Forecasting ragweed pollen characteristics with nonparametric regression methods over the most polluted areas in Europe

摘要: Nonparametric time-varying regression methods were developed to forecast daily ragweed pollen concentration, and the probability of exceedance a given concentration threshold 1 day ahead. Five-day 10-day predictions start end season also addressed with nonparametric technique combining analysis method temperature sum. Our applied three most polluted regions in Europe, namely Lyon (Rhone Valley, France), Legnano (Po River Plain, Italy) Szeged (Great Hungary). For 1-day prediction both exceedance, order these cities from smallest largest errors was Legnano, Lyon, Szeged, respectively. The important predictor for each location previous days. second main precipitation Szeged. Wind speed should be considered at exceedances Prediction capabilities compared annual cycles decreased west east. lowest 5- predictions, while 5-day predictions.