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…

Legal protection of the vitivinicultural terroirs in Yamanashi Prefecture, Japan

This study analyses the actual situation regarding the legal protection of the vitivinicultural terroirs in Yamanashi Prefecture, the centre of Japanese wine industry with more than 150 years of wine-making tradition.

Cell-to-cell contact modulates Starmerella bacillaris early death in mixed fermentations with Saccharomyces cerevisiae in a couple-dependent way

AIM: The diversity and complexity of the fermentation ecosystem during wine making limits the successful prediction of wine characteristics. The use of selected starter cultures has allowed a better control of the fermentation process and the production of wines with established characteristics. Among them, the use of mixed fermentations with Starmerella bacillaris and Saccharomyces cerevisiae yeasts has gained attention in recent years due to the fructophylic nature of the first and the ability of this inoculation protocol to reduce the acetic acid and ethanol content of the wines.

Analysis of temporal variability of cv. Tempranillo phenology within Ribera del Duero Do (Spain) and relationships with climatic characteristics

The Ribera del Duero Designation of Origin (DO) has acquired great recognition during the last decades, being considered one of the highest quality wine producing regions in the world. This DO has grown from 6,460 ha of vineyards officially registered in 1985 to approximately 21,500 ha in 2013. The total grape production stands at around 90 million kg, with an average yield that approaches nearly 4,500 kg/ha. Most vineyards are cultivated under rainfed conditions.

Caratterizzazione vitivinicola delle “Terre del Piacenziano” ricomprese nella zona D.O.C. “colli piacentini” attraverso l’analisi sensoriale dei vini prodotti

I territori della Riserva Geologica del Piacenziano sono parte del pedeappennino piacentino e sono noti per essere la culla del Pliocene, quel periodo di storia della Terra compreso tra 5.3 e 1.8 milioni di anni fa. Gli strati argillosi e sabbiosi riccamente fossiliferi qui presenti sono da sempre oggetto di studi geo-paleontologici tant’è che il Pliocene medio (3.6-2.6 milioni di anni fa) è internazionalmente noto come Piacenziano. Le analisi sensoriali strutturate dei vini qui prodotti hanno evidenziato, soprattutto per il vino Monterosso, le positive peculiarità dei loro caratteri sensoriali e descritto gli scostamenti significativi del loro profilo sensoriale rispetto agli altri vini presi a riferimento.

What practices in the vineyard lead to the production of wines that consistently win medals?

High quality wines start in the vineyard however little is known about the role vineyard management practices play in this quality outcome. Gold medals and well-known regionality increase consumer preference for purchasing a wine. An increase in the former will certainly also drive an increase in the latter and therefore practices in production that consistently lead to gold medal winning wines will improve both the marketability of the region and its products. It is argued that vinification is the main driver of wine quality and in fact, the presence of some oak compounds is a well-known consumer and expert mark of quality. However, only select wines are vinified in oak and therefore the original grape quality at the winery door must in fact drive all further downstream vinification decisions.