Advanced search
1 file | 4.21 MB Add to list

X-ray microtomography and linear discriminant analysis enable detection of embolism-related acoustic emissions

Niels De Baerdemaeker (UGent) , Michiel Stock (UGent) , Jan Van den Bulcke (UGent) , Bernard De Baets (UGent) , Luc Van Hoorebeke (UGent) and Kathy Steppe (UGent)
(2019) PLANT METHODS. 15(1).
Author
Organization
Abstract
Background: Acoustic emission (AE) sensing is in use since the late 1960s in drought-induced embolism research as a non-invasive and continuous method. It is very well suited to assess a plant's vulnerability to dehydration. Over the last couple of years, AE sensing has further improved due to progress in AE sensors, data acquisition methods and analysis systems. Despite these recent advances, it is still challenging to detect drought-induced embolism events in the AE sources registered by the sensors during dehydration, which sometimes questions the quantitative potential of AE sensing. Results: In quest of a method to separate embolism-related AE signals from other dehydration-related signals, a 2-year-old potted Fraxinus excelsior L. tree was subjected to a drought experiment. Embolism formation was acoustically measured with two broadband point-contact AE sensors while simultaneously being visualized by X-ray computed microtomography (mu CT). A machine learning method was used to link visually detected embolism formation by mu CT with corresponding AE signals. Specifically, applying linear discriminant analysis (LDA) on the six AE waveform parameters amplitude, counts, duration, signal strength, absolute energy and partial power in the range 100-200 kHz resulted in an embolism-related acoustic vulnerability curve (VCAE-E) better resembling the standard mu CTVC(VCCT), both in time and in absolute number of embolized vessels. Interestingly, the unfiltered acoustic vulnerability curve (VCAE) also closely resembled VCCT, indicating that VCs constructed from all registered AE signals did not compromise the quantitative interpretation of the species' vulnerability to drought-induced embolism formation. Conclusion: Although machine learning could detect similar numbers of embolism-related AE as mu CT, there still is insufficient model-based evidence to conclusively attribute these signals to embolism events. Future research should therefore focus on similar experiments with more in-depth analysis of acoustic waveforms, as well as explore the possibility of Fast Fourier transformation (FFT) to remove non-embolism-related AE signals.
Keywords
Biotechnology, Plant Science, Genetics, Drought-induced embolism formation, Acoustic emissions, Machine learning, Linear discriminant analysis, X-ray computed microtomography, Fraxinus excelsior L, XYLEM CAVITATION RESISTANCE, DROUGHT-INDUCED EMBOLISM, HYDRAULIC VULNERABILITY, MICRO-CT, DYNAMICS, TREES, QUANTIFICATION, IDENTIFICATION, SIGNALS, SAPWOOD

Downloads

  • KERMIT-A1-547.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 4.21 MB

Citation

Please use this url to cite or link to this publication:

MLA
De Baerdemaeker, Niels, et al. “X-Ray Microtomography and Linear Discriminant Analysis Enable Detection of Embolism-Related Acoustic Emissions.” PLANT METHODS, vol. 15, no. 1, 2019.
APA
De Baerdemaeker, N., Stock, M., Van den Bulcke, J., De Baets, B., Van Hoorebeke, L., & Steppe, K. (2019). X-ray microtomography and linear discriminant analysis enable detection of embolism-related acoustic emissions. PLANT METHODS, 15(1).
Chicago author-date
De Baerdemaeker, Niels, Michiel Stock, Jan Van den Bulcke, Bernard De Baets, Luc Van Hoorebeke, and Kathy Steppe. 2019. “X-Ray Microtomography and Linear Discriminant Analysis Enable Detection of Embolism-Related Acoustic Emissions.” PLANT METHODS 15 (1).
Chicago author-date (all authors)
De Baerdemaeker, Niels, Michiel Stock, Jan Van den Bulcke, Bernard De Baets, Luc Van Hoorebeke, and Kathy Steppe. 2019. “X-Ray Microtomography and Linear Discriminant Analysis Enable Detection of Embolism-Related Acoustic Emissions.” PLANT METHODS 15 (1).
Vancouver
1.
De Baerdemaeker N, Stock M, Van den Bulcke J, De Baets B, Van Hoorebeke L, Steppe K. X-ray microtomography and linear discriminant analysis enable detection of embolism-related acoustic emissions. PLANT METHODS. 2019;15(1).
IEEE
[1]
N. De Baerdemaeker, M. Stock, J. Van den Bulcke, B. De Baets, L. Van Hoorebeke, and K. Steppe, “X-ray microtomography and linear discriminant analysis enable detection of embolism-related acoustic emissions,” PLANT METHODS, vol. 15, no. 1, 2019.
@article{8639643,
  abstract     = {Background: Acoustic emission (AE) sensing is in use since the late 1960s in drought-induced embolism research as a non-invasive and continuous method. It is very well suited to assess a plant's vulnerability to dehydration. Over the last couple of years, AE sensing has further improved due to progress in AE sensors, data acquisition methods and analysis systems. Despite these recent advances, it is still challenging to detect drought-induced embolism events in the AE sources registered by the sensors during dehydration, which sometimes questions the quantitative potential of AE sensing.

Results: In quest of a method to separate embolism-related AE signals from other dehydration-related signals, a 2-year-old potted Fraxinus excelsior L. tree was subjected to a drought experiment. Embolism formation was acoustically measured with two broadband point-contact AE sensors while simultaneously being visualized by X-ray computed microtomography (mu CT). A machine learning method was used to link visually detected embolism formation by mu CT with corresponding AE signals. Specifically, applying linear discriminant analysis (LDA) on the six AE waveform parameters amplitude, counts, duration, signal strength, absolute energy and partial power in the range 100-200 kHz resulted in an embolism-related acoustic vulnerability curve (VCAE-E) better resembling the standard mu CTVC(VCCT), both in time and in absolute number of embolized vessels. Interestingly, the unfiltered acoustic vulnerability curve (VCAE) also closely resembled VCCT, indicating that VCs constructed from all registered AE signals did not compromise the quantitative interpretation of the species' vulnerability to drought-induced embolism formation.

Conclusion: Although machine learning could detect similar numbers of embolism-related AE as mu CT, there still is insufficient model-based evidence to conclusively attribute these signals to embolism events. Future research should therefore focus on similar experiments with more in-depth analysis of acoustic waveforms, as well as explore the possibility of Fast Fourier transformation (FFT) to remove non-embolism-related AE signals.},
  articleno    = {153},
  author       = {De Baerdemaeker, Niels and Stock, Michiel and Van den Bulcke, Jan and De Baets, Bernard and Van Hoorebeke, Luc and Steppe, Kathy},
  issn         = {1746-4811},
  journal      = {PLANT METHODS},
  keywords     = {Biotechnology,Plant Science,Genetics,Drought-induced embolism formation,Acoustic emissions,Machine learning,Linear discriminant analysis,X-ray computed microtomography,Fraxinus excelsior L,XYLEM CAVITATION RESISTANCE,DROUGHT-INDUCED EMBOLISM,HYDRAULIC VULNERABILITY,MICRO-CT,DYNAMICS,TREES,QUANTIFICATION,IDENTIFICATION,SIGNALS,SAPWOOD},
  language     = {eng},
  number       = {1},
  pages        = {18},
  title        = {X-ray microtomography and linear discriminant analysis enable detection of embolism-related acoustic emissions},
  url          = {http://dx.doi.org/10.1186/s13007-019-0543-4},
  volume       = {15},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: