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.

Download the PDF

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…

Environmental protection by means of (“Great”) vitiviniculture zonation

In the paper is discussed the first example of environmental protection, agreed in a wide term sense, by means of vitiviniculture zonations performed in Istria (Croatia) in the area of Butoniga lake

Read More

Cultivation forms and viticulture models adapting to adverse “environmental” conditions

One of the main problems in viticultural production in Istria (Croatia) is a labour shortage in periods of intensive works, mainly during summer, respectively during tourist season.

Read More

SIP and save the planet: a sensory and consumer exploration of australian wines made from potentially drought-tolerant white wine grapes

In order to attenuate the effects of climate change on the ability to cultivate quality wine grape vines in Australia, it is essential to adapt to the projected less favourable Australian climate scenarios. One response may be to convert a portion of the current grapevine plantings to those varieties that demand less water and can tolerate increased heat. This investigation aimed to (i) generate sensory profiles and (ii) obtain knowledge about Australian wine consumers’ preferences and opinions of Australian wines made from potentially drought tolerant, white wine grape varieties not traditionally cultivated in Australia. A Rate-All-That-Apply (RATA) sensory panel (n = 49) generated sensory profiles of 44 commercial white wines made from 7 different white grape varieties (Arinto, Fiano, Garganega, Greco, Verdejo, Verdelho and Vermentino), plus two benchmark examples each of an Australian Riesling, Pinot Gris and Chardonnay wine.

Read More

Terroir effects on the response of Tempranillo grapevines to irrigation in four locations of Spain: grape and must composition

This work discusses the effects of soil and weather conditions on the grape composition of cv. Tempranillo in four different locations of Spain, during the 2008-2011 seasons.

Read More

Identification, quantification and organoleptic impact of « dried fruit » molecular markers in Merlot and Cabernet Sauvignon grapes and in red wines

The aromas found in young Bordeaux red wines made with Merlot and Cabernet Sauvignon suggest a complex mixture of aromas of fresh red fruits such as cherry or blackberry for Merlot, and strawberry or blackcurrant for Cabernet Sauvignon. The aromas of these wines are closely linked with the maturity of the grapes. The climate change that has occurred during the last decade in Bordeaux has induced changes in the ripening conditions of grape berries. It is now widely admitted that over-ripening of the berries during hot and dry summers results in the development of characteristic flavors reminiscent of cooked fruits (fig, prune). The presence of these overriding odors found in both musts and young wines affects the quality and subtlety of the wine flavor and may shorten its shelf life.

Read More