| Autor: |
Ranzi, Andrea, Lauriola, Paolo, Marletto, Vittorio, Zinoni, Franco |
| Zdroj: |
Aerobiologia; Mar2003, Vol. 19 Issue 1, p39-45, 7p |
| Abstrakt: |
People's sensitivity to allergies may representone of the most important health factors of thenext century to which attention must be paid inorder to reduce the incidence of social costsand improve the quality of life.Taking into consideration the earnest requestsof the medical-scientific communityEmilia-Romagna ARPA (Regional Agency for thePrevention of the Environment) moved theattention from the monitoring to a short andmedium term prediction of the concentration ofallergenic pollens in the air in order toachieve a more effective therapeutic action.Our main objectives are to improve seasonalforecasts and to interpret anomalous years.A neural network model for grass pollenforecasting has been implemented. Inputvariables were meteorological situations, i.e.,daily temperature (max., min. and average) andrainfall, in addition to combinations ofindividual variables and their thresholds. Theoutput was daily pollen concentration.The model was able to understand and predictanomalous years. We demonstrate that therelationships between pollen concentrations andmeteorological situations are independent fromsite. This means that such models canunderstand the differences in differentareas. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink