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…

Techniques to study graft union formation in grapevine 

Grapevines are grown grafting in most viticultural regions. Grapevine rootstocks are either hybrids or pure species of different American Vitis spp. (particularly V. berlandieri, V. rupestris and V. riparia), which are primarily used to provide root resistance to the insect pest Phylloxera. In addition to Phylloxera resistance, ideally grapevine rootstocks should be resistant to other soil borne pathogens and adapted to abiotic stress conditions. New rootstocks have the potential to adapt agriculture to climate change without changing the characteristics of the harvested product. However, high grafting success rates are an essential prerequisite.

Read More

Implications of grapevine row orientation in South Africa

Row orientation is a critical long-term viticulture practice, which may have a determining effect on grape and wine quality as well as cost efficiency on a specific terroir selected for cultivation.

Read More

Impact of glutathione and elemental sulphur juice addition on the volatile thiol production in South African Sauvignon blanc wine

Three compounds, 3-mercaptohexanol (3MH), 3-mercaptohexyl-acetate (3MHA) and 4-mercapto-4-methylpentan-2-one (4MMP), also known as varietal thiols, have been identified to contribute positively to wine aroma and are responsible for the distinct gooseberry, grapefruit, guava and box tree character found in Sauvignon blanc wines. Certain volatile thiol compounds though, can cause off-aromas of onion, garlic, rubber and rotten egg, this group of molecules is known as reductive sulphur compounds (RSC). This study looks into how the addition of sulphur-compounds to Sauvignon blanc juice contributes to the varietal thiol (3MH and 3MHA) concentration and reductive sulphur compound concentration in South African Sauvignon blanc wine.

Read More

From the current probabilistic approach to a deterministic production process, a clear step towards digital transformation in the wine sector

Currently, to consistently ensure the maintenance of a wine-style while benefiting from the utmost rigor made possible by the winemaking process, the composition of the wine blend is made using sensory control. This is performed after the wine is made with no real possibility of deterministic intervention.

Read More

Viticultural potential assessment and its spatial delineation analysis in Goriška Brda viticultural area

Viticultural potential has a complex conditioning, determined by relief,
soil, climate and lithology. Delineation of viticultural potential from vineyard areas is essential for the purpose to collect the necessary data for viticultural zoning. Using this data, we can achieve greater yield quality, which is the most important criteria in viticulture. The main purpose of this research is
characterizing of viticultural potential and zoning of homogeneous viticultural zones in Goriška Brda region by assessing the suitability of defined ecological factors.

Read More