Assessment of the optimal spectral bands for designing a sensor for vineyard disease detection: the case of ‘Flavescence dorée’

Al-Saddik, Hania; Simon, Jean‐Claude; Cointault, Frédéric

doi:10.1007/s11119-018-9594-1

Cited by 39 publications

(35 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this pilot study, Esca disease detection was only performed on one white grapevine cultivar and should therefore also be applied to others, since there is a large diversity of symptoms between red and white varieties [37]. This will be another challenging task in testing the transferability of disease detection models because spectral reflectance differs by cultivar as recently demonstrated by Al-Saddik et al [42] and Gutiérrez et al [43]. The pre-symptomatic detection approach showed very promising results, especially in 2018.…”

Section: Discussionmentioning

confidence: 99%

Evaluating the suitability of hyper- and multispectral imaging to detect foliar symptoms of the grapevine trunk disease Esca in vineyards

et al. 2020

View full text Add to dashboard Cite

Background Grapevine trunk diseases (GTDs) such as Esca are among the most devastating threats to viticulture. Due to the lack of efficient preventive and curative treatments, Esca causes severe economic losses worldwide. Since symptoms do not develop consecutively, the true incidence of the disease in a vineyard is difficult to assess. Therefore, an annual monitoring is required. In this context, automatic detection of symptoms could be a great relief for winegrowers. Spectral sensors have proven to be successful in disease detection, allowing a non-destructive, objective, and fast data acquisition. The aim of this study is to evaluate the feasibility of the in-field detection of foliar Esca symptoms over three consecutive years using ground-based hyperspectral and airborne multispectral imaging. Results Hyperspectral disease detection models have been successfully developed using either original field data or manually annotated data. In a next step, these models were applied on plant scale. While the model using annotated data performed better during development, the model using original data showed higher classification accuracies when applied in practical work. Moreover, the transferability of disease detection models to unknown data was tested. Although the visible and near-infrared (VNIR) range showed promising results, the transfer of such models is challenging. Initial results indicate that external symptoms could be detected pre-symptomatically, but this needs further evaluation. Furthermore, an application specific multispectral approach was simulated by identifying the most important wavelengths for the differentiation tasks, which was then compared to real multispectral data. Even though the ground-based multispectral disease detection was successful, airborne detection remains difficult. Conclusions In this study, ground-based hyperspectral and airborne multispectral approaches for the detection of foliar Esca symptoms are presented. Both sensor systems seem to be suitable for the in-field detection of the disease, even though airborne data acquisition has to be further optimized. Our disease detection approaches could facilitate monitoring plant phenotypes in a vineyard.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluating the suitability of hyper- and multispectral imaging to detect foliar symptoms of the grapevine trunk disease Esca in vineyards

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In this pilot study, Esca disease detection was only performed on one white grapevine cultivar and should therefore also be applied to others, since there is a large diversity of symptoms between red and white varieties [34]. This will be another challenging task in testing the transferability of disease detection models because spectral reflectance differs by cultivar as recently demonstrated by Al-Saddik et al [39] and Gutiérrez et al [40].…”

Section: Discussionmentioning

confidence: 99%

“…Based on these wavelengths an inexpensive multispectral sensor could be designed that would allow for faster data acquisition while being mounted on a tractor or UAV. Identification of optimal spectral bands is a common approach that has successfully been implemented for the detection of three sugar beet diseases [12], yellow rust on winter wheat [45], anthracnose on strawberries [46], or Flavescence dorée on grapevine [39]. Yeh et al [46] and Moshou et al [45] found that the number of selected wavelengths significantly influences CAs.…”

Section: Discussionmentioning

confidence: 99%

Evaluating the Suitability of Hyper- and Multispectral Imaging to Detect Foliar Symptoms of the Grapevine Trunk Disease Esca in Vineyards

