RESUMO
BACKGROUND: There is evidence that global anthropogenic climate change may be impacting floral phenology and the temporal and spatial characteristics of aero-allergenic pollen. Given the extent of current and future climate uncertainty, there is a need to strengthen predictive pollen forecasts. METHODS: The study aims to use CatBoost (CB) and deep learning (DL) models for predicting the daily total pollen concentration up to 14 days in advance for 23 cities, covering all five continents. The model includes the projected environmental parameters, recent concentrations (1, 2 and 4 weeks), and the past environmental explanatory variables, and their future values. RESULTS: The best pollen forecasts include Mexico City (R2(DL_7) ≈ .7), and Santiago (R2(DL_7) ≈ .8) for the 7th forecast day, respectively; while the weakest pollen forecasts are made for Brisbane (R2(DL_7) ≈ .4) and Seoul (R2(DL_7) ≈ .1) for the 7th forecast day. The global order of the five most important environmental variables in determining the daily total pollen concentrations is, in decreasing order: the past daily total pollen concentration, future 2 m temperature, past 2 m temperature, past soil temperature in 28-100 cm depth, and past soil temperature in 0-7 cm depth. City-related clusters of the most similar distribution of feature importance values of the environmental variables only slightly change on consecutive forecast days for Caxias do Sul, Cape Town, Brisbane, and Mexico City, while they often change for Sydney, Santiago, and Busan. CONCLUSIONS: This new knowledge of the ecological relationships of the most remarkable variables importance for pollen forecast models according to clusters, cities and forecast days is important for developing and improving the accuracy of airborne pollen forecasts.
Assuntos
Alérgenos , Previsões , Pólen , Pólen/imunologia , Previsões/métodos , Humanos , Mudança Climática , Modelos Teóricos , Monitoramento Ambiental/métodosRESUMO
BACKGROUND: Ongoing climate change might, through rising temperatures, alter allergenic pollen biology across the northern hemisphere. We aimed to analyse trends in pollen seasonality and pollen load and to establish whether there are specific climate-related links to any observed changes. METHODS: For this retrospective data analysis, we did an extensive search for global datasets with 20 years or more of airborne pollen data that consistently recorded pollen season indices (eg, duration and intensity). 17 locations across three continents with long-term (approximately 26 years on average) quantitative records of seasonal concentrations of multiple pollen (aeroallergen) taxa met the selection criteria. These datasets were analysed in the context of recent annual changes in maximum temperature (Tmax) and minimum temperature (Tmin) associated with anthropogenic climate change. Seasonal regressions (slopes) of variation in pollen load and pollen season duration over time were compared to Tmax, cumulative degree day Tmax, Tmin, cumulative degree day Tmin, and frost-free days among all 17 locations to ascertain significant correlations. FINDINGS: 12 (71%) of the 17 locations showed significant increases in seasonal cumulative pollen or annual pollen load. Similarly, 11 (65%) of the 17 locations showed a significant increase in pollen season duration over time, increasing, on average, 0·9 days per year. Across the northern hemisphere locations analysed, annual cumulative increases in Tmax over time were significantly associated with percentage increases in seasonal pollen load (r=0·52, p=0·034) as were annual cumulative increases in Tmin (r=0·61, p=0·010). Similar results were observed for pollen season duration, but only for cumulative degree days (higher than the freezing point [0°C or 32°F]) for Tmax (r=0·53, p=0·030) and Tmin (r=0·48, p=0·05). Additionally, temporal increases in frost-free days per year were significantly correlated with increases in both pollen load (r=0·62, p=0·008) and pollen season duration (r=0·68, p=0·003) when averaged for all 17 locations. INTERPRETATION: Our findings reveal that the ongoing increase in temperature extremes (Tmin and Tmax) might already be contributing to extended seasonal duration and increased pollen load for multiple aeroallergenic pollen taxa in diverse locations across the northern hemisphere. This study, done across multiple continents, highlights an important link between ongoing global warming and public health-one that could be exacerbated as temperatures continue to increase. FUNDING: None.