Forecasting daily total pollen concentrations on a global scale.
allergy
artificial intelligence
environmental variables
feature importance cluster
pollen forecast
Journal
Allergy
ISSN: 1398-9995
Titre abrégé: Allergy
Pays: Denmark
ID NLM: 7804028
Informations de publication
Date de publication:
12 Jul 2024
12 Jul 2024
Historique:
revised:
30
04
2024
received:
22
11
2023
accepted:
27
05
2024
medline:
12
7
2024
pubmed:
12
7
2024
entrez:
12
7
2024
Statut:
aheadofprint
Résumé
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. 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. The best pollen forecasts include Mexico City (R 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.
Sections du résumé
BACKGROUND
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
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
RESULTS
The best pollen forecasts include Mexico City (R
CONCLUSIONS
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.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024 European Academy of Allergy and Clinical Immunology and John Wiley & Sons Ltd.
Références
Masoli M, Fabian D, Holt S, Beasley R. The global burden of asthma: executive summary of the GINA dissemination committee report. Allergy. 2004;59:469‐478.
World Allergy Organisation. In: Pawankar R, Canonica GW, Holgate S, Lockey RF, eds. White Book on Allergy: Update 2013. World Allergy Organization; 2013.
National Asthma Council Australia. Updated Asthma Charts for Health Professionals. Accessed June 25, 2023. http://www.nationalasthma.org.au
GBD 2017 Disease and Injury Incidence and Prevalence Collaborators. Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017: a systematic analysis for the global burden of disease study 2017. Lancet. 2018;392:1789‐1858.
World Health Organization. World Health Statistics 2018: Monitoring Health for the SDGs, Sustainable Development Goals. World Health Organization; 2018.
Brunekreef B, Hoek G, Fischer P, Spieksma FT. Relation between airborne pollen concentrations and daily cardiovascular and respiratory‐disease mortality. Lancet. 2000;355:1517‐1518.
Hanigan I, Johnston FH. Respiratory hospital admissions were associated with ambient airborne pollen in Darwin, Australia, 2004‐2005. Clin Exp Allergy. 2007;37:1556‐1565.
Weichenthal S, Lavigne E, Villeneuve PJ, Reeves F. Airborne pollen concentrations and emergency room visits for myocardial infarction: a multicity case‐crossover study in Ontario, Canada. Am J Epidemiol. 2016;183:613‐621.
Low RB, Bielory L, Qureshi AI, Dunn V, Stuhlmiller DFE, Dickey DA. The relation of stroke admissions to recent weather, airborne allergens, air pollution, seasons, upper respiratory infections, and asthma incidence, September 11, 2001, and day of the week. Stroke. 2006;37:951‐957.
Stickley A, Ng CFS, Konishi S, Koyanagi A, Watanabe C. Airborne pollen and suicide mortality in Tokyo, 2001‐2011. Environ Res. 2017;155:134‐140.
Gilles S, Blume C, Wimmer M, et al. Pollen exposure weakens innate defence against respiratory viruses. Allergy. 2020;75:487‐730.
Damialis A, Gilles S, Sofiev M, Sofieva V, et al. Higher airborne pollen concentrations correlated with increased SARS‐CoV‐2 infection rates, as evidenced from 31 countries across the globe. Proc Natl Acad Sci USA. 2021;118:e2019034118.
Maya‐Manzano JM, Smith M, Markey E, Hourihane Clancy J, Sodeau J, O´Connor DJ. Recent developments in monitoring and modelling airborne pollen, a review. Grana. 2021;60:1‐19.
Voukantsis D, Niska H, Karatzas K, Riga M, Damialis A, Vokou D. Forecasting daily pollen concentrations using data‐driven modeling methods in Thessaloniki, Greece. Atmos Environ. 2010;44:5101‐5111.
Chen C, HeW ZH, Xue Y, Zhu M. A comparative study among machine learning and numerical models for simulating groundwater dynamics in the Heihe River basin, northwestern China. Sci Rep. 2020;10:1‐13.
Navares R, Aznarte JL. Predicting the Poaceae pollen season: six month‐ahead forecasting and identification of relevant features. Int J Biometeorol. 2017;61:647‐656.
Cordero JM, Rojo J, Gutiérrez‐Bustillo AM, Narros A, Borge R. Predicting the Olea pollen concentration with a machine learning algorithm ensemble. Int J Biometeorol. 2021;65:541‐554.
Voukantsis D, Karatzas K, Jaeger S, Berger U, Smith M. Analysis and forecasting of airborne pollen‐induced symptoms with the aid of computational intelligence methods. Aerobiologia. 2013;29:175‐185.
Valencia JA, Astray G, Fernández‐González M, Aira MJ, Rodríguez‐Rajo FJ. Assessment of neural networks and time series analysis to forecast airborne Parietaria pollen presence in the Atlantic coastal regions. Int J Biometeorol. 2019;63:735‐745.
