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…

Discrimination of white wines by Raman spectroscopy coupled with chemometric methods

France is the largest exporter of wine in the world. The export turnover is estimated at 8.7 billion euros in 2017 for 13 million hectoliters sold. This lucrative business pushes scammers to increase the value of some low-end wines by cheating on their appellations, quality or even their origins. These facts lead to losing 1.3 billion euros each year to the European Union’s wine and spirits companies.

Read More

Data fusion approaches for sensory and multimodal chemistry data applied to storage conditions

The need to combine multimodal data for complex samples is due to the different information captured in each of the techniques (modes).

Read More

Understanding the complexity of grapevine winter physiology in the face of changing climate

The vast majority of our understanding of grapevine physiology is focused on the processes that occur during the growing season. Though not obvious, winter physiological changes are dynamic and complex, and have great influence on the survival and phenology of grapevines. In cool and cold climates, winter temperatures are a constant threat to vine survival. Additionally, as climate changes, grapevine production is moving toward more traditionally cool and cold climates, either latitudinal or altitudinal in location. Our research focuses on understanding how grapevines navigate winter physiological changes and how temperature impacts aspects of cold hardiness and dormancy. Through these studies, we have gained keen insight into the connections between winter temperature, maximum cold haridness, and budbreak phenology, that can be used to develop prediction models for viticulture in a changing climate.

Read More

Mapping terroirs at the reconnaissance level, by matching soil, geology, morphology, land cover and climate databases with viticultural and oenological results from experimental vineyards

This work was aimed at setting up a methodology to define and map the «Unités Terroir de Reconnaissance» (UTR), combining environmental information stored in a Soil Information System with experimental data coming from benchmark vineyards of Sangiovese vine.

Read More

Influence of protective colloids on tartrate stability, polysaccharide contents and volatile compound profile of a white wine

The tartaric salts precipitation is one of the main issues regarding wine instability 1. In addition to the well-known and deeply studied phenomena of potassium hydrogentartrate precipitation (KHT), the last decade has been increased the phenomena of calcium tartrate (CaT) precipitation, that is a concern for the wine industry 2.

Read More