Ecophysiological Modeling of Grapevine Water Stress in Burgundy Terroirs by a Machine-Learning Approach

GrapevineXL reliably predicts multi-annual dynamics of vine water status, berry growth, and sugar accumulation in vineyards

Climate and water availability greatly affect each season's grape yield and quality. Using models to accurately predict environment impacts on fruit productivity and quality is a huge challenge. We calibrated and validated the functional-structural model, GrapevineXL, with a data set including grapevine seasonal midday stem water potential (Ψ_xylem), berry dry weight (DW), fresh weight (FW), and sugar concentration per volume ([Sugar]) for a wine grape cultivar (Vitis vinifera cv. Cabernet Franc) in field conditions over 13 years in Bordeaux, France. Our results showed that the model could make a fair prediction of seasonal Ψ_xylem and good-to-excellent predictions of berry DW, FW, [Sugar] and leaf gas exchange responses to predawn and midday leaf water potentials under diverse environmental conditions with 14 key parameters. By running virtual experiments to mimic climate change, an advanced veraison (i.e. the onset of ripening) of 14 and 28 days led to significant decreases of berry FW by 2.70% and 3.22%, clear increases of berry [Sugar] by 2.90% and 4.29%, and shortened ripening duration in 8 out of 13 simulated years, respectively. Moreover, the impact of the advanced veraison varied with seasonal patterns of climate and soil water availability. Overall, the results showed that the GrapevineXL model can predict plant water use and berry growth in field conditions and could serve as a valuable tool for designing sustainable vineyard management strategies to cope with climate change.

Water stress assessment on grapevines by using classification and regression trees

Multiple factors, such as the vineyard environment and winemaking practices, are known to affect the development of vines as well as the final composition of grapes. Water stress promotes the synthesis of phenols and is associated with grape quality as long as it does not inhibit production. To identify the key parameters for managing water stress and grape quality, multivariate statistical analysis is essential. Classification and regression trees are methods for constructing prediction models from data, especially when data are complex and when constructing a single global model is difficult and models are challenging to interpret. The models were obtained by recursively partitioning the data space and fitting a simple prediction model within each partition. The partitioning can be represented graphically as a decision tree. This approach permitted the most decisive variables for predicting the most vulnerable vineyards and wine quality parameters associated with water stress. In Priorat AOC, Carignan grapevines had the highest water potential and abscisic acid concentration in the early growth plant stages and permitted vineyards to be classified by mesoclimate. This information is useful for identifying which measurements could most easily differentiate between early and late-ripening vineyards. LWP and Ts during an early physiological stage (pea size) permitted warm and cold areas to be differentiated.

Deep Learning Sensor Fusion in Plant Water Stress Assessment: A Comprehensive Review

Water stress is one of the major challenges to food security, causing a significant economic loss for the nation as well for growers. Accurate assessment of water stress will enhance agricultural productivity through optimization of plant water usage, maximizing plant breeding strategies, and preventing forest wildfire for better ecosystem management. Recent advancements in sensor technologies have enabled high-throughput, non-contact, and cost-efficient plant water stress assessment through intelligence system modeling. The advanced deep learning sensor fusion technique has been reported to improve the performance of the machine learning application for processing the collected sensory data. This paper extensively reviews the state-of-the-art methods for plant water stress assessment that utilized the deep learning sensor fusion approach in their application, together with future prospects and challenges of the application domain. Notably, 37 deep learning solutions fell under six main areas, namely soil moisture estimation, soil water modelling, evapotranspiration estimation, evapotranspiration forecasting, plant water status estimation and plant water stress identification. Basically, there are eight deep learning solutions compiled for the 3D-dimensional data and plant varieties challenge, including unbalanced data that occurred due to isohydric plants, and the effect of variations that occur within the same species but cultivated from different locations.

Grapevine Red Blotch Virus May Reduce Carbon Translocation Leading to Impaired Grape Berry Ripening

Grapevine red blotch virus (GRBV) is suspected to alter berry ripening and chemistry. This study performed a physiological characterization of GRBV infected grapevines with attention to the factors leading to chemical changes during ripening of Cabernet Sauvignon in two rootstocks, 110R and 420A. RB(+) grapevines had transiently lower net photosynthesis; however, berry total soluble solids (TSS) accumulation was consistently reduced in the two years of study. Accumulation of anthocyanins and loss of titratable acidity and proanthocyanins were also delayed in RB(+) plants. However, the comparison of samples with the same TSS led to lower pH and anthocyanins content. The reduction in carbon import into berries under mild and transient reductions in carbon fixation suggested an impairment of translocation mechanisms with RB(+), leading into a desynchronization of ripening-related processes.

