Auswahl der wissenschaftlichen Literatur zum Thema „Grapevine microclimate“

Detection of drought stress is of great importance in grapevines because the plant’s water status strongly affects the quality of the grapes and hence, resulting wine. Measurements of stem diameter variations show promise for detecting drought stress, but they depend strongly on microclimatic changes. Tools for advanced data analysis might be helpful to distinguish drought from microclimate effects. To this end, we explored the possibilities of two data mining techniques: Unfold principal component analysis (UPCA) – an already established tool in several biotechnological domains – and functional unfold principal component analysis (FUPCA) – a newer technique combining functional data analysis with UPCA. With FUPCA, the original, multivariate time series of variables are first approximated by fitting the least-squares optimal linear combination of orthonomal basis functions. The resulting coefficients of these linear combinations are then subjected to UPCA. Both techniques were used to detect when the measured stem diameter variations in grapevine deviated from their normal conditions due to drought stress. Stress was detected with both UPCA and FUPCA days before visible symptoms appeared. However, FUPCA is less complex in the statistical sense and more robust than original UPCA modelling. Moreover, FUPCA can handle days with missing data, which is not possible with UPCA.

California table grape (Vitis vinifera) growers cover the canopies of late-season varieties with plastic (polyethylene) covers to shield the fruit from rain. Green- or white-colored covers are commonly used, but there is lack of information whether either cover might be preferable based on canopy microclimate or fruit quality. In late September, ‘Redglobe’ (in 2011) and ‘Autumn King’ (in 2012) table grapevines were covered with green or white plastic, or left uncovered, and canopy microclimate, fungal and bacterial rot incidence, and fruit yield and quality at harvest, and after postharvest storage, were evaluated. Green covers were more transparent and less reflective than white covers, and daily maximum temperature difference in the top center of the canopies of grapevine with green covers was consistently >5 °C than that of grapevine subjected to other treatments, but covers had little effect on temperatures in the fruit zones, which were not enveloped by covers. Effects on relative humidity (RH) depended on location within the canopy and time of day; RH peaked in early morning and was at a minimum in late afternoon. All cover treatments had relatively similar peak RH in south-facing fruit zones and the top center of the canopy. However, in the north-facing fruit zone, vines with green covers had higher RH at night than vines subjected to other treatments. Both covers consistently reduced evaporative potential in the top center of the canopy, but not in fruit zones. Treatment effects on condensation beneath the covers were inconsistent, possibly due to differences in canopy size, variety, or season, but south-facing cover surfaces generally had less condensation than the top or north-facing surfaces. About 0.5 inch of rain fell on 5 Oct. 2011, but no rain occurred during the 2012 experiment. In 2011, green covers delayed fruit maturation slightly, but not in 2012. Covers did not affect vineyard rot incidence, the number of boxes of fruit harvested, or postharvest fruit quality in 2011, but fruit from covered grapevine had less postharvest rot in 2012 than fruit from noncovered grapevines, even though a measurable rain event occurred in 2011 but not in 2012. In conclusion, our results suggest that white covers may be preferable to green since green covers were associated with higher temperatures in both seasons and higher RH in the ‘Autumn King’ trial of 2012, but otherwise performed similarly.

Climate change is a critical challenge for the global grape and wine industry, as it can disrupt grapevine growth, production, and wine quality. Climate change could influence the cost-effectiveness and growth of the wine industry in different wine regions since grapevine development is deeply dependent on weather (short-term) and climate (long-term) conditions. Innovation and new technologies are needed to meet the challenge. This review article addresses the impact of climate change on grapevines, such as vine phenology, pest and disease pressure, crop load, and grape and wine composition. It also reviews recent advances in the areas of viticultural manipulation and relevant technologies to potentially reduce the impact of climate change and help growers improve grape quality. Remote sensing is used for vineyard microclimate monitoring; thermal sensors combined with UAVs, aircraft, or satellites are used for water management; soil electrical conductivity sensors have been developed for soil mapping. Viticultural manipulations, such as regulated deficit irrigation for water use efficiency and berry-ripening delay for growing quality fruit, are also discussed. The review assesses future directions for further technological development, such as soil and vine water monitoring devises, precision viticulture, and artificial intelligence in vineyards.

Terroir factors and vineyard practices largely determine canopy and root system functioning. In this study, changes in soil conditions, multi-level (vertical, horizontal) light interception (quantitative, photographic, schematic, 3D modelled), leaf water potential and photosynthetic activity were measured during the grape ripening period on NS, EW, NE-SW, and NW-SE orientated (Southern Hemisphere) vertically trellised Shiraz grapevine canopies. It was hypothesised that the spatial radiation interception angle and radiation distribution of differently orientated and vertically trained grapevine rows would affect soil conditions and vine physiological activity. Soil water content showed an increase and soil temperature a decreasing gradient with soil depth. In the afternoon, soil layers of EW orientated rows reached their highest temperature. This, along with measured photosynthetic active radiation received by canopies, complimented the diurnally-captured photographic, constructed and 3D modelled images (also schematically) of canopy and soil exposure patterns. The top, bottom and outside of NS canopies mainly received radiation from directly above, from the E and the W; during midday, high radiation was only received from above. The EW rows received the highest radiation component from above and from the N. The NE-SW rows received high levels of radiation from above, from the SE until 10:00, and from the NW from 13:00. A similar profile can be described for NW-SE rows, but with high radiation received from the NE up to 13:00 and from the SW from 16:00. Overall, lowest leaf water potential occurred for NE-SW canopies, followed by those orientated NW-SE, NS and EW. Photosynthetic activity reflected the positive radiation impact of the sun azimuth during the grape ripening period; best overall performance seemed to occur for E and N exposed canopy sides. This was largely driven by the responsiveness of the secondary leaves to radiation. Photosynthetic output decreased from apical to basal canopy zones with low, erratic values in the light-limited canopy centre. The NS and EW orientated canopies generally showed the highest average photosynthesis, while it was lower for the sides facing S, SE and SW. The results provide a better understanding of the physiological functioning of horizontal and vertical leaf layers in differently orientated grapevine canopies, as affected by climatic conditions. The study contributes to the longstanding challenges of capturing the complexity of parallel microclimatic and physiological output of grapevine canopies under open field conditions. The results can be directly applied to the selection of vineyard practices and seasonal management to ensure the attainment of yield, grape composition and wine quality objectives.

Viticulture practices that change the light distribution in the grapevine canopy can interfere with several physiological mechanisms, such as grape berry photosynthesis and other metabolic pathways, and consequently impact the berry biochemical composition, which is key to the final wine quality. We previously showed that the photosynthetic activity of exocarp and seed tissues from a white cultivar (Alvarinho) was in fact responsive to the light microclimate in the canopy (low and high light, LL and HL, respectively), and that these different light microclimates also led to distinct metabolite profiles, suggesting a berry tissue-specific interlink between photosynthesis and metabolism. In the present work, we analyzed the transcript levels of key genes in exocarps and seed integuments of berries from the same cultivar collected from HL and LL microclimates at three developmental stages, using real-time qPCR. In exocarp, the expression levels of genes involved in carbohydrate metabolism (VvSuSy1), phenylpropanoid (VvPAL1), stilbenoid (VvSTS1), and flavan-3-ol synthesis (VvDFR, VvLAR2, and VvANR) were highest at the green stage. In seeds, the expression of several genes associated with both phenylpropanoid (VvCHS1 and VvCHS3) and flavan-3-ol synthesis (VvDFR and VvLAR2) showed a peak at the véraison stage, whereas that of RuBisCO was maintained up to the mature stage. Overall, the HL microclimate, compared to that of LL, resulted in a higher expression of genes encoding elements associated with both photosynthesis (VvChlSyn and VvRuBisCO), carbohydrate metabolism (VvSPS1), and photoprotection (carotenoid pathways genes) in both tissues. HL also induced the expression of the VvFLS1 gene, which was translated into a higher activity of the FLS enzyme producing flavonol-type flavonoids, whereas the expression of several other flavonoid pathway genes (e.g., VvCHS3, VvSTS1, VvDFR, and VvLDOX) was reduced, suggesting a specific role of flavonols in photoprotection of berries growing in the HL microclimate. This work suggests a possible link at the transcriptional level between berry photosynthesis and pathways of primary and secondary metabolism, and provides relevant information for improving the management of the light microenvironment at canopy level of the grapes.