Bendel

Kicherer

Backhaus

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Grapevine trunk diseases (GTDs) such as Esca are among the most devastating threats to viticulture. Due to the lack of efficient preventive and curative treatments, Esca causes severe economic losses worldwide. Since symptoms do not develop consecutively, the true incidence of the disease in a vineyard is difficult to assess. Therefore, an annual monitoring is required. In this context, automatic detection of symptoms could be a great relief for winegrowers. Spectral sensors have proven to be successful in disease detection, allowing a non-destructive, objective, and fast data acquisition. The aim of this study is to evaluate the feasibility of the in-field detection of foliar Esca symptoms over three consecutive years using ground-based hyperspectral and airborne multispectral imaging.Results: Hyperspectral disease detection models have been successfully developed using either original field data or manually annotated data. In a next step, these models were applied on plant scale. While the model using annotated data performed better during development, the model using original data showed higher classification accuracies when applied in practical work. Moreover, the transferability of disease detection models to unknown data was tested. Although the visible and near-infrared (VNIR) range showed promising results, the transfer of such models is challenging. Initial results indicate that external symptoms could be detected pre-symptomatically, but this needs further evaluation. Furthermore, an application specific multispectral approach was simulated by identifying the most important wavelengths for the differentiation tasks, which was then compared to real multispectral data. Even though the ground-based multispectral disease detection was successful, airborne detection remains difficult.Conclusions: In this study, different approaches for the detection of foliar Esca symptoms are presented. Both sensor systems seem to be suitable for the in-field detection of the disease, even though airborne data acquisition has to be further optimized. Our disease detection approaches could facilitate monitoring plant phenotypes in a vineyard.

show abstract

“…et al (2016) found that hyperspectral techniques can support water management strate-gies. Automatic detection of pests, for instance, of Flavescence dorée, proved to be successful (Al-Saddik, H. et al 2019). The application of the SPA Successive Projection algorithm ensures more than 96 per cent accuracy in pest detection.…”

Section: Introductionmentioning

confidence: 99%

Crop growth, carbon sequestration and soil erosion in an organic vineyard of the Villány Wine District, Southwest Hungary

et al. 2020

View full text Add to dashboard Cite

A more resilient adaptation to changing climate calls for crop diversification in vineyards, too. As a contribution to the H2020 collaborative project of the European Union, called Diverfarming, and part of the agroecological experiments during 2018 and 2019, grapevine biomass growth was monitored in connection with carbon storage types in soil and in the deposits removed by soil erosion. Phenometry was carried out interpreting segmented images to follow changes in biomass. It was found that crop growth could be best described by the Richards growth function. The distinction between grapevine and intercrop growth, however, requires further refinement in image analysis. In the laboratory TOC and Ntotal were measured for both the soil and the plant organs as well as for the eroded sediments. Greenhouse gas emissions and photosynthesis were monitored. Looking at the change of Leaf Area Index (LAI) over the growing period, image analysis pointed out the role of cut shoots from pruning in the C and N cycles. Maximum leaf area (at ripening) for guyot cultivation technique was extimated at 7,840 m2 ha-1. Soil loss by erosion was established by sediment traps at the end of vinestock rows. The grain size distribution analysis led to the remarkable result that as erosion proceeded, the ratio of the sand fraction increased but remained within the range for the textural class of loam. Organic matter contents grew to 38 g kg-1. The rate of soil erosion is higher in ploughed than in grassed interrows by orders of magnitude.

show abstract

Assessment of the optimal spectral bands for designing a sensor for vineyard disease detection: the case of ‘Flavescence dorée’

Cited by 39 publications

References 49 publications

Evaluating the suitability of hyper- and multispectral imaging to detect foliar symptoms of the grapevine trunk disease Esca in vineyards

Evaluating the suitability of hyper- and multispectral imaging to detect foliar symptoms of the grapevine trunk disease Esca in vineyards

Evaluating the Suitability of Hyper- and Multispectral Imaging to Detect Foliar Symptoms of the Grapevine Trunk Disease Esca in Vineyards

Crop growth, carbon sequestration and soil erosion in an organic vineyard of the Villány Wine District, Southwest Hungary

Contact Info

Product

Resources

About