Artificial neural network model of the relationship between Betula pollen and meteorological factors in Szczecin (Poland)

Abstract

Birch pollen is one of the main causes of allergy during spring and early summer in northern and central Europe. The aim of this study was to create a forecast model that can accurately predict daily average concentrations of Betula sp. pollen grains in the atmosphere of Szczecin, Poland. In order to achieve this, a novel data analysis technique—artificial neural networks (ANN)—was used. Sampling was carried out using a volumetric spore trap of the Hirst design in Szczecin during 2003–2009. Spearman’s rank correlation analysis revealed that humidity had a strong negative correlation with Betula pollen concentrations. Significant positive correlations were observed for maximum temperature, average temperature, minimum temperature and precipitation. The ANN resulted in multilayer perceptrons 366 8: 2928-7-1:1, time series prediction was of quite high accuracy (SD Ratio between 0.3 and 0.5, R > 0.85). Direct comparison of the observed and calculated values confirmed good performance of the model and its ability to recreate most of the variation.