terclim by ICS banner
IVES 9 IVES Conference Series 9 GiESCO 9 GiESCO 2023 9 Toward an automatic way to identify red blotch infected vines from hyperspectral images acquired in the field

Toward an automatic way to identify red blotch infected vines from hyperspectral images acquired in the field


Context and purpose of the study – Vineyards are affected by different virus diseases, which can lower yield and affect the quality of grapes. Grapevine red blotch disease is one of them, and no curative solution exists. Once infected, a vine must be removed and replaced with a virus-free vine (aka roguing). Screening vineyards to look for symptoms can be time-consuming and needs well-trained experts. To improve this process, we conducted an experiment identifying infected vines using a hyperspectral camera in the field.

Material and methods – We monitored one vineyard in Rutherford, California, at the symptomatic stage in September and October 2020 and in August (pre-symptomatic stage), September and October 2021. More than 700 vines were sampled and analyzed through Polymerase Chain Reaction (PCR). We imaged the same vine canopies using a Senop HSC hyperspectral camera mounted on a tripod and captured 230 bands from the visible (510 nm) to the near-infrared (900 nm). We segmented leaves from the background through a U-Net neural network model and extracted the canopy signal. We tested different machine learning algorithms, Random Forest (RF), Partial Least Square (PLS), Support Vector Machine (SVM), and their multiple-model ensembles, to predict the PCR results (Infected vs. Non-infected). We evaluated and interpreted each model using mean accuracies, confusion matrices, and feature importance computation. We also computed a spectral binning and used recursive feature elimination (RFE) selection. 

Results The stacking ensemble of PLS and SVM models had the highest overall (cross-validated) accuracy of 69.5% for the entire dataset, 61% for the pre-symptomatic, and 74.5% for the symptomatic dataset. In this dataset, the model correctly classified non-infected vines with 83% accuracy and infected vines with 65% accuracy. Absolute values of PLS coefficients were the most important for reflectance at wavelengths between 550-600 nm and 750-800 nm. Concerning the permutation importance of the SVM model, the greatest values were obtained for reflectance around 600 nm, 710 nm, and 830 nm. These wavelengths are related to pigments known to be affected by red blotch. Using the RFE on the binning dataset, the overall accuracy reached 73.3% using 23 bands for the entire dataset and 76% using 30 bands for the symptomatic dataset. This study proves that hyperspectral imaging can help reduce the spread of red blotch by identifying vines that may be infected and could be rogued or molecularly analyzed if higher certainty is desired.


Publication date: June 22, 2023

Issue: GiESCO 2023

Type: Article


Eve LAROCHE-PINEL1,2, Benjamin CORALES1,2, Erica SAWYER1,2,3, Khushwinder SINGH1,2, Kaylah VASQUEZ1,2, Monica COOPER 4, Marc FUCHS 5, Luca BRILLANTE1,2*

 1Department of Viticulture & Enology, California State University Fresno, Fresno, CA, USA
2Viticulture and Enology Research Center, California State University Fresno, Fresno, CA, USA
3Department of Mathematics, California State University Fresno, Fresno, CA, USA
4University of California, Agriculture & Natural Resources, Napa, CA, USA 
5Plant Pathology and Plant-Microbe Biology, Cornell University, Geneva, NY, USA 

Contact the author*


disease detection, Grapevine Red Blotch virus, hyperspectral imaging, machine learning, imaging spectroscopy


GiESCO | GIESCO 2023 | IVES Conference Series


Related articles…

An excessive leaf-fruit ratio reduces the yeast assimilable nitrogen in the must

Yeast assimilable nitrogen (YAN) in the grape must is a key variable for wine quality as a source of aroma precursors. In a situation of YAN deficiency, a foliar urea application upon the vine at veraison enhances YAN concentration and facilitates must fermentation. In 2013, Agroscope investigated the impact of leaf-fruit ratio on the nitrogen (N) assimilation and partitioning in grapevine Vitis vinifera cv. Chasselas following foliar-urea application with the aim of improving its efficiency on the YAN concentration.

Extraction of polyphenols from grape marc by supercritical fluid extraction (SFE) and evaluation of their ‘bioavailability’ as dietary supplements

In the winemaking process, several compounds that remain in the grape skins and seeds after the fermentation stage are bioactive-compounds (substances with potential beneficial effects on health) that can be extracted in order to recovery valuable substances with a high commercial value for the cosmetic, food (nutraceuticals) and pharmaceutical industries. The skins contain significant amounts of bioactive substances such as tannins (16-27%) and other polyphenolic compounds (2-6.5%) in particular, catechins, anthocyanins, proanthocyanins, quercetin , ellagic acid and resveratrol.

The impacts of frozen material-other-than-grapes (MOG) on aroma compounds of red wine varieties

An undesirable note called “floral taint” has been observed in red wines by winemakers in the Niagara region caused by large volumes of frozen leaves and petioles [materials-other-than-grapes (MOG)] introduced during mechanical harvest and subsequent winemaking late in the season. The volatiles, which we hypothesized are responsible, are primarily terpenes, norisoprenoids, and specific esters in frozen leaves and petioles. The purpose of this study was to investigate the volatile compounds which may cause the floral taint problem and explore how much of them (thresholds) may lead to the problem. Also, the glycosidic precursors of some of these compounds were analyzed to see the changes happening during frost events.

Aromatic profile of six different clones of Chardonnay grape berries in Minas Gerais (Brazil)

Aromas are one of the key points in food analysis since they are related to character, quality and consequently consumer acceptance. It is not different in the winery industry, where the aromatic profile is a combination of viticultural and oenological practices. Based on the development of more aromatic clones and on the potential to produce sparkling wines at Caldas, in the southern region of Minas Gerais (Brazil) (21°55´S and 46°23´W, altitude 1,100m), the aim of this work was the determination of volatile compounds in six different clones of Chardonnay grape berries to better understand which compounds add bouquet to the wine, and additionally comprehend the impacts of the edaphoclimatic and annual conditions on the improvement of grape-growing and winemaking practices.

Improving stilbenes in vitis Labrusca L. Grapes through methyl jasmonate applications

Grapes (Vitis sp.) are considered a major source of phenolic compounds such as flavonols, anthocyanins and stilbenes. Studies related to the beneficial effects of these compounds on health have encouraged research aimed at increasing their concentration in fruits. On this behalf, several plant growth regulators such as jasmonic acid and its volatile ester, methyl-jasmonate (MeJa), have demonstrated promising results in many fruits. However, Brazilian subtropical climate might interfere on treatment response. The present study aims to evaluate the application of MeJa in the pre-harvest period in Concord and Isabel Precoce grapes (Vitis labrusca L.).