and deteriorate the wine bouquet when its content is high. No TDN aromas are usually perceived in young Riesling wines, but they can appear after several years of aging due to the gradual formation of TDN. Management of TDN in Riesling wines is an actual task, since global warming can promote formation of this compound and compromise the aromatic composition of wine. Therefore, the aim of the current work was, firstly, to study the sensory particularities of TDN in Riesling wine at various concentrations. Secondly, to investigate the ability of bottle closures to absorb (scalp) TDN from Riesling wine under various storage conditions. These studies also include the comparative assessment of our findings with previously published data. METHODS: sensory analysis, GC-MS (SBSE), HPLC,1H-NMR and other methods related to the synthesis and determination of TDN. RESULTS: First of all, the method of the synthesis of highly purified TDN (95% and 99.5%) was optimized [1].

Using δ13C and hydroscapes as a tool for discriminating cultivar specific drought response

Measurement of carbon isotope discrimination in berry juice sugars at maturity (δ13C) provides an integrated assessment of water use efficiency (WUE) during the period of berry ripening, and when collected over multiple seasons can be used as an indication of drought stress response. Berry juice δ13C measurements were carried out on 48 different varieties planted in a common garden experiment in Bordeaux, France from 2014 through 2021 and were paired with midday and predawn leaf water potential measurements on the same vines in a subset of six varieties. The aim was to discriminate a large panel of varieties based on their stomatal behaviour and potentially identify hydraulic traits characterizing drought tolerance by comparing δ13C and hydroscapes (the visualisation of plant stomatal behaviour as a response to predawn water potential). Cluster analysis found that δ13C values are likely affected by the differing phenology of each variety, resulting in berry ripening of different varieties taking place under different stress conditions within the same year. We accounted for these phenological differences and found that cluster analysis based on specific δ13C metrics created a classification of varieties that corresponds well to our current empirical understanding of their relative drought tolerances. In addition, we analysed the water potential regulation of the subset of six varieties (using the hydroscape approach) and found that it was well correlated with some δ13C metrics. Surprisingly, a variety’s water potential regulation (specifically its minimum critical leaf water potential under water deficit) was strongly correlated to δ13C values under well-watered conditions, suggesting that base WUE may have a stronger impact on drought tolerance than WUE under water deficit. These results give strong insights on the innate WUE of a very large panel of varieties and suggest that studies of drought tolerance should include traits expressed under non-limiting conditions.