TIME-SERIES PREDICTIONS WITH NEURAL NETS - APPLICATION TO AIRBORNE POLLEN FORECASTING

Pollen allergy is a common disease causing rhinoconjunctivitis (hay fe ver) in 5-10% of the population. Medical studies have indicated that p ollen related diseases could be highly reduced if future pollen conten ts in the air could be predicted. In this work we have developed a new forecasting method that applies the ability of neural nets to predict the future behaviour of chaotic systems in order to make accurate pre dictions of the airborne pollen concentration. The method requires tha t the neural net be fed with non-zero values, which restricts the meth od predictions to the period following the start of pollen flight. The operational method outlined here constitutes a different point of vie w with respect to the more generally used forecasts of time series ana lysis, which require input of many meteorological parameters. Excellen t forecasts were obtained training a neural net by using only the time series pollen concentration values.