Several studies have revealed that fruit-zone leaf removal could change the microclimate of grapevine growth, thereby causing complex effects on fruit composition. This study analyzed the profiles of volatiles in Cabernet Sauvignon (Vitis vinifera L.) grapes exposed to leaf removal treatment at different phenological periods in three continuous years. The treatments (leaf removal before flowering, after flowering, and veraison) were applied to Cabernet Sauvignon grapevines grown in Yantai (Shandong, China). Berry samples were harvested at maturation to determine the chemical composition, including total soluble solids, phenols, and volatiles. Leaf removal (particularly before flowering) could increase total soluble solids and phenols (anthocyanins, flavonols, and tartaric esters). Volatiles greatly changed in the different years, and leaf removal before flowering could increase the concentration of amino acid-derived volatiles and isoprene-derived volatiles compared with leaf removal after flowering or at veraison. This research provides a basis for further studies on optimizing Cabernet Sauvignon aroma and breeding in vineyards.

Phomopsis viticola (Sacc.) Sacc. (syn. Cryptosporella viticola Shear, Diaporthe viticola Nitschke, Diplodia viticola Desm, Fusicoccum viticolum Reddick, Phoma flaccida Viala & Ravaz, Phoma viticola Sacc.), is the causal agent of the grapevine disease named ‘Phomopsis cane’ and ‘Leaf spot’ in the U.S.A. or ‘Excoriose’ in Europe. This study aims to evaluate the influence of the microclimate on Phomopsis viticola attack in Aiud-Ciumbrud vineyards. The observations were done on four plots in Aiud-Ciumbrud vineyards in the period March-August 2020. Up to the end of August 2020, ten treatments with contact and systemic products based on metiram and sulphour were done together with the other standard agro-technological operations. In the ecological conditions of spring-summer 2020, with higher temperature than the average in January, February, March and June, more rain than the average in February, March and June and less rain in January, April and May, we found frequency of the excoriosis in the range of 4%-12% at the beginning of the season. After the fungicide treatments, the attack frequency decreased up to 0%-7%. In the present research work, we show that in Aiud-Ciumbrud vineyards Phomopsis viticola attack was present and influenced by the microclimate conditions and also it was reduced by the fungicide treatments.

The influence of light and thermal microclimate on berry quality of a Vermentino vineyard, managed with deficit irrigation strategies in north-western Sardinia, was analyzed. Two water deficit, pre- (ED) and post-veraison (LD), an irrigation (IC) and a non-irrigation (NC) control treatments were compared during berry development. Grapevine performances were evaluated by analyzing leaf gas exchange, source-sink balance, light and thermal microclimate effects on berry composition. Early and/or late deficit irrigation following a mild to moderate water stress threshold enabled high leaf physiological performances. Though with high stomatal conductance sensitivity to water deficit and anisohydric behavior, this variety exhibited high assimilation rate and quick recovery capacity after enduring moderate and severe water stress. All treatments achieved satisfactory sugar and acidic levels. Berry phenols were higher in LD due to lower canopy coverage and better light conditions compared to IC. Up to mid-ripening, cluster exposure to elevated temperatures negatively influenced phenolic accumulation, mostly in NC and to a lower extent in ED. In the last ripening weeks, total phenols was majorly influenced by light interception.

Le réchauffement climatique planétaire annoncé ne sera pas sans conséquence sur le métabolisme de la baie et en particulier sur la teneur en composés phénoliques. Les objectifs de cette thèse visent à mieux comprendre les processus de régulation associant le microclimat des baies et la synthèse des composés phénoliques. Par des approches moléculaires et biochimiques, ce travail a permis de mieux décrire les réponses spécifiques des baies de raisin (cultivar Cabernet-Sauvignon) aux facteurs rayonnement et température.L'analyse du transcriptome des baies exposées soit à un stress thermique soit à un stress lumineux a mis en lumière deux processus, une réponse rapide ayant lieu dès les premières heures de traitement et une réponse apparaissant au bout de plusieurs jours d’exposition aux stress. Cette étude a également permis de valider le système expérimental de découplage des effets du rayonnement et de la température.L'analyse des profils d’expression d’une vingtaine de gènes intervenant dans la voie de biosynthèse des flavonoïdes révèle des différences dans la réponse transcriptionnelle des gènes en fonction du stress et du stade développement auquel il a été appliqué. Néanmoins cette réponse n'est pas ou peu corrélée avec les variations des teneurs en anthocyanes et flavonols observées. Les teneurs en anthocyanes sont fortement réduites par l’action de la chaleur alors que les teneurs de certains flavonols augmentent sous l’influence du rayonnement. Au niveau des acides présents dans la pulpe des baies, l’acide malique voit sa teneur réduite sous l’effet de la chaleur ainsi que d’une forte intensité lumineuse. Les analyses montrent un impact important du stress thermique sur la teneur de la phénylalanine, de la tyrosine et de la lysine dans la pellicule.Parallèlement, l'initiation d’une étude du métabolome des pellicules de baies de raisin a été entreprise par UPLC-ESI-LTQ-Orbitrap™ et a permis d'acquérir des bases solides pour optimiser le protocole utilisé en vue d'analyses futures. Cette étude permet de dresser une liste préliminaire de métabolites d’intérêts.Enfin, le gène VvGOLS1 (Galactinol synthase 1) voit son expression stimulée dans les baies exposées au stress thermique, ce qui se traduit par une accumulation de galactinol, précurseur de la voie des RFOs. Un rôle de molécule «signal» est envisagé pour le galactinol. Un régulateur de la transcription de VvGOLS1 a également été identifié par des expériences d'expression transitoire en protoplastes. Il s'agit du facteur de transcription VvHsfA2, dont l'expression est également stimulée par le stress thermique. Dans ce contexte, la caractérisation des gènes de la famille des Hsfs (Heat Stress Factors) a été initée
Global warming will affect berry metabolism, and especially phenylpropanoïd contents. This PhD work aimed to acquire a better understanding on the cellular processus linking the microclimate and the phenolic synthesis. By molecular and biochemical approaches, we extended this study to detail specific responses taking place in berries under heat and light stress.Transcriptomic analysis of heat-stressed and light-stressed berries showed the existence of two processes that occur in exposed berries. The first one triggers a rapid and transient expression of genes within the first hours of treatment. The second one mobilizes a set of genes showing increase in their expression after several days of stress exposure. Furthermore, this study validated the experimental set used to discriminate the effects of light and temperature, respectively.Expression analysis of 20 genes involved in the flavonoid biosynthetic pathway revealed strong differences among the transcriptional responses, depending on the nature of stress and the developmental stage of the berry. However, expression patterns of genes involved in the biosynthesis of flavonoid could not fully explain the changes in anthocyanin and flavonol contents. This suggests that additional regulation processes such as post-traductional modifications of enzymes or metabolite degradation might take place in berries under abiotic stress. Anthocyanin content decreases under heat stress whereas flavonol content increases under high light. Malic acid increases in berry exposed to heat stress and high light. Moreover, heat-stressed berries showed an accumulation of phenylalanine, tyrosine and lysine in skin but not in pulp.In parallel, a metabolomic analysis was initiated on stress exposed berry skins by using UPLC-ESI-LTQ-Orbitrap™ technology. The first experiments revealed contrasted metabolite contents in berries according to the stress applied, and highlighted several metabolites of interest. The preliminary assays will help optimize this powerful tool for futures analysis.Finally, expression of VvGOLS1 (Galactinol synthase 1) was strongly induced in grape berries exposed to heat stress, in good agreement with the observed galactinol accumulation. Role of galactinol as a signaling molecule is discussed. Transient expression experiments revealed that VvGOLS1 expression is regulated at the transcriptional level through VvHsfA2 action. VvHsfA2 expression is also stimulated under heat stress. In this context, characterization of the grapevine heat stress factors was initiated

