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…

Factors influencing the production of the antioxidant hydroxytyrosol during alcoholic fermentation: Yeast Assimilable Nitrogen and Sugar content.

Hydroxytyrosol (HT) is well known for its potent antioxidant activity and anticarcinogenic, antimicrobial, cardioprotective and neuroprotective properties. One possible explanation to its origin in wines is the synthesis from tyrosol, which in turn is produced from the Ehrlich pathway by yeasts. This work aims to explore the factors that could increase the final content as the initial concentration of yeast assimilable nitrogen (YAN) and sugar. Two different concentrations of YAN were proved between 210mg/L and 300 mg/L. Additionally, two different concentrations of sugar were used: 100g/L and 240 g/L. Alcoholic fermentations in synthetic must were performed with the strain QA23.

Read More

NEW INSIGHTS INTO VOLATILE SULPHUR COMPOUNDS SCALPING ON MICROAGGLOMERATED WINE CLOSURES

The evolution of wine during bottle ageing has been of great interest to ensure consistent quality over time. While the role of wine closures on the amount of oxygen is well-known [1], closures could also play other roles such as the scalping phenomenon of flavour compounds. Flavour scalping has been described as the sorption of flavour compounds by the packaging material, which could result in losses of flavour intensity. It has been reported in the literature that volatile sulphur compounds (VSC) can be scalped on wine closures depending on the type of closure (traditional and agglomerated cork, screw-cap, synthetic [2]).

Read More

Rationalising the impact of time, light, temperature, and oxygen on the evolution of rosé wines by means of a surface response methodology approach

The widespread use of flint glass bottles for rosé wines is driven by consumer preference for color as a key choice factor.

Read More

The effects of perennial cover crop management on soil temperature and vine water status

The implications of perennial cover crop management on vine vigor and yield have been well documented. However, whereas multiple studies show that cover crop management affects grapevine dry matter production, water, and nutrient status, the specific effects of a new hybrid perennial cover crop on soil temperature and its relationship to vine water status in vineyards has not been explored. This study will compare 3 different perennial cover crop combinations and tillage practices with a no-till seeding of a new hybrid perennial, Poa bulbosa (Pb).

Read More

Impact of the non-volatile matrix composition on red wine aroma release and perception of olfactory and oral cues

Aroma and mouthfeel cues are the main characteristics defining red wine quality. During wine tasting, perceptual and physical-chemical phenomena leading to mutual interactions between volatiles and non-volatiles sensory active compounds, can occur. Aroma perception depends on the release of volatiles from wine, that is affected by wine constituents present in the medium (Pittari et al. 2021; Lyu et al. 2021). Our aim was to evaluate the effect of the non-volatile wine matrix composition (polyphenols, PPh) on the release and perception of red wine aromas by an experiment of matrix enrichment.

Read More