Detecting Airborne Pollen Using an Automatic, Real-Time Monitoring System: Evidence from Two Sites

Local spatiotemporal dynamics of particulate matter and oak pollen measured by machine learning aided optical particle counters

Conventional techniques for monitoring pollen currently have significant limitations in terms of labour, cost and the spatiotemporal resolution that can be achieved. Pollen monitoring networks across the world are generally sparse and are not able to fully represent the detailed characteristics of airborne pollen. There are few studies that observe concentrations on a local scale, and even fewer that do so in ecologically rich rural areas and close to emitting sources. Better understanding of these would be relevant to occupational risk assessments for public health, as well as ecology, biodiversity, and climate. We present a study using low-cost optical particle counters (OPCs) and the application of machine learning models to monitor particulate matter and pollen within a mature oak forest in the UK. We characterise the observed oak pollen concentrations, first during an OPC colocation period (6 days) for calibration purposes, then for a period (36 days) when the OPCs were distributed on an observational tower at different heights through the canopy. We assess the efficacy and usefulness of this method and discuss directions for future development, including the requirements for training data. The results show promise, with the derived pollen concentrations following the expected diurnal trends and interactions with meteorological variables. Quercus pollen concentrations appeared greatest when measured at the canopy height of the forest (20-30 m). Quercus pollen concentrations were lowest at the greatest measurement height that is above the canopy (40 m), which is congruent with previous studies of background pollen in urban environments. The attenuation of pollen concentrations as sources are depleted is also observed across the season and at different heights, with some evidence that the pollen concentrations persist later at the lowest level beneath the canopy (10 m) where catkins mature latest in the season compared to higher catkins.

Isolating pollen signals from laser diode aerosol Optical Particle Counter (OPC) data through positive matrix factorization (PMF) and Unmix receptor models

Pollen, a significant natural bioaerosol and allergen for sensitized individuals, is expected to increase in prevalence due to climate change. Mitigating allergy symptoms involves avoiding pollen exposure and pre-medication, emphasizing the importance of real-time knowledge of localized ambient air pollen concentrations. Laser diode Optical Particle Counters (OPCs) are commonly used for monitoring particle number concentrations in ambient air. This study explores the hypothesis that OPCs can monitor pollen but may struggle to distinguish them from other particles. We aimed to isolate the pollen signal from collective particle number concentrations using source apportionment models, specifically Positive Matrix Factorization (PMF) and Unmix, applied to multiple bin OPC data. The pollen signals isolated using PMF show slightly better correlation values than those isolated using Unmix. PMF-derived pollen signals exhibit strong correlations with Holoptelea (r = 0.64) and total pollen (r = 0.54) concentrations, while a moderate correlation is observed with Poaceae (r = 0.47). Exclusion of low pollen events strengthens correlations for Holoptelea and Poaceae to very strong (r = 0.87) and strong (r = 0.67), respectively. Although both model types effectively isolate the pollen signal, metrics suggest that Unmix has the potential for more accurate predictions of both moderate and extreme pollen events simultaneously. The Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Relative Root Mean Square Error (RRMSE) metrics for Holoptelea are 46.2 grains m-3, 72.4 grains m-3, and 15.3; for Poaceae, 3.9 grains m-3, 4.9 grains m-3, and 13.0; and for total pollen, 43.5 grains m-3, 72.1 grains m-3, and 14.1. This study represents a significant development in the use of source apportionment models and ambient OPCs for real-time pollen monitoring, offering a cost-effective alternative to conventional automated pollen sensors. Despite challenges, the proposed methodology provides a practical and accessible solution for pollen monitoring, contributing to the advancement of bioaerosol monitoring technologies.

Constructing a pollen proxy from low-cost Optical Particle Counter (OPC) data processed with Neural Networks and Random Forests

Pollen allergies affect a significant proportion of the global population, and this is expected to worsen in years to come. There is demand for the development of automated pollen monitoring systems. Low-cost Optical Particle Counters (OPCs) measure particulate matter and have attractive advantages of real-time high time resolution data and affordable costs. This study asks whether low-cost OPC sensors can be used for meaningful monitoring of airborne pollen. We employ a variety of methods, including supervised machine learning techniques, to construct pollen proxies from hourly-average OPC data and evaluate their performance, holding out 40 % of observations to test the proxies. The most successful methods are supervised machine learning Neural Network (NN) and Random Forest (RF) methods, trained from pollen concentrations collected from a Hirst-type sampler. These perform significantly better than using a simple particle size-filtered proxy or a Positive Matrix Factorisation (PMF) source apportionment pollen proxy. Twelve NN and RF models were developed to construct a pollen proxy, each varying by model type, input features and target variable. The results show that such models can construct useful information on pollen from OPC data. The best metrics achieved (Spearman correlation coefficient = 0.85, coefficient of determination = 0.67) were for the NN model constructing a Poaceae (grass) pollen proxy, based on particle size information, temperature, and relative humidity. Ability to distinguish high pollen events was evaluated using F1 Scores, a score reflecting the fraction of true positives with respect to false positives and false negatives, with promising results (F1 ≤ 0.83). Model-constructed proxies demonstrated the ability to follow monthly and diurnal trends in pollen. We discuss the suitability of OPCs for monitoring pollen and offer advice for future progress. We demonstrate an attractive alternative for automated pollen monitoring that could provide valuable and timely information to the benefit of pollen allergy sufferers.

