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

Abstract

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.

DOI:

Publication date: June 22, 2023

Issue: GiESCO 2023

Type: Article

Authors

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*

Keywords

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

Tags

GiESCO | GIESCO 2023 | IVES Conference Series

Citation

Related articles…

Effect of foliar application of Ca, Si and their combination on grape volatile composition

Calcium (Ca) is an important nutrient for plants which plays key signaling and structural roles. It has been observed that exogenous Ca application favors the pectin accumulation and inhibition of polygalacturonase enzymes, minimizing fruit spoilage. Silicon (Si) is a non-essential element which has been found to be beneficial for improving crop yield and quality, as well as plant tolerance to diverse abiotic and biotic stress factors. The effect of Si supply to grapevine has been assessed in few investigations, which reported positive changes in grape quality and must composition.

Late winter pruning induces a maturity delay under temperature-increased conditions in cv. Merlot from Chile

Chile is considered vulnerable to climate change; and these phenomena affect several mechanisms in the grape physiology and quality. The global temperature increase affects sugar contents, organic acids, and phenolic compounds in grapes, producing an imbalance maturity. In this sense, an alternative to reduce the impact is to perform pruning after vine budburst, known as “Late Pruning” (LP).

Effect of two water deficit regimes on the agronomic response of 12 grapevine varieties cultivated in a semi-arid climate

The Mediterranean basin is one of the most vulnerable regions to Climate Change effects. According to unanimous forecasts, the vineyards of Castilla-La Mancha will be among the most adversely affected by rising temperatures and water scarcity during the vine’s vegetative period. One potential strategy to mitigate the negative impacts of these changes involves the identification of grapevine varieties with superior water use efficiency, while ensuring satisfactory yields and grape quality.

Influence of irrigation frequency on berry phenolic composition of red grape varieties cultivated in four spanish wine-growing regions

The global warming phenomenon involves the frequency of extreme meteorological events accompanied by a change in rainfall distribution. Irrigation frequency (IF) affects the spatial and temporal soil water distribution but its effects on the phenolic composition of the grape have been scarcely studied. The aim of this work was to evaluate the effects of four deficit irrigation frequencies of 30 % ETo: one irrigation per day (T01), two irrigations per week (T03), one irrigation per week (T07) and one irrigation every two weeks (T15) on berry phenolic composition at harvest.

Response of red grape varieties irrigated during the summer to water availability at the end of winter in four Spanish wine-growing regions: berry phenolic composition

Water availability is the most limiting factor for vineyard productivity under Mediterranean conditions. Due to the effects caused by the current climate change, wine-growing regions may face serious soil moisture conservation problems, due to the lower water retention capacity of the soil and higher soil irradiation. The aim of this work was to evaluate the effects of soil recharge irrigation in pre-sprouting and summer irrigation every week (30 % ETo) from the pea size state until the end of ripening (RP) compared to exclusively summer irrigation every week (R) in the same way that RP, on berry phenolic composition at harvest.