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…

Comparison of genotype x environment interaction of clonal and polyclonal grapevine selected materials

Conserving and exploring the intra-varietal diversity of ancient varieties is essential to foster their use in the future, preserving the traditions and history of ancient growing regions and their wines. The conservation of representative samples of ancient varieties and the utilization of intra-varietal variability through polyclonal selection are advisable strategies to save and promote the cultivation of each variety, respectively.

Assessment of wine non-Saccharomyces yeast strains as promising producers of glutathione

AIM: Glutathione (GSH) is a non-protein thiol naturally present in grape berries and produced by yeasts during fermentation. It has a strong antioxidant activity, thus can be added during winemaking to limit the oxidative phenomena of wine, preserving sensory characteristics and stability, ultimately promoting a healthier product by reducing the need for SO2 addition.

Aromatic profile evolution of corvina, corvinone and rondinella grapes during withering

AIM AND METHODS: Grape withering is one of the key steps in the production of the most renowned red wines of the Valpolicella area, namely Amarone and Recioto. This practice, which was already used since Roman times, entails important modifications in grape composition and in the chemical and sensorial characteristics of the corresponding wines, especially in terms of aromatic profile. The aim of this research is evaluating the aromatic evolution during grape withering of the three main varieties used in Valpolicella wines: Corvina, Corvinone and Rondinella.Samples of the three varieties were analyzed at harvest and at different stages of withering, namely10%, 20% and 30% of weight loss. Free and glycosidically bound compounds were extracted and analyzed using Gas Chromatography- Mass Spectrometry (GC-MS). RESULTS: For all the samples the data were normalized to eliminate the effect of concentration due to grape dehydration. Terpene content and evolution varied considerably in relationship to grape variety. Corvinone was richer in cyclic terpenes (including phellandrene, limonene, and cymene) and they decreased during withering.

Metabolomic study of mixed Saccharomyces cerevisiae yeast during fermentation

Alcoholic fermentation conducted by microorganism is a key step in the production of wine. In this process, interactions between different species of yeast are widely described but their mechanisms are still poorly understood. The interactions studied in wine are mainly between Saccharomyces and non-Saccharomyces species. Therefore, little is known about the mechanisms of interactions

Are Farm to fork strategy goals reasonable and achievable? State of the art of Península de Setubal’s winegrowers

The European Union’s “farm to fork” strategy sets out several objectives to be achieved by farmers, who, among others, relate to increasing biodiversity, protecting soils and reducing the use of pesticides. At a time when the amendments to the national plans of Sustainable Use of pesticides are being discussed, it is important to understand what the Setúbal Peninsula region status is.