Isolating the species element in grass pollen allergy: A review

Grass pollen is a leading cause of allergy in many countries, particularly Europe. Although many elements of grass pollen production and dispersal are quite well researched, gaps still remain around the grass species that are predominant in the air and which of those are most likely to trigger allergy. In this comprehensive review we isolate the species aspect in grass pollen allergy by exploring the interdisciplinary interdependencies between plant ecology, public health, aerobiology, reproductive phenology and molecular ecology. We further identify current research gaps and provide open ended questions and recommendations for future research in an effort to focus the research community to develop novel strategies to combat grass pollen allergy. We emphasise the role of separating temperate and subtropical grasses, identified through divergence in evolutionary history, climate adaptations and flowering times. However, allergen cross-reactivity and the degree of IgE connectivity in sufferers between the two groups remains an area of active research. The importance of future research to identify allergen homology through biomolecular similarity and the connection to species taxonomy and practical implications of this to allergenicity is further emphasised. We also discuss the relevance of eDNA and molecular ecological techniques (DNA metabarcoding, qPCR and ELISA) as important tools in quantifying the connection between the biosphere with the atmosphere. By gaining more understanding of the connection between species-specific atmospheric eDNA and flowering phenology we will further elucidate the importance of species in releasing grass pollen and allergens to the atmosphere and their individual role in grass pollen allergy.

Towards European automatic bioaerosol monitoring: Comparison of 9 automatic pollen observational instruments with classic Hirst-type traps

To benefit allergy patients and the medical practitioners, pollen information should be available in both a reliable and timely manner; the latter is only recently possible due to automatic monitoring. To evaluate the performance of all currently available automatic instruments, an international intercomparison campaign was jointly organised by the EUMETNET AutoPollen Programme and the ADOPT COST Action in Munich, Germany (March-July 2021). The automatic systems (hardware plus identification algorithms) were compared with manual Hirst-type traps. Measurements were aggregated into 3-hourly or daily values to allow comparison across all devices. We report results for total pollen as well as for Betula, Fraxinus, Poaceae, and Quercus, for all instruments that provided these data. The results for daily averages compared better with Hirst observations than the 3-hourly values. For total pollen, there was a considerable spread among systems, with some reaching R² > 0.6 (3 h) and R² > 0.75 (daily) compared with Hirst-type traps, whilst other systems were not suitable to sample total pollen efficiently (R² < 0.3). For individual pollen types, results similar to the Hirst were frequently shown by a small group of systems. For Betula, almost all systems performed well (R² > 0.75 for 9 systems for 3-hourly data). Results for Fraxinus and Quercus were not as good for most systems, while for Poaceae (with some exceptions), the performance was weakest. For all pollen types and for most measurement systems, false positive classifications were observed outside of the main pollen season. Different algorithms applied to the same device also showed different results, highlighting the importance of this aspect of the measurement system. Overall, given the 30 % error on daily concentrations that is currently accepted for Hirst-type traps, several automatic systems are currently capable of being used operationally to provide real-time observations at high temporal resolutions. They provide distinct advantages compared to the manual Hirst-type measurements.

Climate change, airborne allergens, and three translational mitigation approaches

One of the important adverse impacts of climate change on human health is increases in allergic respiratory diseases such as allergic rhinitis and asthma. This impact is via the effects of increases in atmospheric carbon dioxide concentration and air temperature on sources of airborne allergens such as pollen and fungal spores. This review describes these effects and then explores three translational mitigation approaches that may lead to improved health outcomes, with recent examples and developments highlighted. Impacts have already been observed on the seasonality, production and atmospheric concentration, allergenicity, and geographic distribution of airborne allergens, and these are projected to continue into the future. A technological revolution is underway that has the potential to advance patient management by better avoiding associated increased exposures, including automated real-time airborne allergen monitoring, airborne allergen forecasting and modelling, and smartphone apps for mitigating the health impacts of airborne allergens.

