Abstract
Monitoring of airborne pollen concentrations provides an important source of information for the globally increasing number of hay fever patients. Airborne pollen is traditionally counted under the microscope, but with the latest developments in image recognition methods, automating this process has become feasible. A challenge that persists, however, is that many pollen grains cannot be distinguished beyond the genus or family level using a microscope. Here, we assess the use of Convolutional Neural Networks (CNNs) to increase taxonomic accuracy for airborne pollen. As a case study we use the nettle family (Urticaceae), which contains two main genera (Urtica and Parietaria) common in European landscapes which pollen cannot be separated by trained specialists. While pollen from Urtica species has very low allergenic relevance, pollen from several species of Parietaria is severely allergenic. We collect pollen from both fresh as well as from herbarium specimens and use these without the often used acetolysis step to train the CNN model. The models show that unacetolyzed Urticaceae pollen grains can be distinguished with > 98% accuracy. We then apply our model on before unseen Urticaceae pollen collected from aerobiological samples and show that the genera can be confidently distinguished, despite the more challenging input images that are often overlain by debris. Our method can also be applied to other pollen families in the future and will thus help to make allergenic pollen monitoring more specific.
Highlights
As a result of anthropogenic distribution and climate c hange[14,15]
The only species of Urticaceae that can be distinguished in aerobiological samples is Urtica membranacea due to its small size (~ 10–12 μm) and a high number of pores
Recent advances have been made in the field of aerobiological samples with for example the distinction of anomalous from normal pollen grains of common hazel (Corylus avellana L.) 32
Summary
As a result of anthropogenic distribution and climate c hange[14,15]. Parietaria sensitization is highly different per geographic area, but has been reported to reach 80% in southern Italy while a value of 13% was found in the United Kingdom[16]. Subtle variations in morphology that are not readily apparent through microscopic investigation may be consistently detected by neural networks This has for example been shown for the highly similar pollen of black spruce (Picea mariana (Mill.) Britton, Sterns & Poggenb.) and white spruce (Picea glauca (Moench) Voss) using machine learning 30 and for pollen of ten species of the thistle genus Onopordum L. using an artificial neural network[31]. Because of the limited size of the pollen image dataset, pre-training the CNN on a publicly available image database can help to recognize the distinguishing features of pollen grains such as pores, texture and shape. We test both the deep CNN VGG16 and the faster CNNs MobileNetV1 and V2, and optimize the performance using data augmentation. Urtica is expected to be dominant in Vielha, while in the direct surroundings of Lleida, Parietaria is very abundant
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
