Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep-learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and require considerable effort to produce large amounts of annotated data, an effort that must be repeated for new particles, geographical regions, or measurement systems. In this work, we show that self-supervised learning and few-shot learning can be combined to classify holographic images of bioaerosol particles using a large collection of unlabelled data and only a few examples for each particle type. We first demonstrate that self-supervision on pictures of unidentified particles from ambient air measurements enhances identification even when labelled data is abundant. Most importantly, it greatly improves few-shot classification when only a handful of labelled images are available. Our findings suggest that real-time bioaerosol monitoring workflows can be substantially optimized, and the effort required to adapt models for different situations considerably reduced.

As seasonal allergy sufferers will attest, the concentration of allergens in the air varies every few paces. A nearby blossoming tree or sudden gust of pollen-tinged wind can easily set off sneezing and watery eyes. But concentrations of airborne allergens are reported city by city, at best. A network of deep learning-powered devices could change that, enabling scientists to track pollen density block by block. Researchers at the University of California, Los Angeles, have developed a portable AI device that identifies levels of five common allergens from pollen and mold spores with 94 percent accuracy, according to the team's recent paper.

When applied to previously-collected atmospheric samples and data, their findings support evidence that on average these bioaerosols globally make up less than 1 percent of the particles in the upper troposphere -- where they could influence cloud formation and by extension, the climate -- and not around 25 to 50 percent as some previous research suggests. While atmospheric and climate modeling suggests that bioaerosols, globally averaged, are not abundant and efficient enough at freezing to significantly influence cloud formation, research findings have varied significantly. The group leveraged the presence of phosphorus in the mass spectra to train the classification machine learning algorithm on known samples and then, primed, applied it to field data acquired from Desert Research Institute's Storm Peak Laboratory in Steamboat Springs, Colorado, and from the Carbonaceous Aerosol and Radiative Effects Study based in the town of Cool, California. Knowing that the principal atmospheric emissions of phosphorus are from mineral dust, combustion products, and biological particles, they exploited the presence of phosphate and organic nitrogen ions and their characteristic ratios in known samples to classify the particles.