Drivers of the release of the allergens Bet v 1 and Phl p 5 from birch and grass pollen.

The drivers affecting the Pollen Allergen Potency (PAP, amount of allergen released per pollen) are sparsely known. Betula and Poaceae airborne pollen are the two main allergenic pollen in the World. Airborne pollen and their allergens Bet v 1 and Phl p 5 were simultaneously measured from 2010 to 2015 in Davos (Switzerland) and Munich (Germany) by using volumetric traps and ChemVol cascade impactors. Daily variations in PAP were analysed in PM>10 and PM2.5-10 air fractions and generalized additive models were created to explain which factors determine PAP, including meteorological parameters and inorganic pollutants. 87.1 ± 13.9% of Bet v 1 and 88.8 ± 15.5% of Phl p 5 was detected in the fraction PM>10 where most pollen grains were collected. Significantly higher PAP for grasses (3.5 ± 1.9 pg Phl p 5/pollen grain) were observed in Munich than in Davos (2.4 ± 1.5 pg/pollen grain, p < 0.001), but not for Betula (2.5 ± 1.6 pg Bet v 1/pollen grain in Munich and 2.3 ± 1.7 in Davos, N.S.). PAP varied between days, years and location, and increased along the pollen season for Poaceae, but remaining constant for Betula. Free allergens (allergens observed in the fraction with limited pollen, PM2.5- 10) were recorded mostly at the beginning or at the end of the pollen season, being linked to higher humidity and rainy days. Also, PAP was higher when the airborne pollen concentrations increased rapidly after one day of low/moderate levels. Our findings show that pollen exposure explains allergen exposure only to a limited extend, and that day in the season, geographic location and some weather conditions need to be considered also to explain symptoms of allergic individuals.

Effects of future climate change on birch abundance and their pollen load.

Climate change impacts on the structure and function of ecosystems will worsen public health issues like allergic diseases. Birch trees (Betula spp.) are important sources of aeroallergens in Central and Northern Europe. Birches are vulnerable to climate change as these trees are sensitive to increased temperatures and summer droughts. This study aims to examine the effect of climate change on airborne birch pollen concentrations in Central Europe using Bavaria in Southern Germany as a case study. Pollen data from 28 monitoring stations in Bavaria were used in this study, with time series of up 30 years long. An integrative approach was used to model airborne birch pollen concentrations taking into account drivers influencing birch tree abundance and birch pollen production and projections made according to different climate change and socioeconomic scenarios. Birch tree abundance is projected to decrease in parts of Bavaria at different rates, depending on the climate scenario, particularly in current centres of the species distribution. Climate change is expected to result in initial increases in pollen load but, due to the reduction in birch trees, the amount of airborne birch pollen will decrease at lower altitudes. Conversely, higher altitude areas will experience expansions in birch tree distribution and subsequent increases in airborne birch pollen in the future. Even considering restrictions for migration rates, increases in pollen load are likely in Southwestern areas, where positive trends have already been detected during the last three decades. Integrating models for the distribution and abundance of pollen sources and the drivers that control birch pollen production allowed us to model airborne birch pollen concentrations in the future. The magnitude of changes depends on location and climate change scenario.

Predicting the main pollen season of Broussonetia Papyrifera (paper mulberry) tree.

Paper mulberry pollen, declared a pest in several countries including Pakistan, can trigger severe allergies and cause asthma attacks. We aimed to develop an algorithm that could accurately predict high pollen days to underpin an alert system that would allow patients to take timely precautionary measures. We developed and validated two prediction models that take historical pollen and weather data as their input to predict the start date and peak date of the pollen season in Islamabad, the capital city of Pakistan. The first model is based on linear regression and the second one is based on phenological modelling. We tested our models on an original and comprehensive dataset from Islamabad. The mean absolute errors (MAEs) for the start day are 2.3 and 3.7 days for the linear and phenological models, respectively, while for the peak day, the MAEs are 3.3 and 4.0 days, respectively. These encouraging results could be used in a website or app to notify patients and healthcare providers to start preparing for the paper mulberry pollen season. Timely action could reduce the burden of symptoms, mitigate the risk of acute attacks and potentially prevent deaths due to acute pollen-induced allergy.

Machine learning methods for low-cost pollen monitoring - Model optimisation and interpretability.

Pollen is a major issue globally, causing as much as 40 % of the population to suffer from hay fever and other allergic conditions. Current techniques for monitoring pollen are either laborious and slow, or expensive, thus alternative methods are needed to provide timely and more localised information on airborne pollen concentrations. We have demonstrated previously that low-cost Optical Particle Counter (OPC) sensors can be used to estimate pollen concentrations when machine learning methods are used to process the data and learn the relationships between OPC output data and conventionally measured pollen concentrations. This study demonstrates how methodical hyperparameter tuning can be employed to significantly improve model performance. We present the results of a range of models based on tuned hyperparameter configurations trained to predict Poaceae (Barnhart), Quercus (L.), Betula (L.), Pinus (L.) and total pollen concentrations. The results achieved here are a significant improvement on results we previously reported: the average R2 scores for the total pollen models have at least doubled compared to using previous parameter settings. Furthermore, we employ the explainable Artificial Intelligence (XAI) technique, SHAP, to interpret the models and understand how each of the input features (i.e. particle sizes) affect the estimated output concentration for each pollen type. In particular, we found that Quercus pollen has a strong positive correlation with particles of optical diameter 1.7-2.3 µm, which distinguishes it from other pollen types such as Poaceae and may suggest that type-specific subpollen particles are present in this size range. There is much further work to be done, especially in training and testing models on data obtained across different environments to evaluate the extent of generalisability. Nevertheless, this work demonstrates the potential this method can offer for low-cost monitoring of pollen and the valuable insight we can gain from what the model has learned.

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.

Environmental exposure and sensitization patterns in a Swiss alpine pediatric cohort.

Background: The level of environmental exposure throughout life may contribute to the prevalence of allergic sensitization and allergic disease. The alpine climate has been considered a healthy climate with little allergen exposure and pollution. We conducted a cross-sectional study to investigate local environmental exposure and concomitant prevalence of allergic sensitization among local school children born and raised in an alpine environment. Methods: Clinical and demographic data were collected with a questionnaire. Allergen content was assessed in residential settled dust samples, lifetime exposure to pollen and air pollution was calculated using data from national pollen and air pollution monitoring stations, and the allergic sensitization profile was determined with component resolved diagnostics (ISAC®). Univariate and multivariate regression models were used to estimate the relation between exposure and sensitization. Results: In a cohort of children born and raised in an alpine environment, sensitization to aeroallergens is quite common (38%), especially to grass (33%) and cat (16%). House dust mite allergen was detected in up to 38% of residential dust samples, but sensitization to HDM was low (2.5%). Pollutant levels were low, but an increasing trend was observed in the amount of ozone and PM10. Living close to a busy road was associated with increased odds OR (95% CI) for being sensitized to any allergen 2.7 (1.0-7.2), to outdoor allergens 2.8 (1.1-7.1) and being sensitized plus reporting symptoms of rhinoconjunctivitis 4.4 (1.3-14.8) and asthma 5.5 (1.4-21). Indoor living conditions, including the presence of visible mold, increased the odds of being sensitized to indoor allergens (1.9 (1.1-3.2) and being sensitized plus reporting symptoms of rhinoconjunctivitis 1.9 (1.0-3.6) and asthma 2.1 (1.0-4.1). Conclusion: In a healthy alpine environment, pollution might still be an important factor contributing to allergic sensitization.

Diurnal pattern of Poaceae and Betula pollen flight in Central Europe.

In Central Europe the most common allergies are provoked by grass or birch pollen allergens. We determined the intra-daily behavior of airborne pollen grains of grasses (Poaceae) and birch (Betula ssp.) in Central Europe, based on data obtained from a network of automatic pollen monitors over Europe (www.pollenscience.eu). Our aim was to determine the time of day when the lowest concentrations occur, to provide allergic individuals the optimal time to ventilate their homes. The study was carried out in three Central European capitals, Berlin (Germany), Paris-Saclay (France), and Luxembourg (Luxembourg), as well as in eight stations in Germany (Altötting, Feucht, Garmisch-Partenkirchen, Hof, Marktheidenfeld, Mindelheim, Munich and Viechtach). The diurnal rhythm of these eleven locations was analyzed for either the complete, first week, peak week, peak day and last week of the pollen season. The data studied were reported as pollen/m3 measured in 3 h periods. Stations were classified as city, semi-populated or countryside areas using land-use and population density criteria. Grass pollen has a more pronounced diurnal rhythm than birch pollen concentrations. A significant difference was observed when comparing day (6-21 h) versus night (21-6 h) for all stations. No difference was detected between city and countryside for both pollen types, although for Poaceae a longer period of maximum concentrations was observed in big cities and higher day/night-time differences were registered in the countryside (6.4) than in cities (3.0). The highest pollen concentrations were observed between 9 and 18 h for grass, but the rhythm was less pronounced for birch pollen. For allergic individuals who want to bring in fresh air in their homes, we recommend opening windows after 21 h, but even better early in the morning between 6 and 9 h before pollinations (re)starts.

Alternaria spore exposure in Bavaria, Germany, measured using artificial intelligence algorithms in a network of BAA500 automatic pollen monitors.

Although Alternaria spores are well-known allergenic fungal spores, automatic bioaerosol recognition systems have not been trained to recognize these particles until now. Here we report the development of a new algorithm able to classify Alternaria spores with BAA500 automatic bioaerosol monitors. The best validation score was obtained when the model was trained on both data from the original dataset and artificially generated images, with a validation unweighted mean Intersection over Union (IoU), also called Jaccard Index, of 0.95. Data augmentation techniques were applied to the training set. While some particles were not recognized (false negatives), false positives were few. The results correlated well with manual counts (mean of four Hirst-type traps), with R2 = 0.78. Counts from BAA500 were 1.92 times lower than with Hirst-type traps. The algorithm was then used to re-analyze the historical automatic pollen monitoring network (ePIN) dataset (2018-2022), which lacked Alternaria spore counts. Re-analysis of past data showed that Alternaria spore exposure in Bavaria was very variable, with the highest counts in the North (Marktheidenfeld, 154 m a.s.l.), and the lowest values close to the mountains in the South (Garmisch-Partenkirchen, 735 m a.s.l.). This approach shows that in our network future algorithms can be run on past datasets. Over time, the use of different algorithms could lead to misinterpretations as stemming from climate change or other phenological causes. Our approach enables consistent, homogeneous treatment of long-term series, thus preventing variability in particle counts owing to changes in the algorithms.

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.