Automatic real-time monitoring of fungal spores: the case of Alternaria spp.

Erb, Sophie; Berne, Alexis; Burgdorfer, Nina; Clot, Bernard; Graber, Marie-José; Lieberherr, Gian-Duri; Sallin, Christine; Tummon, Fiona; Crouzy, Benoît

doi:10.1007/s10453-023-09780-z

Cited by 9 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first model investigated uses a convolutional neural network (CNN) that employs only the two holographic images as input ("Holo.-Only"). This model differs from models used in previous studies of bioaerosol identification (Sauvageat et al, 2020;Erb et al, 2023a) The model training resulted in an overall accuracy of 90% on the test dataset. Particle types that share size and shape characteristics perform worse than those with defining features, such as pollen.…”

Section: Particle Classification Using Machine Learningmentioning

confidence: 74%

“…Digital holography can provide improved information about aerosol particle size and shape beyond other light scattering methods (Berg et al, 2017) and has been demonstrated for various coarse-mode particles, including bioaerosol (Sauvageat et al, 2020;Erb et al, 2023a), ice crystals (Touloupas et al, 2020), and more (Berg et al, 2017). The SwisensPoleno is a powerful instrument to capture a diverse range of single-particle morphology in near real-time.…”

Section: Discussionmentioning

confidence: 99%

“…The SwisensPoleno resolves two digital holograms of the same single particle in the sample stream using digital inline holography (Berg, 2022;Berg and Videen, 2011), with imaging sensors placed perpendicular to each other and the imaging plane perpendicular to the sample flow. Using only holographic imaging and image analysis, the SwisensPoleno has been used to detect and classify pollen particles from several different plant species in the size range between 10 -200 μm with high accuracy (Sauvageat et al, 2020), later adapted to identify fungal spores during ambient monitoring in Switzerland (Erb et al, 2023a), and recently shown to be successful when combining holography and fluorescence information for pollen classification (Erb et al, 2023b). After hologram reconstruction and processing, each particle image is 200x200 pixels, with a resolution of 0.595 µm per pixel.…”

Section: Swisenspolenomentioning

confidence: 99%

“…No study has used the intrinsic fluorescence of polymers for airborne particle identification and characterization in situ. However, the recent introduction of the SwisensPoleno air-flow cytometer (Swisens AG; Emmen, Switzerland), which was shown to classify biological aerosol particles with high accuracy (Sauvageat et al, 2020;Erb et al, 2023a, b), provides an opportunity to explore the identification and characterization of other airborne particles, such as MPs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Merging holography, fluorescence, and machine learning for in situ, continuous characterization and classification of airborne microplastics

Beres,

Burkart,

Graf

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. The continued increase in global plastic production and poor waste management ensures that plastic pollution is a serious environmental concern for years to come. Because of their size, shape, and relatively low density, plastic particles between 1–1000 μm in size (known as microplastics, or MPs) emitted directly into the environment (“primary”) or created due to degradation (“secondary”) may be transported through the atmosphere, similar to other coarse-mode particles, such as mineral dust. MPs can thus be advected over great distances, reaching even the most pristine and remote areas of the Earth, and may have significant negative consequences for humans and the environment. The detection and analysis of MPs once airborne, however, remains a challenge because most observational methods are offline and resource-intensive, and, therefore, are not capable of providing continuous quantitative information. In this study, we present results using an online, in situ airflow cytometer (SwisensPoleno Jupiter; Swisens AG; Emmen, Switzerland) – coupled with machine learning – to detect, analyze, and classify airborne, single-particle MPs in near real time. The performance of the instrument to differentiate single-particle MPs of five common polymer types (including polypropylene, polyethylene, polyamide, poly(methyl methacrylate), and polyethylene terephthalate) was investigated under laboratory conditions using combined information about their size and shape (determined using holographic imaging) and fluorescence measured using three excitation wavelengths and five emission detection windows. The classification capability using these methods was determined alongside other coarse-mode aerosol particles with similar morphology or fluorescence characteristics, such as a mineral dust and several pollen taxa. The tested MPs exhibit a measurable fluorescence signal that not only allows them to be distinguished from the other fluorescent particles, such as pollen, but can also be differentiated from each other, with high (> 90 %) classification accuracy based on their multispectral fluorescence signatures. The classification accuracies of machine learning models using only holographic images of particles, only the fluorescence response, and combined information from holography and fluorescence to predict particle type are presented and compared. The results provide a foundation towards significantly improving the understanding of the properties and types of MPs present in the atmosphere.

show abstract

Section: Particle Classification Using Machine Learningmentioning

confidence: 74%

Section: Discussionmentioning

confidence: 99%

Section: Swisenspolenomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Merging holography, fluorescence, and machine learning for in situ, continuous characterization and classification of airborne microplastics

Beres,

Burkart,

Graf

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“… 51 , 52 Most systems have, to date, focused on the main pollen types present in Central Europe. However, many research groups are actively working to extend the current capabilities to fungal pathogens 53 , 54 and other types of particles (e.g., Šikoparija et al. 55 ), in convergence with aerosol and air quality observations.…”

Section: Automated Monitoringmentioning

confidence: 99%