Abstract
Biological particles in the air such as pollen grains can cause environmental problems in the allergic population. Medical studies report that a prior knowledge of pollen season severity can be useful in the management of pollen-related diseases. The aim of this work was to forecast the severity of the Poaceae pollen season by using weather parameters prior to the pollen season. To carry out the study a historical database of 21 years of pollen and meteorological data was used. First, the years were grouped into classes by using cluster analysis. As a result of the grouping, the 21 years were divided into 3 classes according to their potential allergenic load. Pre-season meteorological variables were used, as well as a series of characteristics related to the pollen season. When considering pre-season meteorological variables, winter variables were separated from early spring variables due to the nature of the Mediterranean climate. Second, a neural network model as well as a discriminant linear analysis were built to forecast Poaceae pollen season severity, according to the three classes previously defined. The neural network yielded better results than linear models. In conclusion, neural network models could have a high applicability in the area of prevention, as the allergenic potential of a year can be determined with a high degree of reliability, based on a series of meteorological values accumulated prior to the pollen season.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Angeline PJ, Saunders GM, Pollack JB (1994) An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans Neural Networks 1:54–65
Arizmendi CM, Sánchez JR, Ramos NE, Ramos GJ (1993) Time series predictions with neural nets: applications to airborne pollen forecasting. Int J Biometeorol 37:139–144
Bebis G, Georgiopoulos M, Kasparis T (1997) Coupling weight elimination with genetic algorithms to reduce network size and preserve generalization. Neurocomputing 17:167–194
Brown RW (1995) The water relations of range plants: adaptations of water deficits. In: Bedunah DJ, Sosebee RE (eds). Wildland plants: physiological ecology and developmental morphology. Society for Range Management, Denver, Colo., pp 291–413
D’Amato G, Spieksma F Th M, Liccardi G, Jäger S, Russo M, Kontou-Fili K, Nikkels H, Wüthrich B, Bonini S (1998) Pollen-related allergy in Europe. Allergy 53:567–578
Domínguez E, Galán C, Villamandos F, Infante F (1992) Manejo y Evaluación de los datos obtenidos en los muestreos aerobiológicos. Monografías REA/EAN 1:1–13
Emberlin J (1994) The effects of patterns in climate and pollen abundance on allergy. Allergy 49:15–20
Frenguelli G, Bricchi E, Romano B, Mincigrucci G, Spieksma F Th M (1989) A predictive study on the beginning of the pollen season for Gramineae and Olea europea L. Aerobiologia 5:64–70
Galán C, Cuevas J, Infante F, Domínguez E (1989) Seasonal and diurnal variation of pollen from Gramineae in the atmosphere of Córdoba (Spain). Allergol immunopathol 17:245–249
Galán C, Emberlin J, Domínguez E, Bryant R, Villamandos F (1995) A comparative análisis of daily variations in the Gramineae pollen counts at Córdoba, Spain and London, UK. Ghana 34:189–198
Galán C, Fuillerat MJ, Comtois P, Domínguez E (1998) A predictive study of Cupressaceae pollen season onset, severity, maximum value and maximum value data. Aerobiologia 14:195–199
García N, Hervás C, Muñoz J, Covnet A (2003) A cooperative evolutionary model for evolving artificial neural networks”. IEEE Trans Neural Networks 14:575–596
González-Minero FJ, Candau P (1996) Prediction of the beginning of the olive full pollen season in South-West Spain. Aerobiologia 12:91–96
Hervás C, Algar JA, Silva M (2000) Correction of temperature variations in kinetic-based determinations by use of pruning computational neural networks in conjunction with genetic algorithms. J Chem Inf Comput Sci 40:724–731
Hidalgo PJ, Mangin A, Galán C, Hembise O, Vázquez LM, Sánchez O (2002) An automated system for surveying and forecasting Olea pollen dispersion. Aerobiologia 18:23–31
Jacobs RA (1978) Increased rates of convergence trough learning rate adaptation. Neural Networks 1:295–307
Laaidi M (2001) Forecasting the start of the pollen season of Poaceae: evaluation of some methods based on meteorological factors. Int J Biometeorol 45:1–7
Norris-Hill J, Emberlin J (1991) Diurnal variation of pollen concentration in the air of north-central London. Grana 30:229–234
Ranzi A, Lauriola P, Marletto V, Zinoni F (2003) Forecasting airborne pollen concentrations: development of local models. Aerobiology 19:39–45
Rumelhart DE, McLelland JC (1986) Parallel distributed processing: explorations in the microstructure of cognition. MIT, Boston
Sánchez Mesa JA, Galán C, Martínez JA, Hervás 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 32:1606–1612
Sánchez Mesa JA, Serrano P, Cariñanos P, Moreno C, Guerra F, Galán C (in press) Pollen allergy in Cordoba city: frequency of sensitization and relation with antihistamines sales. J Invest Allergol Clin Immunol
Spiekma F Th M, D’amato G, Mullins J, Nolard N, Wachter R, Weeke ER (1989) City Spore Concentrations in the European Economic Community (EEC). VI. Poaceae (Grasses), 1982–1986. Aerobiologia 5:38–43
Werbos PJ (1974) Beyond regression: New tools for prediction and analysis in the behavioural sciences. Ph D. thesis, University of Harvard
Whitley LD, Schaffer JD (1992) International workshop on combinations of genetic algorithms and neural networks. IEEE Computer Society. Vancouver, Canada
Widrow B, Winter RG, Baxter RA (1988) Layered neural nets for pattern recognition. Trans Acoust Speech Signal Process 36:1109–1118
Williams PM (1994) Bayesian regularization and pruning using a Laplace prior. Neural Computation 7:117–143
Williams RJ, Minai AA (1990) Back-propagation heuristics: A study of the Extended Delta-Bar-Delta algorithms. IEEE Intl Joint Conf Neural Networks 12:595–600
Yao X (1999) Evolving artificial neural networks. Proc IEEE 9:1423–1447
Acknowledgements
The authors wish to thank the Fondo de Investigación Sanitaria (FIS) for the BEFI Grant Ref: 00/9406 and the “Comisión Interministerial de Ciencia y Tecnología” TIC2002–04036-C05-02 (Department of Computer Science, University of Córdoba). Additional financial support from FEDER funds was also received
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sánchez Mesa, J.A., Galán, C. & Hervás, C. The use of discriminant analysis and neural networks to forecast the severity of the Poaceae pollen season in a region with a typical Mediterranean climate. Int J Biometeorol 49, 355–362 (2005). https://doi.org/10.1007/s00484-005-0260-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00484-005-0260-8