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…

Phenolic composition and chromatic characteristics of blends of cv. Tempranillo wines from vines grown with different viticultural techniques in a semi-arid area

The quality and color stability of red wines are directly related to content and distribution of phenolic compounds. However, the climate change produces the asynchrony between the dates of technological and maturity of grapes. The crop-forcing technique (CF) restores the coupling between phenolic and technological ripeness while limits vineyard yields. Blending of wines is frequently used to equilibriate composition of wines and to increase their stability, color and quality. The aim of the present work is to study the phenolic composition and color of wine blends made with FW (wines from vines subjected to CF) and CW (wines for vines under the usual cultivation practices).

Historical zoning in the world

The study of the interaction between vineyards and the environment to establish the grapevines in the appropriate places has been applied in wine science for 5000 years. Advances in the field of the zoning have not been uniform in time, and have occupied a preferential place in the contributions of Roman writers of the 1st Century AC, the contemplations of Tokay (1700) and Porto (1756) and works of the second half of the 20th century. Zoning practices today integrate multidisciplinary methodologies (viticulture, enology, soils, climatology, cartography, statistics, computer science) and require further development for future application.

Novel analytical technologies for wine fingerprinting in and beyond the laboratory

For characterization, sensory designing and authentication rapid analytical technologies have become available. Some, like Proton Transfer Reaction Mass Spectrometry allow a rapid spectrum of the volatile compounds of wines. Combined with chemometrics wines can be characterized. The same approach can be used to calculate the results of virtual mixtures and allow formulation of constant quality blends. Other new techniques and portable devices based on spectroscopy allow measurements on production sites and in grocery stores, even for the smart consumer. We will present some examples of the application of these techniques for authentication of wines, both in the laboratory and on site.

Physico-chemical properties of vine pruning residues with potential as enological additive

Grapes are one of the world’s primary fruit crops, and pruning activities generate high amounts of annual wood wastes [1]. These pruning shoots contain valuable phenolic compounds and could have numerous potential applications [1,2]. Consequently, the aim of this work was to evaluate the physico-chemical properties of vine pruning residues with potential as enological additives. For this purpose, grapevine shoots from 12 varieties grown in Chile were collected during the winter of 2021.

How the physical components of the terroir can differently intervene in French wines DPO definitions.Example of Côte de Nuits in Burgundy

European regulations describe what elements must be given in the specifications of DPO determination ; mainly production conditions, links between quality and products characteristics and the physical traits of the production area. These elements are given in the “link to terroir” paragraph relating natural and human factors, detailed product characteristics linked to the geographical area and at last interactions between product originality and the geographical area.