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…

“Gheo” per la vitivinicoltura: un progetto per la produzione dl vini dl alta qualità

Il settore primario, ed in particolare quello agricolo, sta attraversando un periodo partico­larmente delicato. Sia gli aspetti della produzione che quelli della commercializzazione ven­gono infatti messi in discussione da nuovi indirizzi economici e tecnologici.

Effect of Candida zemplinina oak chips biofilm on wine aroma profile

Candida zemplinina (synonym Starmerella bacillaris) is frequently isolated in grape must in different vitivinicultural areas. The enological significance of C. zemplinina strains used in combination with S. cerevisiae has been demonstrated, being wines produced by the above-mixed starter, characterized by higher amounts of glycerol and esters.

Terroir et variabilité microclimatique : pour une approche à l’échelle de la parcelle

The climatic component is one of the elements of the zoning of viticultural potential, alongside the geological and pedological components (Morlat, 1989; Lebon et al , 1993). Many climatic indices have thus been defined to estimate the potential for wine production at the scale of a region or a country (Carbonneau et al ., 1992). The main climatic variables used are temperature and radiation. We note in particular the indices of Branas, Huglin and Ribereau-Gayon (Huglin, 1986). However, few studies have been undertaken on the spatial variability of microclimatic conditions at the scale of a vineyard, a valley, or even a municipality.

Non-Saccharomyces yeast nitrogen consumption and metabolite production during wine fermentation

Over the last decade, the use of non-Saccharomyces yeasts in the winemaking process has been re-assessed and accepted by winemakers. These yeasts can be used to achieve specific objectives such as lowering the ethanol content, preventing wine spoilage and increasing the production of specific aroma compounds. Since these species are unable to complete alcoholic fermentation, strategies of co- and sequential inoculation of non-Saccharomyces and Saccharomyces cerevisiae have been developed. However, when mixed starter cultures are used, several parameters (e.g. strain yeast, inoculation timing and nutrient competitions) impact the growth of the individual yeasts, the fermentation kinetics and the metabolites/aroma production. In particular, competition for nitrogen compounds could have a major impact, potentially leading to sluggish fermentation when the yeast assimilable nitrogen (YAN) availability is low. Moreover, many aroma compounds produced by the yeasts are directly produced and influenced by nitrogen metabolism such as higher alcohols, acetate esters and ethyl esters which participate in the organoleptic complexity of wine.

Long-term drought resilience of traditional red grapevine varieties from a semi-arid region

In recent decades, the scarcity of water resources in agriculture in certain areas has been aggravated by climate change, which has caused an increase in temperatures, changes in rainfall patterns, as well as an increase in the frequency of extreme phenomena such as droughts and heat waves. Although the vine is considered a drought-tolerant specie, it has to satisfy important water requirements to complete its cycle, which coincides with the hottest and driest months. Achieving sustainable viticulture in this scenario requires high levels of efficiency in the use of water, a scarce resource whose use is expected to be severely restricted in the near future. In this regard, the use of drought-tolerant varieties that are able to maintain grape yield and quality could be an effective strategy to face this change. During three consecutive seasons (2018-2020) the behavior in rainfed regime of 13 traditional red grapevine varieties of the Spain central region was studied. These varieties were cultivated in a collection at Centro de Investigación de la Vid y el Vino de Castilla-La Mancha (IVICAM-IRIAF) located in Tomelloso (Castilla-La Mancha, Spain). Yield components (yield, mean bunch and berry weight, pruning weight), physicochemical parameters of the musts (brix degree, total acidity, pH) and some physiological parameters related with water stress during ripening period (δ13C, δ18O) were analysed. The application of different statistical techniques to the results showed the existence of significant differences between varieties in their response to stressful conditions. A few varieties highlighted for their high ability to adapt to drought, being able to maintain high yields due to their efficiency in the use of water. In addition, it was possible quantify to what extent climate can be a determinant in the δ18O of musts under severe water stress conditions.