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…

Analysis of Cabernet Sauvignon and Aglianico winegrape (V. vinifera L.) responses to different pedo-climatic environments in southern Italy

Water deficit is one of the most important effects of climate change able to affect agricultural sectors. In general, it determines a reduction in biomass production, and for some plants, as in the case of grapevine, it can endorse fruit quality. The monitoring and management of plant water stress in the vineyard

Impact of geographical location on the phenolic profile of minority varieties grown in Spain. II: red grapevines

Because terroir and cultivar are drivers of wine quality, is essential to investigate theirs effects on polyphenolic profile before promoting the implantation of a red minority variety in a specific area. This work, included in MINORVIN project, focuses in the polyphenolic profile of 7 red grapevines minority varieties of Vitis vinifera L. (Morate, Sanguina, Santafe, Terriza Tinta Jeromo Tortozona Tinta) and Tempranillo) from six typical viticulture Spanish areas: Aragón (A1), Cataluña (A2), Castilla la Mancha (A3), Castilla –León (A4), Madrid (A5) and Navarra (A6) of 2020 season. Polyphenolic substances were extracted from grapes. 35 compounds were identified and quantified (mg subtance/kg fresh berry) by HPLC and grouped in anthocyanins (ANT) flavanols (FLAVA), flavonols (FLAVO), hydroxycinnamic (AH), benzoic (BA) acids and stilbenes (ST). Antioxidant activity (AA, mmol TE /g fresh berry) was determined by DPPH method. The results were submitted to a two-way ANOVA to investigate the influence of variety, area and their interaction for each polyphenolic family and cluster analysis was used to construct hierarchical dendrograms, searching the natural groupings among the samples. Sanguina (A3) had the most of total polyphenols while Tempranillo (A5) those of ANT. Sanguina (A2) and (A3) reached the highest values of FLAVO, FLAVA and AA. These two last samples had also the maximum of AA. The effect cultivar and area were significant for all polyphenolic families analyzed. A high variability due to variety (>50%) was observed in FLAVA and the maximum value of variability due to growing area was detected in AA (86.41%), ANT and FLAVO (51%); the interaction variety*zone was significant only for ANT, FLAVO, EST and AA. Finally, dendrograms presented five cluster: i) Sanguina (A2); ii) Sanguina (A3); iii) Tempranillo (A5); iv) Tempranillo (A3); Terriza (A3,A5), Morate (A5,A6); v) Santafé (A1,A6); Tortozona tinta (A1,A3,A6); Tinta Jeromo (A3,A4).

Inhibition of Oenococcus oeni during alcoholic fermentation by a selected Lactiplantibacillus plantarum strain

The use of selected cultures of the species Lactiplantibacillus plantarum in Oenology has grown in prominence in recent years. While initial applications of this species centred very much around malolactic fermentation (MLF), there is strong evidence to show that certain strains can be harnessed for their bio-protective effects. Unwanted spontaneous MLF during alcoholic fermentation (AF), driven by rogue Oenococcus oeni, is a winemaking deviation that is very difficult to manage when it occurs. This work set out to determine the efficacy of one particular strain of Lactiplantibacillus plantarum(Viniflora® NoVA™ Protect), against this problem in Cabernet Sauvignon must. The work was carried out at commercial scale and in a winery environment and compared the bio-protective culture with the more traditional approach of reducing must pH by the addition of tartaric acid. The combination of both was also investigated. The concentration of both Oenococcus oeni and Lactiplantibacillus plantarum was determined using qPCR. The adventitious Oenococcus oeni showed the most growth during AF in the control wine, whereas in the wines treated with Lactiplantibacillus plantarum a bacteriostatic effect against this species was observed. This effect was comparable to the wines treated with tartaric acid. This has particular commercial relevance for controlling the flora in musts with high pH, or when the addition of tartaric acid is either not permitted or is prohibitive for other reasons.

An analytical framework to site-specifically study climate influence on grapevine involving the functional and Bayesian exploration of farm data time series synchronized using an eGDD thermal index

Climate influence on grapevine physiology is prevalent and this influence is only expected to increase with climate change. Although governed by a general determinism, climate influence on grapevine physiology may present variations according to the terroir. In addition, these site-specific differences are likely to be enhanced when climate influence is studied using farm data. Indeed, farm data integrate additional sources of variation such as a varying representativity of the conditions actually experienced in the field. Nevertheless, there is a real challenge in valuing farm data to enable grape growers to understand their own terroir and consequently adapt their practices to the local conditions. In such a context, this article proposes a framework to site-specifically study climate influence on grapevine physiology using farm data. It focuses on improving the analysis of time series of weather data. The analytical framework includes the synchronization of time series using site-specific thermal indices computed with an original method called Extended Growing Degree Days (eGDD). Synchronized time series are then analyzed using a Bayesian functional Linear regression with Sparse Steps functions (BLiSS) in order to detect site-specific periods of strong climate influence on yield development. The article focuses on temperature and rain influence on grape yield development as a case study. It uses data from three commercial vineyards respectively situated in the Bordeaux region (France), California (USA) and Israel. For all vineyards, common periods of climate influence on yield development were found. They corresponded to already known periods, for example around veraison of the year before harvest. However, the periods differed in their precise timing (e.g. before, around or after veraison), duration and correlation direction with yield. Other periods were found for only one or two vineyards and/or were not referred to in literature, for example during the winter before harvest.

A multidisciplinary approach to evaluate the effects of the training system on the performance of “Aglianico del Vulture” vineyards

Vineyards are complex agro-ecosystems with high spatial and temporal variability. An efficient training system may counteract the adverse effects of this variability. Moreover, considering the climate change issues, choosing an efficient training system that enhances water use and protects the vines from radiative thermal stress has become a priority for the farmers. A multidisciplinary approach that assesses the soil-crop-yield-wine relationships of vineyards in a distributed and holistic way could bring added knowledge on the behavior of the different training systems. This ongoing research aimed to implement a multidisciplinary approach to study the behavior of “Aglianico del Vulture” grapevines trained with two different systems: a spurred cordon (SC) and an “Alberello in parete” (AL), grown in a high-quality wine production area of Basilicata region (Italy). The approach merged several methods and scales of soil, ecophysiology, must/wine quality, and spectral data collection to assess the influence of the training system. Homogeneous zones (HZs) in both training systems were defined through a procedure based on geomorphological classification, unmanned aerial vehicles (UAV) images analysis, and a traditional soil survey supported by geophysical scanning. During the 2021 season, TDR probes monitored soil water content, while grapevine health status was assessed using eco-physiological measurements (LWP, chlorophyll content, PSII photosynthetic efficiency, LAI, and point-based field spectroscopy). These grapevine in-vivo measurements validated the spectral vegetation indexes (NDVI, RENDVI, CVI, and TVI) derived from the UAV multispectral imagery, which monitored the grapevine status in a distributed and non-invasive way. Grape yield, quality of berries, must and wine were measured to assess the effects of the training systems. The first experimental year results showed the variability of the vineyards and revealed relationships among soil parameters, crop characteristics, and vegetation indices of the SC and AL training systems. This multidisciplinary study could bring new insights into the vineyard training system’s effects on grape yield and wine quality.