Terroir 2020 banner
IVES 9 IVES Conference Series 9 International Terroir Conferences 9 Terroir 2020 9 History and innovation of terroir 9 Within-vineyard variability in grape composition at the estate scale can be assessed through machine-learning modeling of plant water status in space and time. A case study from the hills of Adelaida District AVA, Paso Robles, CA, USA

Within-vineyard variability in grape composition at the estate scale can be assessed through machine-learning modeling of plant water status in space and time. A case study from the hills of Adelaida District AVA, Paso Robles, CA, USA

Abstract

Aim: Through machine-learning modelling of plant water status from environmental characteristics, this work aims to develop a model able to predict grape phenolic composition in space and time to guide selective harvest decisions at the estate scale.

Methods and Results: Work was conducted during two consecutive seasons in a ~40ha (100ac) premium wine estate located in the Adelaida District AVA of Paso Robles, CA, USA. The vineyard topography was very diverse, with a large variation in slope grade (0-30%) and exposure (0-359). One hundred experimental units were identified by a maximum dissimilarity sampling algorithm based on environmental attributes derived from a digital elevation model and a soil map. Reflecting the estate varietal distribution, ~70% were Cabernet-Sauvignon units, 20% Cabernet-Franc, and 10% Petit-Verdot units grafted on 1103P or 420A (~50-50%). Grapevine water status was monitored by weekly measurements of stem water potentials, Ψstem, and analysis of carbon isotope discrimination of grape musts, δ13C, at harvest. The grape composition during ripening was assessed by measuring total soluble solids, titratable acidity, and pH of musts and by a comprehensive assessment of skin phenolic composition with HPLC-DAD. Additional field measurements included shoot-count and yield assessment. Vegetation indexes were derived from canopy reflectance obtained from ~3m resolution CubeSat satellites. Irrigation amounts were provided by the grower, and weather data were obtained from three on-site stations. 

Grapevine Ψstem was modelled from weather data (temperature, relative humidity, rainfall), irrigation amounts, vegetation indexes, topographic attributes, soil type using a gradient-boosting-machine algorithm. The model was able to predict plant water status with <0.1 MPa of error (estimated as root mean squared error in a cross-validation procedure). Significant differences in water status were observed between rootstocks and main environmental drivers were slope grade and aspect (i.e. exposure). External validation of the model was carried out by correlating predictions with δ13C. The model allowed obtaining high-resolution daily mapping of Ψstem at the estate scale. Time-series of grapevine Ψstem were significantly correlated with the content of total soluble solids of musts, grape anthocyanin amounts, and the ratio of tri-hydroxylated to di-hydroxylated compounds at harvest and mapped. Spatial-clustering of grape anthocyanin composition was obtained from Ψstem model-estimates and used to guide harvest selectively. 

Conclusion: 

Grapevine water status confirmed to be an important driver in the variability of grape composition, even though the vineyard was irrigated. Variability in water status was related to environmental attributes (slope, aspect, incoming radiation) and the machine-learning approach proved to be useful to predict and understand plant-environment interactions and effects on grape composition in a varied and large dataset.

Significance and Impact of the Study: Vineyards are often located on slopes and accurate modelling of grapevine water status in hillslope conditions is a challenging task. This research demonstrates for the first time that it is possible to obtain daily estimates of grapevine water status at the estate scale by re-elaborating routine measurements with machine-learning technologies. This information can be used to drive selective harvest decisions and clustering within-vineyard variability at the estate scale to easily implement selective harvest decisions.

DOI:

Publication date: March 19, 2021

Issue: Terroir 2020

Type: Video

Authors

Luca Brillante

California State University Fresno, Fresno, United States

Contact the author

Keywords

Grapevine water status, machine learning, phenolic composition

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

The impact of leaf canopy management on eco-physiology, wood chemical properties and microbial communities in root, trunk and cordon of Riesling grapevines (Vitis vinifera L.)