Lo F, Bitz CM, Hess JJ. Development of a Random Forest Model for forecasting allergenic pollen in North America. Sci Total Environ. 2021;773:145590.
Csépe Z, Makra L, Voukantsis D, et al. Predicting daily ragweed pollen concentrations using computational intelligence techniques over two heavily polluted areas in Europe. Sci Total Environ. 2014;476‐477:542‐552.
Csépe Z, Leel‐Őssy Á, Mányoki G, et al. The application of a neural network‐based ragweed pollen forecast by the Ragweed Pollen Alarm System in the Pannonian biogeographical region. Aerobiologia. 2020;36:131‐140.
Zewdie GK, Lary DJ, Levetin E, Garuma GF. Applying deep neural networks and ensemble machine learning methods to forecast airborne Ambrosia pollen. Int J Environ Res Public Health. 2019a;16:1‐14.
Dai W, Jin H, Zhang Y, Liu T, Zhou Z. Detecting temporal changes in the temperature sensitivity of spring phenology with global warming: application of machine learning in phenological model. Agric For Meteorol. 2019;279:107702.
Zewdie GK, Lary DJ, Liu X, Wu DJ, Levetin E. Estimating the daily pollen concentration in the atmosphere using machine learning and NEXRAD weather radar data. Environ Monit Assess. 2019b;191:418.
Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Andrey G. CatBoost: unbiased boosting with categorical features. arXiv. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa‐Bianchi N, Garnett R, eds. Advances in Neural Information Processing Systems. Vol 31. NeurIPS; 2018.
Bentéjac C, Csörgő A, Martínez‐Muñoz G, et al. A comparative analysis of gradient boosting algorithms. Artif Intell Rev. 2021;54:1937‐1967.
Kuhn M, Johnson K. Applied Predictive Modeling. Springer; 2013.
Russell S, Norvig P. Artificial Intelligence: A Modern Approach. 3rd ed. Pearson Education Limited; 2015.
Xu Y, Goodacre R. On splitting training and validation set: a comparative study of cross‐validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. J Anal Test. 2018;2:249‐262.
Lops Y, Choi Y, Eslami E, Sayeed A. Real‐time 7‐day forecast of pollen counts using a deep convolutional neural network. Neural Comput & Applic. 2020;32:11827‐11836.
Chicco D, Warrens MJ, Jurman G. The coefficient of determination R‐squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci. 2021;7:e623.
CatBoost. Feature Importance, PredictionValuesChange method. Accessed October 17, 2021. https://catboost.ai/en/docs/concepts/fstr#regular‐feature‐importance
McInnes L, Healy J, Melville J. UMAP: Uniform manifold approximation and projection for dimension reduction. 2018. arXiv:1802.03426.
Ester M, Kriegel HP, Sander J, Xu X. A density‐based algorithm for discovering clusters in large spatial databases with noise. KDD‐96 Proceedings. 1996;96:226‐231.
Pawankar R. Allergic diseases and asthma: a global public health concern and a call to action. World Allergy Organ J. 2014;7:12.
Kolek F, Plaza MDP, Leier‐Wirtz V, Friedmann A, Traidl‐Hoffmann C, Damialis A. Earlier flowering of Betula pendula roth in Augsburg, Germany, due to higher temperature, NO2 and urbanity, and relationship with Betula spp. pollen season. Int J Environ Res Public Health. 2021;18:10325.
Rojo J, Oteros J, Picornell A, et al. Effects of future climate change on birch abundance and their pollen load. Glob Chang Biol. 2021;27:5934‐5949.
Silverberg JI, Braunstein M, Lee‐Wong M. Association between climate factors, pollen counts, and childhood hay fever prevalence in the United States. J Allergy Clin Immunol. 2015;135(2):463‐469.
Sun ZB, Zhao YX, An XQ, et al. Effects of airborne pollen on allergic rhinitis and asthma across different age groups in Beijing. China Sci Total Environ. 2024;912:169215.
Zewdie GK, Liu X, Wu DJ, Lary DJ, Levetin E. Applying machine learning to forecast daily Ambrosia pollen using environmental and NEXRAD parameters. Environ Monit Assess. 2019c;191(S2):261.
Emmerson KM, Addison‐Smith E, Ebert E, et al. Evaluation of the performance of short‐term curated daily airborne grass pollen forecasts in diverse biogeographical regions during the AusPollen partnership project 2016‐2020. Atmos Environ. 2022;X15:100183.
Davies JM, Addison‐Smith B, Milic A, et al. The AusPollen partnership project: allergenic airborne grass pollen seasonality and magnitude across temperate and subtropical eastern Australia, 2016‐2020. Environ Res. 2022;214:113762.