International Journal of Biometeorology

, Volume 49, Issue 5, pp 310–316 | Cite as

Artificial neural networks as a useful tool to predict the risk level of Betula pollen in the air

  • M. Castellano-MéndezEmail author
  • M. J. Aira
  • I. Iglesias
  • V. Jato
  • W. González-Manteiga
Original Article


An increasing percentage of the European population suffers from allergies to pollen. The study of the evolution of air pollen concentration supplies prior knowledge of the levels of pollen in the air, which can be useful for the prevention and treatment of allergic symptoms, and the management of medical resources. The symptoms of Betula pollinosis can be associated with certain levels of pollen in the air. The aim of this study was to predict the risk of the concentration of pollen exceeding a given level, using previous pollen and meteorological information, by applying neural network techniques. Neural networks are a widespread statistical tool useful for the study of problems associated with complex or poorly understood phenomena. The binary response variable associated with each level requires a careful selection of the neural network and the error function associated with the learning algorithm used during the training phase. The performance of the neural network with the validation set showed that the risk of the pollen level exceeding a certain threshold can be successfully forecasted using artificial neural networks. This prediction tool may be implemented to create an automatic system that forecasts the risk of suffering allergic symptoms.


Aerobiology Allergenic risk Binary data Betula pollen Error function Neural networks Pollen level Probability function 



This study was partially funded by the Xunta de Galicia’s Environment Department (PGDIT00MAM38301PR). D.W. González-Manteiga’s work was funded by BFM2002-03213 (European FEDER support included) from the Spanish Ministry of Science and Technology, and by PGIDIT03PXIC20702PN Dirección Xeral de I+D Xunta de Galicia.


  1. Aira MJ, Jato V, Iglesias I (1998) Alnus and Betula pollen content in the atmosphere of Santiago de Compostela, north-western Spain (1993–1995). Aerobiologia 14:135–140Google Scholar
  2. Aira MJ, Ferreiro M, Iglesias I, Jato V, Marcos C, Varela S, Vidal C (2001) Aeropalinología de cuatro ciudades de Galicia y su incidencia sobre la sintomatología alérgica estacional. Actas XIII Simposio de la A.P.L.E.CartagenaGoogle Scholar
  3. Agresti A (1990) Categorical data analysis. Wiley, New YorkGoogle Scholar
  4. Andersen TB (1991) A model to predict the beginning of the pollen season. Grana 30:269–275Google Scholar
  5. Arenas L, González C, Tabarés JM, Iglésias I, Méndez J, Jato V (1996) Sensibilización cutánea a pólenes en pacientes afectos de rinoconjuntivitis-asma en la población de Ourense en el año 1994–95. 1st European symposium on aerobiology, Santiago de Compostela, 11–13 September 1996Google Scholar
  6. Atkinson H, Larsson KA (1990) A 10-year record of the arboreal pollen in Stockholm, Sweden. Grana 29:229–237Google Scholar
  7. Bishop C (1995) Neural networks for pattern recognition. Clarendon, OxfordGoogle Scholar
  8. Caramiello R, Siniscalco C, Mercalli L, Potenza A (1994) The relationship between airborne pollen grains and unusual weather conditions in Turin (Italy) in 1989, 1990 and 1991. Grana 33:327–332Google Scholar
  9. Chakraborty K, Mehrotra K (1992) Forecasting the behaviour of a multivariate time series using neural networks. Neural Netw 5:961–970Google Scholar
  10. Chauvin Y, Rumelhart DE (1995) Backpropagation: theory, architectures, and applications. Lawrence Erlbaum Associates, Mawah, N.J.Google Scholar
  11. Clot B (2001) Airborne birch pollen in Neuchâtel (Switzerland): onset, peak and daily patterns. Aerobiologia 17:25–29CrossRefGoogle Scholar
  12. Corsico R (1993) L’asthme allergique en Europe. In: Spieksma FTM, Nolard N, Frenguelli G, Van Moerbeke D (eds) Pollens de l’air en Europe. UCB, Braine-l’Alleud, pp 19–29Google Scholar
  13. Costa M, Higueras J Morla C (1990) Abedulares de la Sierra de San Mamed (Orense, España). Acta B Malacitana 15:253–265Google Scholar
  14. Cybenko G (1989) Approximations by superpositions of a sigmoidal function. Math Contr Signals Syst l 2:303–314Google Scholar
  15. D’Amato G Spieksma FTM (1992) European allergenic pollen types. Aerobiologia 8:447–450Google Scholar
  16. Domínguez E (1995) La Red Española de Aerobiología. Monografía REA 1:1–8Google Scholar
  17. Dopazo A (2001) Variación estacional y modelos predictivos de polen y esporas aeroalergénicos en Santiago de Compostela. Dissertation, University of Santiago de CompostelaGoogle Scholar
  18. Ekebom A, Verterberg O, Hjelmroos M (1996) Detection and quantification of airborne birch pollen allergens on PVDF membranes: immunoblotting and chemiluminescence. Grana 35:113–118Google Scholar
  19. Goldberger AS (1973) Correlations between binary choices and probabilistic predictions. J Am Stat Assoc 68:84Google Scholar
  20. Hastie T (1987) A closer look at the deviance. Am Stat 41:16–20Google Scholar
  21. Hidalgo PJ, Mangin A, Galán C, Hembise O, Vázquez LM, Sánchez O (2002). An automated system for surveying and forecasting Olea pollen dispersion. Aerobiologia 18:23–31CrossRefGoogle Scholar
  22. Hjelmroos M (1991) Evidence of long-distance transport of Betula pollen. Grana 30:215–228Google Scholar
  23. Hornik KM, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366CrossRefGoogle Scholar
  24. Izco J (1994) O bosque Atlántico. In: Vales C (ed) Os Bosques Atlánticos Europeos. Bahía, La Coruña, pp 13–49Google Scholar
  25. Jato V, Aira MJ, Iglésias MI, Alcázar P, Cervigón P, Fernández D, Recio M, Ruíz L, Sbai L (2000) Aeropalynology of birch (Betula sp.) in Spain. Pollen 10:39–49Google Scholar
  26. Laaidi M (2001) Regional variations in the pollen season of Betula in Burgundy: two models for predicting the start of the pollination. Aerobiologia 17:247–254CrossRefGoogle Scholar
  27. Larsson K (1993) Prediction of the pollen season with a cumulated activity method. Grana 32:111–114Google Scholar
  28. Latalowa M, Mietus M, Uruska A (2002) Seasonal variations in the atmospheric Betula pollen count in Gdansk (southern Baltic coast) in relation to meteorological parameters. Aerobiologia 18:33–43CrossRefGoogle Scholar
  29. Lewis WH, Vinay P, Zenger VE (1983) Airborne and allergenic pollen of North America. Johns Hopkins University Press, BaltimoreGoogle Scholar
  30. McCullagh P, Nelder JA (1989) General linear models, 2nd edn. Chapman & Hall, LondonGoogle Scholar
  31. Méndez J (2000) Modelos de comportamiento estacional e intradiurno de los pólenes y esporas de la ciudad de Ourense y su relación con los parámetros meteorológicos. Dissertation, University of VigoGoogle Scholar
  32. Moreno G (1990) Flora Ibérica. In: Castroviejo S. (ed) Real Jardín Botánico, vol. 2. C.S.I.C., MadridGoogle Scholar
  33. Moore PD, Webb JA (1978) An illustrated guide to pollen analysis. Hodder and Stoughton, LondonGoogle Scholar
  34. Moseholm L, Weeke ER, Petersen BN (1987) Forecast of pollen concentration of Poaceae (grasses) in the air by time series analysis. Pollen Spores 2–3:305–322Google Scholar
  35. Negrini AC, Voltolini S, Troise C, Arobba D (1992) Comparison between Urticaceae (Parietaria) pollen count and hay fever symptoms: assessment of a threshold value. Aerobiologia 8:325–329Google Scholar
  36. Norris-Hill J, Emberlin J (1991) Diurnal variation of pollen concentration in the air of north-central London. Grana 30:229–234Google Scholar
  37. Park J, Sandberg IW (1991) Universal approximation using radial basis function networks. Neural Comput 3:246–257Google Scholar
  38. Rantio-Lehtimäki A, Pehkonen E, Yli Panula P (1996) Pollen allergic symptoms in the off season? Compostela Aerobiol 96:91–92Google Scholar
  39. Ranzi A, Lauriola P, Marletto V Zinozi F (2000) Forecasting airborne pollen concentrations: development of local models. In: Abstracts of the European Symposium on Aerobiology, Vienna, 5–9 September 2000, p 43Google Scholar
  40. Ripley BB (1996) Pattern recognition using neural networks. Cambridge University Press, CambridgeGoogle Scholar
  41. Rodríguez-Rajo FJ (2000) El polen como fuente de contaminación ambiental. Dissertation, University of VigoGoogle Scholar
  42. Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65:386–408Google Scholar
  43. Ruffaldi P Greffier F (1991) Birch (Betula) pollen incidence in France (1987–1990). Grana 30:248–254Google Scholar
  44. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing: explorations in the microstructure of cognition, vol 1. MIT Press, Cambridge, Mass., pp 318–362Google Scholar
  45. Sánchez-Mesa JA, Galán C, Martínez-Heras JA, Hervás-Martínez C (2002) The use of a neural network to forecast daily grass pollen concentration in a Mediterranean region: the southern part of the Iberian Peninsula. Clin Exp Allergy 32:1606–1612CrossRefGoogle Scholar
  46. Spieksma FTM (1990) Pollinosis in Europe: new observations and developments. Rev Paleobot Palynol 64:35–40CrossRefGoogle Scholar
  47. Spieksma FTM, Frenguelli G, Nikkels AH, Mincigrucci G, Smithius LOMJ, Bricchi E, Dankaart W, Romano B (1989) Comparative study of airborne pollen concentrations in central Italy and The Netherlands (1982–1985). Grana 28:25–36Google Scholar
  48. Spieksma FTM, Emberlin JC, Hjelmroos M, Jäger S, Leuschner RM (1995) Atmospheric birch (Betula) pollen in Europe: trends and fluctuations in annual quantities and the starting dates of the seasons. Grana 34:51–57Google Scholar
  49. Wallin JE, Segerström V, Rosenhall L, Bergmann E, Hjelmroos M (1991) Allergic symptoms caused by long distance transported birch pollen. Grana 30:256–268Google Scholar
  50. Wihl JA, Ipsen B, Nüchel PB, Munch EP, Janniche EP, Lövenstein H (1998) Immunotherapy with partially purified and standardized tree pollen axtracts. Allergy 43:363–369Google Scholar

Copyright information

© ISB 2005

Authors and Affiliations

  • M. Castellano-Méndez
    • 1
    Email author
  • M. J. Aira
    • 2
  • I. Iglesias
    • 3
  • V. Jato
    • 3
  • W. González-Manteiga
    • 1
  1. 1.Department of Statistics and Operation ResearchUniversidade de Santiago de CompostelaSantiago de Compostela A CoruñaSpain
  2. 2.Department of Vegetal BiologyUniversidade de Santiago de CompostelaSantiago de Compostela A CoruñaSpain
  3. 3.Departament of Vegetal Biology and Soil SciencesUniversity of VigoSpain

Personalised recommendations