In the last decades, climate change required already adaptation of vineyard management. Increase in temperature and unexpected weather events cause changes in all phenological stages requiring new management tools. For example, defoliation can be a useful tool to reduce the sugar content in the berries creating differences in the wine profiles. In a ten-year field experiment using Riesling (Vitis vinifera L, planted 1986, Geisenheim, Germany), various mechanical defoliation strategies and different intensities were trialed until 2016 before the vineyard was uprooted. Wood was sampled from the plant compartments root, trunk, cordon and shoot for analyses of physicochemical properties (e.g. lignin and element content, pH, diameter), nonstructural carbohydrates and the microbial communities. The aim of the study was to investigate the influence of reduced canopy leaf area on the sink-source allocation into different compartments and potential changes of the fungal and prokaryotic wood-inhabiting community using a metabarcoding approach. Severe summer pruning (SSP) of the canopy and mechanical defoliation (MDC) above the bunch zone decreased the leaf area by 50% compared to control (C). SSP reduced the photosynthetic capacity, which resulted in an altered source-sink allocation and carbohydrate storage. With lower leaf area, less carbohydrates are allocated. This for example resulted in a decreased trunk diameter. Further, it affected the composition of the grapevine wood microbiota. SSP and MDC management changed significantly the prokaryotic community composition in wood of the root samples, but had no effect in other compartments. In general, this study found strong compartment and less management effects of the microbial community composition and associated physicochemical properties. The highest microbial diversities were identified in the wood of the trunk, and several species were recorded the first time in grapevine.

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.

Climate projections over France wine-growing region and its potential impact on phenology

Climate change represents a major challenge for the French wine industry. Climatic conditions in French vineyards have already changed and will continue to evolve. One of the notable effects on grapevine is the advancing growing season. The aim of this study is to characterise the evolution of agroclimatic indicators (Huglin index, number of hot days, mean temperature, cumulative rainfall and number of rainy days during the growing season) at French wine-growing regions scale between 1980 and 2019 using gridded data (8 km resolution, SAFRAN) and for the middle of the 21th century (2046-2065) with 21 GCMs statistically debiased and downscaled at 8 km. A set of three phenological models were used to simulate the budburst (BRIN, Smoothed-Utah), flowering, veraison and theoretical maturity (GFV and GSR) stages for two grape varieties (Chardonnay and Cabernet-Sauvignon) over the whole period studied. All the French wine-growing regions show an increase in both temperatures during the growing season and Huglin index. This increase is accompanied by an advance in the simulated flowering (+3 to +9 days), veraison (+6 to +13 days) and theoretical maturity (+6 to +16 days) stages, which are more noticeable in the north-eastern part of France. The climate projections unanimously show, for all the GCMs considered, a clear increase in the Huglin index (+662 to 771 °C.days compared to the 1980-1999 period) and in the number of hot days (+5.6 to 22.6 days) in all the wine regions studied. Regarding rainfall, the expected evolution remains very uncertain due to the heterogeneity of the climates simulated by the 21 models. Only 4 regions out of 21 have a significant decrease in the number of rainy days during the growing season. The two budburst models show a strong divergence in the evolution of this stage with an average difference of 18 days between the two models on all grapevine regions. The theoretical maturity is the most impacted stage with a potential advance between 40 and 23 days according to wine-growing regions.

Soil, vine, climate change – what is observed – what is expected

To evaluate the current and future impact of climate change on Viticulture requires an integrated view on a complex interacting system within the soil-plant-atmospheric continuum under continuous change. Aside of the globally observed increase in temperature in basically all viticulture regions for at least four decades, we observe several clear trends at the regional level in the ratio of precipitation to potential evapotranspiration. Additionally the recently published 6th assessment report of the IPCC (The physical science basis) shows case-dependent further expected shifts in climate patterns which will have substantial impacts on the way we will conduct viticulture in the decades to come.
Looking beyond climate developments, we observe rising temperatures in the upper soil layers which will have an impact on the distribution of microbial populations, the decay rate of organic matter or the storage capacity for carbon, thus affecting the emission of greenhouse gases (GHGs) and the viscosity of water in the soil-plant pathway, altering the transport of water. If the upper soil layers dry out faster due to less rainfall and/or increased evapotranspiration driven by higher temperatures, the spectral reflection properties of bare soil change and the transport of latent heat into the fruiting zone is increased putting a higher temperature load on the fruit. Interactions between micro-organisms in the rhizosphere and the grapevine root system are poorly understood but respond to environmental factors (such as increased soil temperatures) and the plant material (rootstock for instance), respectively the cultivation system (for example bio-organic versus conventional). This adds to an extremely complex system to manage in terms of increased resilience, adaptation to and even mitigation of climate change. Nevertheless, taken as a whole, effects on the individual expressions of wines with a given origin, seem highly likely to become more apparent.