Terroir 2020 banner
IVES 9 IVES Conference Series 9 International Terroir Conferences 9 Terroir 2020 9 History and innovation of terroir 9 Detection of spider mite using artificial intelligence in digital viticulture

Detection of spider mite using artificial intelligence in digital viticulture

Abstract

Aim: Pests have a high impact on yield and grape quality in viticulture. An objective and rapid detection of pests under field conditions is needed. New sensing technologies and artificial intelligence could be used for pests detection in digital viticulture. The aim of this work was to apply computer vision and deep learning techniques for automatic detection of spider mite symptoms in grapevine under field conditions. 

Methods and Results: RGB images of grapevine canopy attacked by the spider mite (Eotetranychus carpini Oud) were manually taken in commercial vineyard (Etxano, Basque Country, Spain) under natural day light conditions. Leaf segmentation in images was performed based on computer vision techniques, isolating target leaves with spider mite visual symptoms from the vineyard canopy. HSV colour space was used to consider colour variations representing symptoms on the leaves, separating these values from those of saturation and brightness of the image. Spider mite detection was done using Convolutional Neural Networks (CNN) models with an artificially augmented dataset for the classification of leaves with this pest symptoms. An accuracy surpassing 75% was obtained using a hold-out validation.

Conclusions: 

High accuracy proves the effectiveness of the trained model in the classification of grapevine leaves. Computer vision techniques were useful to image classification on the relevant pixels. Additionally, deep learning techniques provided a robust model to find complex features of spider mite visual symptoms.

Significance and Impact of the Study: Non-invasive technology and artificial intelligence shown promising results in the automatic detection of pests in commercial vineyards.

DOI:

Publication date: March 23, 2021

Issue: Terroir 2020

Type: Video

Authors

Inés Hernández1, Salvador Gutiérrez2, Sara Ceballos1, Ignacio Barrio1, Fernando Palacios1, Ana M. Diez-Navajas3, Javier Tardáguila1*

1Televitis Research Group. University of La Rioja, 26007 Logroño, Spain 
2Department of Computer Science and Engineering, University of Cádiz, 11519 Puerto Real, Spain 
3Department of Plant Production and Protection, NEIKER-Basque Institute for Agricultural Research and Development, Basque Research and Technology Alliance (BRTA), 01192 Arkaute, Spain

Contact the author

Keywords

Deep learning, computer vision, pests, grapevine, crop protection

Tags

IVES Conference Series | Terroir 2020

Citation

Related articles…

Comprendre la sensibilité des cépages, une clé pour la gestion durable de l’esca

Dans le cadre de TerclimPro 2025, Pierre Gastou a présenté un article IVES Technical Reviews. Retrouvez la présentation ci-dessous ainsi que l’article associé : https://ives-technicalreviews.eu/article/view/8300

1H NMR spectroscopy data to discriminate Petit verdot wines from three different soil types in the São Francisco valley, Brazil

Tropical wines have been produced in the São Francisco river Valley thirty years ago, in the Northeast of Brazil. The main grape cultivar used for red tropical wines is ‘Syrah’, but wines have presented fast evolution, if they were made in the first or second semester, due to the high values of pH in grapes and wines and high climate temperatures.

Transforming winemaking waste: grape pomace as a sustainable source of bioactive compounds

Grapevines (Vitis vinifera L.) are plants of great economic importance, with over 80% of grape production dedicated to wine production, yielding more than 258 million hectoliters annually [1].

Impact of urbanization on optimum wine Terroirs in the Bordeaux region sample of one township of the Entre-Deux-Mers Area

L’étude présentée porte sur une commune de l’Entre-Deux-Mers dans le bordelais. Nous caractérisons dans un premier temps les potentialités des sols vis-à-vis de la production de vins rouges de qualité (délimitation de terroirs grâce à la prise en compte des couvertures pédologiques et des caractéristiques morphométriques du terrain : pentes, expositions, convexités. Dans un second temps, nous récapitulons l’évolution historique des occupations des sols depuis 1790 : l’emplacement des vignes est ainsi localisé sur les terroirs respectifs des communes. Enfin, une étude prospective résultant d’enquêtes sur l’utilisation du foncier, situe le devenir prévisible de l’espace étudié (en particulier dans ses composantes viticoles et urbaines).

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.