Development and application of a method to classify airborne pollen taxa concentration using light scattering data

Abstract

Although automated pollen monitoring networks using laser optics are well-established in Japan, it is thought that these methods cannot distinguish between pollen counts when evaluating various pollen taxa. However, a method for distinguishing the pollen counts of two pollen taxa was recently developed. In this study, we applied such a method to field evaluate the data of the two main allergens in Japan, Chamaecyparis obtusa and Cryptomeria japonica. We showed that the method can distinguish between the pollen counts of these two species even when they are simultaneously present in the atmosphere. This result indicates that a method for automated and simple two pollen taxa monitoring with high spatial density can be developed using the existing pollen network.

Deductive automated pollen classification in environmental samples via exploratory deep learning and imaging flow cytometry

“…Consisting of 595 647 brightfield, autofluorescence and side scatter images from 198 549 individual modern pollen grains, the library incorporated 53 pollen types from 26 families, spanning 18 orders (Table 1). The high‐throughput, rapid analysis of pollen performed by IFC is impossible to achieve via human analysts and is unparalleled by other techniques including light microscopy (Langford et al ., 1990; Khanzhin et al ., 2018), SEM (Mander et al ., 2013; Daood et al ., 2016) and classifynder (Holt et al ., 2011), and non‐image‐based techniques such as light scattering (Miki et al ., 2021) and traditional flow cytometry (Tennant et al ., 2013). The high volume of pollen grains analysed by IFC, addressed issues that complicate pollen classification, for example variations in the appearance of pollen grains due to rotation.…”

Comparison of computer vision models in application to pollen classification using light scattering

“…An earlier method of pollen tracking (Kawashima et al, 2007(Kawashima et al, , 2017 is based on laser optics, where light scattered by a pollen grain is measured at two angles. Despite its simplicity, that method proved to be capable of discriminating two key pollen types in Japan, which was enough to build a real-time monitoring network (Miki et al, 2021).…”