Controversies in Midday Water Potential Regulation and Stomatal Behavior Might Result From the Environment, Genotype, and/or Rootstock: Evidence From Carménère and Syrah Grapevine Varieties

Controversies exist regarding the iso/anisohydric continuum for classifying plant water-use strategies. Isohydricity has been argued to result from plant-environment interaction rather than it being an intrinsic property of the plant itself. Discrepancies remain regarding the degree of isohydricity (σ) of plants and their threshold for physiological responses and resistance to drought. Thus, the aim of this study was to evaluate the isohydricity of the grapevine varieties Syrah and Carménère under a non-lethal water deficit progression from veraison from two different locations, the Cachapoal Valley (CV) and Maipo Valley (MV), in central Chile and with different rootstock only in Syrah. For this purpose, the midday stem water potential (Ψ_mds) regulation and stomatal responses to drought, leaf traits related to pressure-volume curves, stomatal sensitivity to ABA, cavitation threshold, and photosynthetic responses were assessed. A higher atmospheric water demand was observed in the CV compared to the MV, with lower Ψ_mds values in the former for both varieties. Also, the σ values in Carménère were 1.11 ± 0.14 MPa MPa^-1 and 0.68 ± 0.18 MPa MPa^-1 in the CV and MV, respectively, and in Syrah they were 1.10 ± 0.07 MPa MPa^-1 in the CV and 0.60 ± 0.10 MPa MPa^-1 in the MV. Even though similar variations in σ between locations in both varieties were evident, Carménère plants showed a conserved stomatal response to Ψ_mds in both study sites, while those of Syrah resulted in a higher stomatal sensitivity to Ψ_mds in the site of lower σ. Besides the differences in seasonal weather conditions, it is likely that the different rootstock and clonal variability of each season in Syrah were able to induce coordinated changes in σ, Ψ_gs12, and osmotic potential at full turgor (π₀). On the other hand, irrespective of the σ, and given the similarity between the π₀ and Ψ_gs12 in leaves before drought, it seems that π₀ could be a convenient tool for assessing the Ψ_mds threshold values posing a risk to the plants in order to aid the irrigation decision making in grapevines under controlled water deficit. Finally, water deficits in vineyards might irreversibly compromise the photosynthetic capacity of leaves.

A dynamic viticultural zoning to explore the resilience of terroir concept under climate change

Climate change (CC) directly influences agricultural sectors, presenting the need to identify both adaptation and mitigation actions that can make local farming communities and crop production more resilient. In this context, the viticultural sector is one of those most challenged by CC due to the need to combine grape quality, grapevine cultivar adaptation and therefore farmers' future incomes. Thus, understanding how suitability for viticulture is changing under CC is of primary interest in the development of adaptation strategies in traditional wine-growing regions. Considering that climate is an essential part of the terroir system, the expected variability in climate change could have a marked influence on terroir resilience with important effects on local farming communities in viticultural regions. From this perspective, the aim of this paper is to define a new dynamic viticultural zoning procedure that is able to integrate the effects of CC on grape quality responses and evaluate terroir resilience, providing a support tool for stakeholders involved in viticultural planning (winegrowers, winegrower consortiums, policy makers etc.). To achieve these aims, a Hybrid Land Evaluation System, combining qualitative (standard Land Evaluation) and quantitative (simulation model) approaches, was applied within a traditional region devoted to high quality wine production in Southern Italy (Valle Telesina, BN), for a specific grapevine cultivar (Aglianico). The work employed high resolution climate projections that were derived under two different IPCC scenarios, namely RCP 4.5 and RCP 8.5. The results obtained indicate that: (i) only 2% of the suitable area of Valle Telesina expresses the concept of terroir resilience orientated towards Aglianico ultra quality grape production; (ii) within 2010-2040, it is expected that 41% of the area suitable for Aglianico cultivation will need irrigation to achieve quality grape production; (iii) by 2100, climate change benefits for the cultivation of Aglianico will decrease, as well as the suitable areas.

