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…

Radiation-associated effects on regulated deficit irrigation management in grapevine cv. Cabernet Sauvignon

The main challenge of regulated deficit irrigation (RDI) research is to isolate the factors that come with RDI, the direct effect of plant water status from the indirect ones like increased radiation and temperature changes on the cluster zone. This study aims to isolate the effects of vine water status from the effects of increased radiation on the phenolic composition of grapes subjected to RDI.
A three-year study on an RDI experiment where radiation was controlled was implemented in a commercial vineyard of Cabernet Sauvignon in Chile. Four RDI treatments based on partial evapotranspiration (ET) irrigation were established. Irrigation treatments were 100% ET, 70% ET, 50-100% ET (50% ET before veraison and 100% ET afterward), and 35-100% ET (35% ET before veraison and 100% ET afterward).

The regulation of ABA-induced anthocyanin accumulation in grape berry

Color is a key quality trait for grape berry and the producing wines. Berry color of red genotypes is mainly determined by the quantity and composition of anthocyanins accumulated in the skin and/or pulp. Both genetic and environmental factors could influence the quantity and composition of anthocyanins, while the underlying mechanisms are not fully clear. To explore the mechanisms underlying the diversity of anthocyanin accumulation in grape berry, we compared two grapevine genotypes showing distinct sensitivities to ABA-induced anthocyanin biosynthesis, where one genotype showed minor responses to exogenous ABA application while the other showed significant increase in anthocyanins after exogenous ABA application.

Brettanomyces bruxellensis, born to live

The wine spoilage yeast Brettanomyces bruxellensis can be found at several steps in the winemaking process due to its resistance to multiple stress conditions. Among the resistance strategies, one could be the formation of biofilm, a lifestyle known to enhance persistence of microorganisms. In this study, we propose to characterize biofilm of B. bruxellensis in wine, especially through several microscopic analyses.

Quantification of γ-nonalactone in botrytized and non-botrytized New Zealand and Australian wines

ƴ-Nonalactonehas been identified as a significant contributor to the aroma profile of a range of wines and is associated with stonefruit and coconut descriptors.

Terroir effects on wine aromatic metabolomics in the eastern foot of Helan Mountain, Ningxia, China

Aim: The eastern foot of Helan Mountain, Ningxia, China is one of the most important wine production regions in China and grape cultivation has spread in several sub-regions with different soils and cultivars. Large diversity in wine aromas have been observed at Ningxia region but which terroir factors drive those diversity in aromas remain to uncover. This study aims to investigate the impacts of grape varieties and soil chemical properties on wine aromas at Ningxia, in order to characterize the aromatic typicality of Ningxia wines and provide foundation for developing a ‘Protected Designation of Origin’ system.