Detection of apple proliferation disease in Malus × domestica by near infrared reflectance analysis of leaves

Barthel, Dana; Ðorđević, N.; Fischnaller, Stefanie; Kerschbamer, Christine; Messner, Manuel; Eisenstecken, Daniela; Robatscher, Peter; Janik, Katrin

doi:10.1016/j.saa.2021.120178

Cited by 8 publications

(13 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…P. mali' infection of the tree. This result is in line with recent data of near-infrared reflectance analyses of AP-infected leaves [8]. Due to the non-systemic colonization of the tree, this could also explain the failure of molecular phytoplasma detection in some cases.…”

Section: Discussionsupporting

confidence: 90%

“…However, the simultaneous occurrence of two or more of these symptoms is considered a reliable indicator of AP infection [5,7]. A definitive diagnosis of an infection can only be achieved by molecular means [8]. Various PCR detection protocols of the causal pathogen 'Ca.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, two different approaches to the use of spectral analyses for the diagnosis of AP have been reported. Near-infrared (NIR) spectroscopy has been successfully applied to distinguish AP-infected and healthy apple leaves [8]. However, this is a destructive approach as it uses dried and ground leaves.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Phytoplasma-Induced Leaf Reddening as a Monitoring Symptom of Apple Proliferation Disease with Regard to the Development of Remote Sensing Strategies

Jarausch,

Runne,

Schwind

et al. 2024

Agronomy

View full text Add to dashboard Cite

Apple proliferation (AP) is an economically important disease in many apple-growing regions caused by ‘Candidatus Phytoplasma mali’ which is spread by migrating psyllid vectors on a regional scale. As infected trees in orchards are the only inoculum source, the early eradication of those trees is one of the most efficient strategies to prevent further spread of AP. Remote sensing is a promising rapid and cost-effective tool to identify infected trees on a regional scale. AP-induced premature leaf reddening was evaluated as a reliable symptom for remote sensing by monitoring more than 20,000 trees in 68 different orchards with 20 representative cultivars from 2019 to 2022 in a highly AP-affected region in Southwest Germany. Specific AP symptoms were almost 100% correlated with molecular detection of ‘Ca. P. mali’ and these specific symptoms were almost 100% correlated with leaf reddening. ‘Ca. P. mali’ was detected in 71–97% of trees which showed partial or entire reddening without any other AP symptom. Experimental and field data showed that reddening was induced by cold night and warm day temperatures (about 5 °C vs. 20 °C) in September. Quantification of the phytoplasma by real-time PCR showed no correlation with the intensity of reddening in the leaf. PCR-RFLP subtyping revealed no influence of different ‘Ca. P. mali’ strains on the symptom expression. In conclusion, leaf reddening in late September/early October was a reliable symptom useful for remote sensing of AP.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Phytoplasma-Induced Leaf Reddening as a Monitoring Symptom of Apple Proliferation Disease with Regard to the Development of Remote Sensing Strategies

Jarausch,

Runne,

Schwind

et al. 2024

Agronomy

View full text Add to dashboard Cite

show abstract

“…With the full dataset, the Partial Least Squares (PLS, 1) and Support Vector Machine (SVM, 1) models performed best, for both the specific and the general models. Both of these methods are particularly well suited to high dimensional data and have been used frequently in the past for the analysis of spectroscopic data on plant material 25 , 37 – 42 . This is because the internal regularization of SVMs and the reduction of the full data set into fewer variables done by PLS makes these models resilient to overfitting, as is demonstrated here by their high performance on the full data set 43 , 44 .…”

Section: Discussionmentioning

confidence: 99%

“…Subsequently, the relationship between leaf biochemistry, physiology and cellular structure and leaf optical properties, especially those related to full range VIS -NIR hyperspectral information, were investigated and modelled 20 , 21 . This had promising implications for the use of the technology for the detection of stress in plants and indeed, spectral sensing has since been applied over the last decades to detect a wide range of different biotic plant stresses: viruses 22 , bacteria 23 , phytoplasma 24 , 25 , fungal and bacterial diseases 26 , 27 and insect pests 28 .…”

Section: Introductionmentioning

confidence: 99%

In vivo spectroscopy and machine learning for the early detection and classification of different stresses in apple trees

Prechsl,

Mejia-Aguilar,

Cullinan

2023

Sci Rep

View full text Add to dashboard Cite

The use of in vivo spectroscopy to detect plant stress in its early stages has the potential to enhance food safety and reduce the need for plant protection products. However, differentiating between various stress types before symptoms appear remains poorly studied. In this study, we investigated the potential of Vis–NIR spectroscopy to differentiate between stress types in apple trees (Malus x domestica Borkh.) exposed to apple scab, waterlogging, and herbicides in a greenhouse. Using a spectroradiometer, we collected spectral signatures of leaves still attached to the tree and utilized machine learning techniques to develop predictive models for detecting stress presence and classifying stress type as early as 1–5 days after exposure. Our findings suggest that changes in spectral reflectance at multiple regions accurately differentiate various types of plant stress on apple trees. Our models were highly accurate (accuracies between 0.94 and 1) when detecting the general presence of stress at an early stage. The wavelengths important for classification relate to photosynthesis via pigment functioning (684 nm) and leaf water (~ 1800–1900 nm), which may be associated with altered gas exchange as a short-term stress response. Overall, our study demonstrates the potential of spectral technology and machine learning for early diagnosis of plant stress, which could lead to reduced environmental burden through optimizing resource utilization in agriculture.

show abstract

Hyperspectral imaging coupled with Dual-channel convolutional neural network for early detection of apple valsa canker

Cui

Wang

et al. 2022

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Detection of apple proliferation disease in Malus × domestica by near infrared reflectance analysis of leaves

Cited by 8 publications

References 71 publications

Phytoplasma-Induced Leaf Reddening as a Monitoring Symptom of Apple Proliferation Disease with Regard to the Development of Remote Sensing Strategies

Phytoplasma-Induced Leaf Reddening as a Monitoring Symptom of Apple Proliferation Disease with Regard to the Development of Remote Sensing Strategies

In vivo spectroscopy and machine learning for the early detection and classification of different stresses in apple trees

Hyperspectral imaging coupled with Dual-channel convolutional neural network for early detection of apple valsa canker

Contact Info

Product

Resources

About