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

A Review of Pollen Counting Networks: From the Nineteenth Century into the Twenty-first Century

PURPOSE OF REVIEW

Pollen is enormously important to the human experience. As pollen became germane to human health in the late nineteenth century, methods for pollen collection and measurement were developed. Techniques were standardized and pollen counting networks were established in many parts of the world during the middle to late part of the twentieth century. With some notable exceptions, the technology of the 1950s and 1960s is presently employed to create the current pollen counting networks. Pollen counting networks in the past faced substantial challenges. Pollen counting networks using the same technology as the past face the same challenges.

RECENT FINDINGS

As we move into the twenty-first century, automated pollen counting technology enables pollen counting networks to be robust, available, scalable, self-perpetuating, and able to meet modern demands. Automated pollen measurement networks present a promising path towards a more informed, data-driven, and effective approach to managing allergens, improving crop yields, and minimizing human suffering caused by pollen. By empowering individuals with comprehensive pollen data, a feat not possible with manual counting, we can help people make informed decisions and take proactive measures to minimize exposure to allergens and improve their well-being.

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

Pollen and tracheophyte spores are ubiquitous environmental indicators at local and global scales. Palynology is typically performed manually by microscopic analysis; a specialised and time-consuming task limited in taxonomical precision and sampling frequency, therefore restricting data quality used to inform climate change and pollen forecasting models. We build on the growing work using AI (artificial intelligence) for automated pollen classification to design a flexible network that can deal with the uncertainty of broad-scale environmental applications. We combined imaging flow cytometry with Guided Deep Learning to identify and accurately categorise pollen in environmental samples; here, pollen grains captured within c. 5500 Cal yr BP old lake sediments. Our network discriminates not only pollen included in training libraries to the species level but, depending on the sample, can classify previously unseen pollen to the likely phylogenetic order, family and even genus. Our approach offers valuable insights into the development of a widely transferable, rapid and accurate exploratory tool for pollen classification in 'real-world' environmental samples with improved accuracy over pure deep learning techniques. This work has the potential to revolutionise many aspects of palynology, allowing a more detailed spatial and temporal understanding of pollen in the environment with improved taxonomical resolution.