L'essor de l'agriculture numérique permet de plus en plus d'observer de manière automatisée et parfois à haute fréquence des dynamiques d'élaboration de la production et de sa qualité en fonction du climat. Les données issues de ces observations dynamiques peuvent être considérées comme des données fonctionnelles. Analyser ce nouveau type de données nécessite d'étendre les outils statistiques usuels au cas fonctionnel ou d'en proposer de nouveaux.Nous avons proposé dans cette thèse une nouvelle approche (SpiceFP: Sparse and Structured Procedure to Identify Combined Effects of Functional Predictors) permettant d'expliquer les variations d'une variable réponse scalaire par deux ou trois prédicteurs fonctionnels dans un contexte d'influence conjointe de ces derniers. Une attention particulière a été apportée à l'interprétabilité des résultats via l'utilisation de classes d'intervalles combinées définissant une partition du domaine d'observation des facteurs explicatifs. Les développements récents autour des modèles LASSO (Least Absolute Shrinkage and Selection Operator) ont été adaptés pour estimer les régions d'influence dans la partition via une régression pénalisée généralisée. L'approche intègre aussi une double sélection, de modèles (parmi les partitions possibles) et de variables (pour une partition donnée) à partir des critères d'information AIC et BIC. La présentation méthodologique de l'approche, son étude grâce à des simulations ainsi qu'une étude de cas basée sur des données réelles ont été présentés dans le chapitre 2.Les données réelles utilisées au cours de cette thèse proviennent d'une expérimentation viticole visant à mieux comprendre l'impact du changement climatique sur l'accumulation d'anthocyanes dans les baies. L'analyse de ces données dans le chapitre 3 à l'aide de l'approche SpiceFP que nous avons étendue a permis d'identifier un impact négatif des combinaisons matinales de faible irradiance (inférieure à environ 100 µmol/s/m2 ou 45 µmol/s/m2 selon l'état avancé-retardé des baies) et température élevée (supérieure à environ 25°C). Une légère différence induite par la température de la nuit a été observée entre ces effets identifiés en matinée.Dans le chapitre 4 de cette thèse, nous proposons une implémentation de l'approche proposée sous la forme d'un package R. Cette implémentation fournit un ensemble de fonctions permettant de construire les intervalles de classes suivant des échelles linéaire ou logarithmique, de transformer les prédicteurs fonctionnels grâces aux classes d'intervalles combinées puis de mettre en oeuvre l'approche en deux ou trois dimensions. D'autres fonctions facilitent la réalisation de post-traitements ou permettent à l'utilisateur de s'intéresser à d'autres modèles que ceux retenus par l'approche comme par exemple une moyenne de différents modèles.Mots clés: Régressions pénalisées, Interaction, critères d'information, scalar-on-function, coefficients interprétables, microclimat de la vigne
The development of digital agriculture allows to observe at high frequency the dynamics of production according to the climate. Data from these dynamic observations can be considered as functional data. To analyze this new type of data, it is necessary to extend the usual statistical tools to the functional case or develop new ones.In this thesis, we have proposed a new approach (SpiceFP: Sparse and Structured Procedure to Identify Combined Effects of Functional Predictors) to explain the variations of a scalar response variable by two or three functional predictors in a context of joint influence of these predictors. Particular attention was paid to the interpretability of the results through the use of combined interval classes defining a partition of the observation domain of the explanatory factors. Recent developments around LASSO (Least Absolute Shrinkage and Selection Operator) models have been adapted to estimate the areas of influence in the partition via a generalized penalized regression. The approach also integrates a double selection, of models (among the possible partitions) and of variables (areas inside a given partition) based on AIC and BIC information criteria. The methodological description of the approach, its study through simulations as well as a case study based on real data have been presented in chapter 2 of this thesis.The real data used in this thesis were obtained from a vineyard experiment aimed at understanding the impact of climate change on anthcyanins accumulation in berries. Analysis of these data in chapter 3 using SpiceFP and one extension identified a negative impact of morning combinations of low irradiance (lower than about 100 µmol/s/m2 or 45 µmol/s/m2 depending on the advanced-delayed state of the berries) and high temperature (higher than about 25°C). A slight difference associated with overnight temperature occurred between these effects identified in the morning.In chapter 4 of this thesis, we propose an implementation of the proposed approach as an R package. This implementation provides a set of functions allowing to build the class intervals according to linear or logarithmic scales, to transform the functional predictors using the joint class intervals and finally to execute the approach in two or three dimensions. Other functions help to perform post-processing or allow the user to explore other models than those selected by the approach, such as an average of different models.Keywords: Penalized regressions, Interaction, information criteria, scalar-on-function, interpretable coefficients,grapevine microclimate

Effects of trellising on water use, absorption of photosynthetically active radiation (PAR, 400 to 700 nm wavelength) by foliage and potentially by fruit, fruit composition, and yield were studied in 1988 under semi-arid conditions on field-grown Vitis vinifera L. 'Petite Sirah' grapevines in a mature vineyard. The positioning of shoots on trellises resulted in canopies that were (1) positioned vertically (vertical canopy), (2) positioned in a "V" pattern with sides inclined 60° from horizontal (inclined canopy), and (3) inclined toward the vineyard floor (standard canopy). Seasonal water use values determined from neutron scattering data were 393 ± 61, 554 ± 73, and 455 ± 57 mm for the standard, vertical and inclined canopies, respectively. On average, about 50% of seasonal water consumption occurred between fruit set and filling stages for each type of canopy. Average crop factors (ratio of actual to reference crop evapotranspiration) of 0.383, 0.540 and 0.444 were for the period bud burst to harvest for standard, vertical and inclined canopy systems, respectively. The diurnal water use patterns of the three trellising canopies were very similar when measured by either the heat pulse technique or by porometer. The average daily heat pulse velocity (HPV) for selected vertical, inclined and standard canopies for 6 days were 8.77, 7.58 and 6.85 cm h⁻¹, respectively. The HPV technique indicated that the average daily water use of the whole plant was 0.227, 0.192 and 0.137 kg/m² leaf area/d for standard, vertical and inclined canopies, respectively. The daily average transpiration rates as measured by the HPV technique were 32, 31, and 25% higher than the average transpiration rates estimated from porometer data for standard, vertical and inclined canopies, respectively. Stomatal conductances of the vertical and inclined canopies were 20 and 40%, respectively, below that of standard canopy. PAR absorption by foliage during mid-day was highest in the standard trellis, and lowest in the inclined trellis. PAR potentially available for absorption by fruits was lowest in the standard trellis, and highest in the inclined trellis. In both inclined and vertical canopies, the average sunfleck values were 26%, but was only 2% in the standard canopy. Analysis of fruit composition at harvest revealed that total dissolved solids (°Brix) was significantly higher in the inclined trellis than for the vertical trellis or the standard trellis. The inclined trellis resulted in the highest alcohol content of wine. Per vine yields did not differ significantly among the three trellis systems. Overall, the standard trellis was optimum because grapevines consumed less water and produced a shading which protected the fruit from direct solar radiation.

Plasmopara viticola is the causal agent of the downy mildew, the most severe disease of grapevines. In order to prevent and/or mitigate the plant disease, fungicide treatments are often required, despite the presence of side effects on the environment and the potential hazard for human health in case of prolonged exposition. The choice of proper treatments and optimal scheduling is the key to managing downy mildew in an eco-friendly way. Plasmopara viticola’s growth depends on meteorological variables, like temperature and rain, plant’s genotype, the degree of exposition to oospores and soil conditions. Field measurements are expensive both for the high cost of oospore sensors and for the need of meteorological sensors describing the microclimate around each plant. Whatever the amount of information gathered from sensors of a vineyard, a decision must be taken, e.g. according to the predicted probability of infected leaves (and grapes) and considering side effects like the impact of a chemical treatment on the soil and on biodiversity. A multi-attribute utility function on variables describing future consequences of a decision may be defined by following the assumptions of utility independence and preferential independence. The inherent uncertainty is described by a Bayesian prior-predictive distribution where prior are elicited from experts, and eventually updated using available data. The resulting optimal decision is defined as the argument that maximises the expected value of the utility function. The proposed utility function may be tuned to match the individual preference scheme of the winegrower and eventually extended to include further variables like those describing the quality and yield of grapes.

Downy and powdery mildews are two of the main diseases threatening grapevine cultivation worldwide caused by the phytopathogens Plasmopara viticola and Uncinula necator, respectively. These diseases may cause severe damage to grapevines by inducing wilting of plant organs, including bunches, especially when vines are untreated. This fact, together with the widespread of these pathogens due to the large extensions of land dedicated to grapevine monoculture, makes necessary to develop new predictive modeling tools that allow anticipating disease appearance in the vineyard, minimizing the losses in fruit yield and quality, and helping farmers in defining appropriate and more sustainable disease management strategies (fungicides applied at the right time and dose). For this purpose, farms located in three countries (Portugal, Spain, and Italy) were selected to study the relationship between the microclimatic characteristics of the plots, the phenological stage of the plants throughout the annual cycle, and the presence of both pathogens using different Machine and Deep Learning classification algorithms: Logistic Regression, Decision Trees, Random Forest, Gradient Boosting, K-Nearest Neighbors, Naïve Bayes, Support Vector Machines, and Deep Neural Networks. The results showed that, after an entire annual grapevine cycle, the best performing models were Support Vector Machines for downy mildew and Random Forest for powdery mildew, providing a prediction accuracy of more than 90% for the infection risk and more than 80% for the treatment recommendation. These models will be fine-tuned during two additional vegetative seasons to ensure their robustness and will receive short- and medium-term climatological and phenological forecasts to make recommendations. The preliminary results obtained show that these models are a promising tool in the field of plant disease prevention and resource saving.

The research was carried out between the 2020 and 2022 growing seasons, in six different wine-growing regions of Romania, including the west, central, south, and east. The grapevine growing technology and production process were investigated, which were carried out differently depending on the soil and environmental resources in each growing area. The climatic conditions were also analyzed, as well as the influence on the production and quality of two grape cultivars for superior red wines grown in the researched areas. Soil management systems, fertilization, disease and insect control were investigated. At the same time, less invasive, eco friendly experimental alternatives were tested as an option to conventional technological versions. Observations and determinations were performed for each experimental alternative regarding the combined influence of the local microclimate and the different management on grape production and concentration in sugars, acidity, and vitamins. Although the grape yield was lower compared to the control variants, the experimental, less invasive and eco-friendly variants proved to be viable alternatives to the conventional ones. These experimental alternatives resulted in lower carbon emissions, less pollution, healthier viticultural products, and higher profits.