Viticulture – Precision Viticulture Session

Accurate and Rapid Monitoring of Grape Ripening in the Field Through On-the-Go NIR/SWIR Hyperspectral Mapping

Luca Brillante,* Abiodun Abioye, Eve Laroche-Pinel, Guadalupe Partida,
Benjamin Corales, Kaylah Vasquez, Vincenzo Cianciola, and Brent Sams
*Department of Viticulture and Enology, California State University Fresno,
2360 E Barstow Ave, Fresno, CA, 93740 (lucabrillante@csufresno.edu)

Different factors can affect berry composition, such as soil characteristics, water availability, or other environmental factors. Knowing the chemical and physical variability of grapes in a vineyard can help manage growing conditions, avoid over-ripening berries, and plan the harvest. A UTV was adapted especially for this study to help lift the canopy and expose fruits. One hyperspectral camera in the NIR/SWIR domains was mounted on the back with GPS systems and halogen lights for night imaging. With this system, a Merlot vineyard located in Madera, California was imaged four times during the growing season and grapes were sampled for analysis in the laboratory. About 650 samples were collected and georeferenced. The grape signal was extracted through semantic segmentation and separated into grape, leaves, and background. The grape composition was predicted using four models: random forest (RF), extra tree regressor (ETR), extreme gradient boosting (XGboost), and gradient boosting (GB). The model’s performances were assessed using 10-fold cross-validation and an external test set collected in a different vineyard and growing season. Predicting grape composition using the reflectance spectrum exhibited promising results, with ETR having the best performance for the prediction of total soluble solids (R2 = 0.91; NRMSE = 7%), pH (R2 = 0.90; NRMSE = 6 %), titratable acidity (R2 = 0.85; NRMSE = 7.5 %), and total anthocyanins (R2 = 0.91; NRMSE = 7 %). The models were used to develop prediction maps to understand the spatial variability of grape composition attributes in the vineyard and ripening heterogeneity. This study successfully proposes a system to accurately and rapidly monitor grape ripening in the field based on on-the-go hyperspectral mapping.

Funding Support: American Vineyard Foundation, California State University – Agriculture Research Institute

Accounting for Spatial Variability to Efficiently Monitor Grape Composition in California Vineyards

Brent Sams,* Mahyar Aboutalebi, Riley Hibbard, Miriam Villa, Jared Nicholson, Luis Sanchez, and Nick Dokoozlian
*E & J Gallo Winery, 1541 Cummins Dr, Modesto, CA, 95358 (brent.sams@ejgallo.com)

Vineyard spatial variability, the inherent differences found across the physical spaces of vineyards, creates challenges for vineyard and winery management. Vineyard managers are tasked with producing high-quality grapes at the highest yield possible and wineries expect fruit delivered from these vineyards to be of uniform quality, despite differences in spatial variability. In recent years, variable-rate management has been widely discussed, but few options are available for commercial use. While these technologies develop, a more practical approach must be found for efficient management of grapes in vineyards and wineries. In 2022, six Cabernet Sauvignon vineyards in the Lodi area were selected for canopy characterization and fruit compositional analysis. During the 2023 season, 10 Sonoma County and 18 Lodi Cabernet Sauvignon vineyards were selected for maturity tracking and fruit compositional analysis. In both years, plots were distributed based on a targeted histogram analysis of early-season Sentinel-2 NDVI images. This targeted histogram analysis entailed selecting field plots in low-, medium-, and high-vigor categories, and identifying a single, three-pixel transect that best represented high, medium, and low histogram variability, otherwise known as the “Best Fit (BF)”. Results in 2022 showed that fruit zone light interception and fruit composition differed among high, medium, and low vigor zones, with the BF representing variability in most vineyards. The 2023 results confirmed that the BF could be used to monitor vineyard maturity in commercial vineyards. Variability caused by pest or disease pressure, topography, or vineyard management decisions created some limitations for the BF method and must be considered when deploying image-based decision platforms.

Funding Support: NA

Pin-Jui Chen, |Joshua VanderWeide | Christopher Mark | Simone D. Castellarin

Relationships among Vine Nutrient Status, Canopy Size, Vine Physiology, Yield, and Grape Aroma within Vineyards

Pin-Jui Chen,* Joshua VanderWeide, Christopher Mark, and Simone D. Castellarin
*Wine Research Centre, University of British Columbia, 2205 East Mall, Vancouver/ BC/ V6T 1Z4, Canada (pj0508@student.ubc.ca)

Several grape cultivars are characterized by a rich assortment of volatile terpenoids (mono- and sesqui-), a class of secondary metabolites that affect grape and wine aroma. Intra-vineyard factors that affect volatile terpenoids are not well known, despite potentially affecting the quality of grapes and wines. This study aimed to assess the relationships between grape volatile terpenoids and other vine parameters within vineyards. Two commercial vineyards (Riesling and Gewürztraminer) in the Okanagan Valley (British Columbia, Canada) were considered. To assess intra-vineyard variation, 40 and 48 plots distributed within the Riesling and Gewürztraminer vineyards, respectively, were selected. Three random vines per plot were used for all measurements. These included plant water status (stem water potential), leaf area, and leaf gas exchange (CO2 assimilation, transpiration, stomatal conductance), measured at bloom and veraison. At the same stages, normalized difference vegetative index (NDVI) and normalized difference red edge index (NDRE), calculated from remote sensing-based multispectral drone images and ground-based measurements, were used to estimate vine vigor. Vine nutrient status was determined by petiole analysis at veraison. Yield, berry technological quality (total soluble solids, pH, and titratable acidity), and volatile terpenoids were determined at harvest. The content of grape volatile terpenoids correlated positively with leaf area, NDVI, NDRE, and yield in Riesling, and with petiole nitrogen content, NDVI, NDRE, and yield in Gewürztraminer. Our study confirms that remote sensing-based NDVI and NDRE correlate positively with petiole nitrogen content, leaf area, and yield, and indicates that these parameters could predict variation in grape volatile terpenoids within vineyards. Our results also suggest that, in the Okanagan Valley, promoting vine vigor can improve grape aroma, and remote sensing-based vegetative indices could serve as a cost-efficient and time-saving approach to estimate vine vigor within a vineyard.

Funding Support: MITACS/ Investment Agriculture Foundation

1:30 pm – 1:50 pm	Accurate and Rapid Monitoring of Grape Ripening in the Field Through On-the-Go NIR/SWIR Hyperspectral Mapping Luca Brillante, California State University, Fresno
1:50 pm – 2:10 pm	Accounting for Spatial Variability to Efficiently Monitor Grape Composition in California Vineyards Brent Sams, E. & J. Gallo Winery, California
2:10 pm – 2:30 pm	Relationships among Vine Nutrient Status, Canopy Size, Vine Physiology, Yield, and Grape Aroma within Vineyards Pin-Jui Chen, University of British Columbia, Canada

Viticulture – Precision Viticulture Session

Research Reports

Moderator:

Share This Page

Speakers

Luca Brillante

Brent Sams

Pin-Jui Chen

Moderator

Yun Zhang