A Multi-Source Data Fusion Decision-Making Method for Disease and Pest Detection of Grape Foliage Based on ShuffleNet V2

Disease and pest detection of grape foliage is essential for grape yield and quality. RGB image (RGBI), multispectral image (MSI), and thermal infrared image (TIRI) are widely used in the health detection of plants. In this study, we collected three types of grape foliage images with six common classes (anthracnose, downy mildew, leafhopper, mites, viral disease, and healthy) in the field. ShuffleNet V2 was used to build up detection models. According to the accuracy of RGBI, MSI, TIRI, and multi-source data concatenation (MDC) models, and a multi-source data fusion (MDF) decision-making method was proposed for improving the detection performance for grape foliage, aiming to enhance the decision-making for RGBI of grape foliage by fusing the MSI and TIRI. The results showed that 40% of the incorrect detection outputs were rectified using the MDF decision-making method. The overall accuracy of MDF model was 96.05%, which had improvements of 2.64%, 13.65%, and 27.79%, compared with the RGBI, MSI, and TIRI models using label smoothing, respectively. In addition, the MDF model was based on the lightweight network with 3.785 M total parameters and 0.362 G multiply-accumulate operations, which could be highly portable and easy to be applied.

Development of agro-climatic grape yield model for Nashik region, Maharashtra, India

Prediction of the crop yield is need of time according to the change in climate conditions. In the present study, the Agro-Climatic Grape Yield (ACGY) model has been developed with monthly climatic parameters using multi-regression analysis approach. The developed model was statistically tested for its predictive ability. The discrepancy ratio, the standard deviation of discrepancy ratio, mean percentage error and standard deviation of mean percentage error for the model was obtained as 1.03, 0.19, 0.03% and 0.19, respectively. Sensitivity analysis was carried out for the developed ACGY model using the parametric sensitivity method. In order to know the future grape yield using ACGY model, climate scenarios were generated under Canadian Earth System Model (CanESM2) for three emissions representative concentration pathways as RCP2.6, RCP4.5, and RCP8.5. According to the analysis using ACGY model, increasing yield was observed in grape up to year 2050 as compared to current yield.

Multiple Effects of Nitrogen Fertilization on Grape Vegetative Growth, Berry Quality and Pest Development in Mediterranean Vineyards

Nitrogen is a key macronutrient for the quantitative and qualitative yield of grapes; in addition, it influences the development and reproduction of grape pests. The multiple effects of different nitrogen rates were investigated on the red berry cultivar ‘Carignano’ and the grape pest Planococcus ficus in a two-year field trial. Different amounts of ammonium nitrate were compared: 0, 80 and 160 Units ha−1 for mineral nitrogen. The amount of nitrogen fertilization supplied influenced the nitrogen status of vines and increased the pruning weight and leaf area, as well as the overall grape yield, by increasing the cluster weight. However, doubling the nitrogen rate did not generally increase the vegetative and productive parameters of grapevines. At harvest, nitrogen supply did not influence the anthocyanin content, tritatable acidity, and soluble solids, although the latter parameter showed a clear, yet not significant, decreasing trend. Planococcus ficus exhibited higher fecundity, survival and shorter development time on grapevines provided with nitrogen, whereas its fertility was unaffected by nitrogen fertilization. Ultimately, nitrogen had a direct and positive effect on grape yield and vine mealybug development, highlighting the importance of integrated cultural and pest control practices to promote grape production.

Development of agro-climatic grape yield model with future prospective

Agriculture sector is most vulnerable to climate change. To predict the crop yield in accordance with the changing climate is a need of hour than choice. To know the climate in advance is crucial for grape growing farmers and grape export agencies for its better planning and security of grape industries from climate change perspective. In the present study, the Agro-Climatic Grape Yield (ACGY) model is developed on monthly scale climatic parameters using correlation, significance and multi-regression analysis approach. The developed model is statistically tested for its predictive ability. The discrepancy ratio, the standard deviation of discrepancy ratio, mean percentage error and standard deviation of mean percentage error for the developed model is obtained as 1.03, 0.19, 0.03% and 0.19 respectively. Sensitivity analysis is carried out for the developed ACGY model using the parametric sensitivity method. In order to know the grape yield for future using developed ACGY model, climate scenarios are generated under Canadian Earth System Model (CanESM2) for three emissions Representative Concentration Pathways (RCP) as RCP2.6, RCP4.5, and RCP8.5. Model response variability is carried out to understand the variation of grape yield. It is observed that grape yield is showing adverse variation with the increase in minimum temperature in January and November months, and precipitation in August and November months. Whereas, minimum temperature in April and sum of monthly mean evapotranspiration showing accordance effect on the grape yield. It is recommended the use of ACGY model for grape yield estimations applicable for the present and future climate of the study area based on the predictive capability of developed model.

