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…

Effect of ozone treatments in wine production of young and short-term aged white wines: destructive and non-destructive evaluation of main quality attributes

The main aim of WiSSaTech project (PRIN P2022LXY3A), supported by Italian Ministero dell’Università e della Ricerca and NextGenerationEU program, is to investigate eco-friendly and safe alternatives to sulphur dioxide (SO2) in wine production.

Study of varietal wines from the qualified origin denomination Rioja (Spain): analysis of wine colour, polysaccharides, polyphenols and biogenic amines and amino acides 

The cultivar with a greater oenological potential was ‘Monastel’, which showed overall better values than ‘Tempranillo’ in colour intensity, total polyphenol index, wine colour, total anthocyanins, resveratrol and gallic acid.

The evaluation of tannin activity in south african red wines

Astringency is an important red wine quality attribute, which can be measured both chemically and sensorially. The use of tannin activity shows potential as a valuable chemical measurement in understanding red wine mouthfeel properties such as astringency and bitterness, which is also affected by tannin structural factors, in addition to matrix effects. Tannin activity is defined as the enthalpy of interaction between tannins and a hydrophobic surface. Studies involving tannin activity have been performed since the early 2010’s, but chemosensory studies used to evaluate how structure-activity relationships change across multiple, consecutive vintages are limited. The aim of this study is to investigate how tannin activity may be linked to red wine mouthfeel, and how all these variables may change according to wine age.

Extracellular substances of lactic acid bacteria interests in biotechnological practices applied to enology

Extracellular substances (ECS) represent all molecules outside the cytoplasmic membrane, which are not directly anchored to the cell wall of microorganisms living through a planktonic or biofilm phenotype. They are the high-biomolecular-weight secretions from microorganisms (i.e. extracellular polymeric substances – EPS – proteins, polysaccharides, humic acid, nucleic acid), and the products of cellular lysis and hydrolysis of macromolecules. In addition, some high- and low-molecular-weight organic and inorganic matters from environment can also be adsorbed to the EPS. All can be firmly bound to the cell surface, associated with the EPS matrix of biofilm, or released as being freely diffusing throughout the medium.

Volatile compounds of base wines for the production of Lessini Durello sparkling wine

AIM Durello is a sparkling wine produced in the Lessini mountains near Verona. The wine is made from Durella grapes, a native white grape variety with a particularly high acidity. In spite of the small production area (375 ha for only 35 producers), there is a growing interest in this product. However, little is known about the aromatic profiles of these wines. The aim of this work was to characterize the aroma profile of Durella base wines suitable for the production of Lessini Durello sparkling wine. METHODS 14 base wines from Durella grapesfrom different producers were used for this study. Solid Phase Microextraction (SPME) and Solid Phase Extraction (SPE) sampling techniques coupled to GC-MS analysis allowed to identify and quantify a total of 62 volatile compounds. RESULTS Durello base wines showed relatively high levels of vitispirane, ß-damascenone, ß-citronellol and esters.