Faster detection of pollen and fungal spores may help citizens breathe easier

New tech could make life easier and safer for people with respiratory illnesses, as AI classifies pollen and fungal spore species quickly and inexpensively.

Man sneezing

Faster detection of pollen and fungal spores may help citizens breathe easier

University of Birmingham experts aim to improve how pollen and fungal spores are detected – developing new technology that could make life easier and safer for people with respiratory illnesses.

Supported by UKRI AI for Health funding, environmental scientists will bring together internet-of-things (IoT) sensor arrays and artificial intelligence (AI) techniques to measure the pollen and spores within the air we breathe.

Machine learning algorithms will classify the pollen and fungal spore species of interest and generate approaches to detect them in real time – improving current detection techniques which can be slow and expensive.

Current means of detecting the spores can be expensive and time consuming - hugely limiting their use. Better detection and forecasting of pollen and fungal spores would allow for interventions to be developed that would reduce their risk to human health.

Professor Francis Pope - University of Birmingham

Working with counterparts at the University of Manchester and UK Health Security Agency (UKHSA), the Birmingham researchers will assess how efficient the new AI and IoT tools are in meeting the bioaerosol detection and forecasting needs of project partners such as the Met Office and Environment Agency.

Project lead Professor Francis Pope, from the University of Birmingham, commented: “Pollen and fungal spores are linked to respiratory illnesses which range in severity from minor to deadly and, for some people, the symptoms are serious - leading to reductions in work productivity, learning outcomes and even death.

“Current means of detecting the spores can be expensive and time consuming - hugely limiting their use. Better detection and forecasting of pollen and fungal spores would allow for interventions to be developed that would reduce their risk to human health.”

The project will see IoT sensors measuring the size distribution of small atmospheric particles present within the air, the sources and composition of which are many and varied.

These particles include bioaerosols composed of fragments from the biosphere, including pollen and fungal spores. Proof of principal work for the proposal was carried out by University of Birmingham PhD student Sophie Mills who will work on the project post PhD as a researcher.[1]

Finding these bioaerosols within much larger populations of other atmospheric aerosols is difficult, but pollen and fungal spores have well defined sizes meaning that AI approaches can classify species of interest and generate approaches to detect them in real time. This will allow for real-time forecasts of pollen and spore species of interest.

Dr Emma Marczylo, Principal Toxicologist at UK Health Security Agency, commented: “We need to embrace and assess new technologies to advance our characterisation and understanding of bioaerosol exposure and associated health impacts. This funding will enable us to develop and test the combination of machine learning with low-cost sensors to monitor pollen and fungal spores at much greater resolution, which could prove to be a real game changer for researchers, regulators, industry and public health professionals.”

Currently the regulatory detection of pollen and fungal spores is limited because of the high associated costs. For example, the UK Met Office currently only has available 11 regulatory grade sites for pollen monitoring from which their pollen forecast is based upon. Similarly, UK agencies lack cheap methodologies to detect fungal spores in both outdoor and indoor locations.

Professor David Topping, from the University of Manchester, commented: “This project provides us with the opportunity to improve near-to-realtime forecasting of bioaerosols which would have a number of benefits. As we move towards a data-driven society, by validating several emerging machine learning approaches, we can co-design methods that could be of use to a number of stakeholders in the public sector at the environment-health interface.”

A high percentage of the UK population has hay fever (allergic rhinitis) due to tree and grass pollen. Indoors, fungal spores are often found in damp and cold environments. These spores can also have significant health outcomes. The cost-of-living crisis has led to an increase in damp and mould problems within UK homes.

[1] Mills, S.A., Bousiotis, D., Maya-Manzano, J.M., Tummon, F., MacKenzie, A.R. and Pope, F.D., 2023. Constructing a pollen proxy from low-cost Optical Particle Counter (OPC) data processed with Neural Networks and Random Forests. Science of The Total Environment, 871, p.161969. https://doi.org/10.1016/j.scitotenv.2023.161969

Notes for editors

For more information, please contact Tony Moran, International Communications Manager, University of Birmingham on +44 (0)782 783 2312. For out-of-hours enquiries, please call +44 (0) 7789 921 165.

The University of Birmingham is ranked amongst the world’s top 100 institutions, its work brings people from across the world to Birmingham, including researchers and teachers and more than 8,000 international students from over 150 countries.