Integration of reference data from different Rapid-E devices supports automatic pollen detection in more locations

Pollen is the most common cause of seasonal allergies, affecting over 33 % of the European population, even when considering only grasses. Informing the population and clinicians in real-time about the actual presence of pollen in the atmosphere is essential to reduce its harmful health and economic impact. Thus, there is a growing network of automatic particle analysers, and the reproducibility and transferability of implemented models are recommended since a reference dataset for local pollen of interest needs to be collected for each device to classify pollen, which is complex and time-consuming. Therefore, it would be beneficial to incorporate the reference dataset collected from other devices in different locations. However, it must be considered that laser-induced data are prone to device-specific noise due to laser and detector sensibility. This study collected data from two Rapid-E bioaerosol identifiers in Serbia and Italy and implemented a multi-modal convolutional neural network for pollen classification. We showed that models lost their performance when trained on data from one and tested on another device, not only in terms of the recognition ability but also in comparison with the manual measurements from Hirst-type traps. To enable pollen classification with just one model in both study locations, we first included the missing pollen classes in the dataset from the other study location, but it showed poor results, implying that data of one pollen class from different devices are more different than data of different pollen classes from one device. Combining all available reference data in a single model enabled the classification of a higher number of pollen classes in both study locations. Finally, we implemented a domain adaptation method, which improved the recognition ability and the correlations of transferred models only for several pollen classes.

Aeroallergen Monitoring by the National Allergy Bureau: A Review of the Past and a Look Into the Future

Monitoring aeroallergens has a long history within the American Academy of Allergy, Asthma & Immunology. The Aeroallergen Network of the National Allergy Bureau is composed mainly of members of the American Academy of Allergy, Asthma & Immunology, whose objectives are to enhance the knowledge of aerobiology and its relationship to allergy, increase the number of certified stations, maintain the standardization and quality of aerobiology data, improve the alert and forecast reporting system, and increase ties with other scientific entities inside and outside the United States. The public has a keen interest in pollen counts and pollen forecasts, as do many health professionals in the allergy community. In this review, we explore the past, present, and future of allergen monitoring with a focus on methods used for sampling, the training of those performing the analysis, and emerging technologies in the field. Although the development of automated samplers with machine intelligence offers great promise for meeting the goal of a fully automated system, there is still progress to be made regarding reliability and affordability.

Field Evaluation of an Automated Pollen Sensor

Background: Seasonal pollen is a common cause of allergic respiratory disease. In the United States, pollen monitoring occurs via manual counting, a method which is both labor-intensive and has a considerable time delay. In this paper, we report the field-testing results of a new, automated, real-time pollen imaging sensor in Atlanta, GA. Methods: We first compared the pollen concentrations measured by an automated real-time pollen sensor (APS-300, Pollen Sense LLC) collocated with a Rotorod M40 sampler in 2020 at an allergy clinic in northwest Atlanta. An internal consistency assessment was then conducted with two collocated APS-300 sensors in downtown Atlanta during the 2021 pollen season. We also investigated the spatial heterogeneity of pollen concentrations using the APS-300 measurements. Results: Overall, the daily pollen concentrations reported by the APS-300 and the Rotorod M40 sampler with manual counting were strongly correlated (r = 0.85) during the peak pollen season. The APS-300 reported fewer tree pollen taxa, resulting in a slight underestimation of total pollen counts. Both the APS-300 and Rotorod M40 reported Quercus (Oak) and Pinus (Pine) as dominant pollen taxa during the peak tree pollen season. Pollen concentrations reported by APS-300 in the summer and fall were less accurate. The daily total and speciated pollen concentrations reported by two collocated APS-300 sensors were highly correlated (r = 0.93–0.99). Pollen concentrations showed substantial spatial and temporal heterogeneity in terms of peak levels at three locations in Atlanta. Conclusions: The APS-300 sensor was able to provide internally consistent, real-time pollen concentrations that are strongly correlated with the current gold-standard measurements during the peak pollen season. When compared with manual counting approaches, the fully automated sensor has the significant advantage of being mobile with the ability to provide real-time pollen data. However, the sensor’s weed and grass pollen identification algorithms require further improvement.

Detection and Recognition of Pollen Grains in Multilabel Microscopic Images

Analysis of pollen material obtained from the Hirst-type apparatus, which is a tedious and labor-intensive process, is usually performed by hand under a microscope by specialists in palynology. This research evaluated the automatic analysis of pollen material performed based on digital microscopic photos. A deep neural network called YOLO was used to analyze microscopic images containing the reference grains of three taxa typical of Central and Eastern Europe. YOLO networks perform recognition and detection; hence, there is no need to segment the image before classification. The obtained results were compared to other deep learning object detection methods, i.e., Faster R-CNN and RetinaNet. YOLO outperformed the other methods, as it gave the mean average precision (mAP@.5:.95) between 86.8% and 92.4% for the test sets included in the study. Among the difficulties related to the correct classification of the research material, the following should be noted: significant similarities of the grains of the analyzed taxa, the possibility of their simultaneous occurrence in one image, and mutual overlapping of objects.