Vineyard water status assessment using on-the-go thermal imaging and machine learning

The high impact of irrigation in crop quality and yield in grapevine makes the development of plant water status monitoring systems an essential issue in the context of sustainable viticulture. This study presents an on-the-go approach for the estimation of vineyard water status using thermal imaging and machine learning. The experiments were conducted during seven different weeks from July to September in season 2016. A thermal camera was embedded on an all-terrain vehicle moving at 5 km/h to take on-the-go thermal images of the vineyard canopy at 1.2 m of distance and 1.0 m from the ground. The two sides of the canopy were measured for the development of side-specific and global models. Stem water potential was acquired and used as reference method. Additionally, reference temperatures Tdry and Twet were determined for the calculation of two thermal indices: the crop water stress index (CWSI) and the Jones index (Ig). Prediction models were built with and without considering the reference temperatures as input of the training algorithms. When using the reference temperatures, the best models casted determination coefficients R2 of 0.61 and 0.58 for cross validation and prediction (RMSE values of 0.190 MPa and 0.204 MPa), respectively. Nevertheless, when the reference temperatures were not considered in the training of the models, their performance statistics responded in the same way, returning R2 values up to 0.62 and 0.65 for cross validation and prediction (RMSE values of 0.190 MPa and 0.184 MPa), respectively. The outcomes provided by the machine learning algorithms support the use of thermal imaging for fast, reliable estimation of a vineyard water status, even suppressing the necessity of supervised acquisition of reference temperatures. The new developed on-the-go method can be very useful in the grape and wine industry for assessing and mapping vineyard water status.

Water status and must composition in grapevine cv. Chardonnay with different soils and topography and a mini meta-analysis of the δ13 C/water potentials correlation

BACKGROUND

The measurement of carbon isotopic discrimination in grape sugars at harvest (δ¹³ C) is an integrated assessment of water status during ripening. It is an efficient alternative to assess variability in the field and discriminate between management zones in precision viticulture, but further work is needed to completely understand the signal.

RESULTS

This work, spanning over 3 years, performed in a hillslope toposequence in Burgundy, delineates the relationships between main soil properties (gravel amount, slope, texture) and the grapevine water status assessed by δ¹³ C. The highest δ¹³ C, indicating most severe water deficit, was recorded in gravelly soils on steep slopes. The amount of sugars and malic and tartaric acids was also related to δ¹³ C. The relationship between δ¹³ C and predawn leaf water potentials (Ψ_pd ) was also investigated, because the absolute values of measured δ¹³ C were lower than the values currently found in the literature.

CONCLUSIONS

A mini-meta-analysis was performed, which showed that the slope of the relationships between minimum Ψ_pd and δ¹³ C was stable across studies (a change of 1‰ in δ¹³ C corresponded to a change of -0.2 MPa in the minimum Ψ_pd ), while the intercept of the comparison δ¹³ C/Ψ_pd changed, probably because of genetic variations between varieties, or environmental differences. © 2017 Society of Chemical Industry.

Assessing Spatial Variability of Grape Skin Flavonoids at the Vineyard Scale Based on Plant Water Status Mapping

Plant water stress affects grape (Vitis vinifera L. cv. Cabernet Sauvignon) berry composition and is variable in space due to variations in the physical environment at the growing site. We monitored the natural variability of grapevine water stress by stem water potential (Ψ_stem) and leaf gas exchange in an equi-distant grid in a commercial vineyard. Spatial differences were measured and related to topographical variation by modeling. Geospatial analysis and clustering allowed researchers to differentiate the vineyard block into two distinct zones having severe and moderate water stress where it varied by 0.2 MPa. Differences in stem water potential affected stomatal conductance, net carbon assimilation, and intrinsic water use efficiency that were different in all measurement dates. The two zones were selectively sampled at harvest for measurements of berry chemistry. The water status zones did not affect berry mass or yield per vine. Significant difference in total soluble solids was observed (3.56 Brix), and in titratable acidity, thus indicating a direct effect of water stress on ripening acceleration. Berry skin flavonol and anthocyanin composition and concentration were measured by C18 reversed-phased high-performance liquid chromatography (HPLC). The anthocyanins were most affected by the two water stress zones. The dihydroxylated anthocyanins were more affected than trihydroxylated; therefore, the ratio of the two forms increased. Flavonols were different in total amounts, but hydroxylation patterns were not affected. Proanthocyanidin isolates were characterized by acid catalysis in the presence of excess phloroglucinol followed by reversed-phase HPLC. Proanthocyanidins showed the least significant difference, although (+)-catechin terminal subunits were important predictors in a partial least square model used to summarize the multivariate relationships, predicting Ψ_stem or the management zone. The results provide fundamental information on vineyard water status to discriminate harvest or direction to vineyard operators to modify irrigation management to equilibrate berry composition at harvest.