Influence of Grapevine Leafroll-associated Virus-3 in Mature Plants of Vitis vinifera L. cv Albariño on 110R and 196.17C Rootstocks

The detrimental effects of grapevine leafroll disease (GLD) have been documented mainly in young plantsand little data is available on infected grapevines when they reach maturity. This study examined theinfluence of the rootstock on the effect of GLRaV-3 in a 20-year-old Vitis vinifera cv Albariño vineyard inwhich the virus has been spread by Planococcus ficus. Plants grafted on Richter 110 or Castell 196.17 withsimilar development were analysed for grapevine leafroll-associated viruses. In particular, 25 GLRaV-3-infected and 25 leafroll-free and asymptomatic vines were selected and monitored during a period of threeyears to determine grape yield and must components. Although the virus infection affected plants on bothrootstocks, it caused a greater effect on plants grafted onto 110R, with average accumulated yield losses ofup to 33%, relative to losses of 16% for plants on 196.17C. The sugar content was lower in the must frominfected plants on 110R (-2.1ºBrix) than in the must from plants on 196.17C (-1.5ºBrix). The presence ofthe virus was associated with decreased concentrations of primary amino nitrogen (PAN) and ammonium(NH4+), with the greatest effect for 110R (-35%). As 110R is the most used rootstock in Spain, particularcare must be taken to prevent the transmission of GLRaV-3 to certified virus-free plants on 110R in newvineyards. In sensitive varieties such as Albariño, particularly in areas with an active spread of the virusby mealybugs, grafting on 196.17C seems to minimise the effect that GLD has in a medium to long term.

RESEARCH ON THE VARIABILITY OF YIELD COMPONENTS IN SOME GRAPEVINE VARIETIES FOR RED WINES

Research was conducted during two growing seasons (2017-2018) in Miniş-Măderat vineyard. The study aimed to evaluate the variability of several red wine grape varieties in order to highlight their main qualitative and quantitative parameters. In the research were involved the morphological parameters: the number of bunches on the vine, the bunch weight, the number of berries in the bunch and the grape yield on the vine. The highest bunches number /vine registered Merlot variety (30.24), while Burgund variety recorded the lowest values (17.76). Burgund variety recorded the highest bunch average weight (119.57 g) while Pinot Noir recorded the lowest value (87.18 g).Merlot variety recorded the highest number of berries/bunch,(111.36) and the lower value was recorded by the Pinot Noir ( 82.36).The Merlot variety achieved a significantly higher production than the other varieties during both growing seasons (3600.87g). The conditions of 2018 growing season had a very significant positive influence on the grape yield/ vine.

Effect of Organic Amendment Addition on Soil Properties, Greenhouse Gas Emissions and Grape Yield in Semi-Arid Vineyard Agroecosystems

In semi-arid vineyard agroecosystems, highly vulnerable in the context of climate change, the soil organic matter (OM) content is crucial to the improvement of soil fertility and grape productivity. The impact of OM, from compost and animal manure, on soil properties (e.g., pH, oxidisable organic C, organic N, NH4+-N and NO3−-N), grape yield and direct greenhouse gas (GHG) emission in vineyards was assessed. For this purpose, two wine grape varieties were chosen and managed differently: with a rain-fed non-trellising vineyard of Monastrell, a drip-irrigated trellising vineyard of Monastrell and a drip-irrigated trellising vineyard of Cabernet Sauvignon. The studied fertiliser treatments were without organic amendments (C), sheep/goat manure (SGM) and distillery organic waste compost (DC). The SGM and DC treatments were applied at a rate of 4600 kg ha−1 (fresh weight, FW) and 5000 kg ha−1 FW, respectively. The use of organic amendments improved soil fertility and grape yield, especially in the drip-irrigated trellising vineyards. Increased CO2 emissions were coincident with higher grape yields and manure application (maximum CO2 emissions = 1518 mg C-CO2 m−2 d−1). In contrast, N2O emissions, mainly produced through nitrification, were decreased in the plots showing higher grape production (minimum N2O emissions = −0.090 mg N2O-N m−2 d−1). In all plots, the CH4 fluxes were negative during most of the experiment (−1.073−0.403 mg CH4-C m−2 d−1), indicating that these ecosystems can represent a significant sink for atmospheric CH4. According to our results, the optimal vineyard management, considering soil properties, yield and GHG mitigation together, was the use of compost in a drip-irrigated trellising vineyard with the grape variety Monastrell.

Effect of grape yield and maceration time on phenolic composition of ‘Fetească neagră’ organic wine

The phenolic composition of wine is mostly determined by the accumulation of the phenolic compounds in the grapes, as well as their extraction into wine. To increase their concentration in grapes, yield reduction is usually performed by pruning, while to increase the extraction in wines, the maceration on skins is extended for longer periods of time. The present study focuses on the possibilities to apply both strategies to improve the polyphenol composition of organic red wines of Romanian variety ‘Fetească neagră’, which stands to benefit more from technological interventions than other varieties, which naturally accumulate higher phenol concentrations in the grapes. In the vineyard three experimental pruning variants were made, with 20, 28 and 36 buds/vine, while for wine, maceration was performed for either 8 or 16 days for each grape variant. The phenolic profiles of wines were determined by HPLC methods. The main anthocyanidins, such as malvidin, petunidin, delphinidin, peonidin and cyanidin, as well as the acylated and coumaroylated derivatives of malvidin and peonidin were quantitatively determined. Some other phenolic compounds, of various classes, such as gallic, p-benzoic, p-coumaric and ferulic acid, catechin, epicatechin, myricetin, quercetin and trans-resveratrol were also determined. The quality of the organic ‘Fetească neagră’ wines depended highly on the vintage, but yield reduction and the extension of skin maceration duration were especially beneficial in the less favourable year, when classical technologies lead to less accumulation of sugars, colour and other polyphenols. Concomitant application of both strategies led to the best results, irrespective of the year.