Application of Artificial Neural Networks in the Prediction of PM10 Levels in the Winter Months: A Case Study in the Tricity Agglomeration, Poland

摘要: Poor urban air quality due to high concentrations of particulate matter (PM) remains a major public health problem worldwide. Therefore, research efforts are being made forecast ambient PM concentrations. In this study, artificial neural networks (ANNs) were employed generate models forecasting hourly PM10 1–6 h ahead, involving 3 measurement locations in the Tricity Agglomeration, Poland. Poland, majority concentration cases occurs winter coal combustion main energy carrier. For reason, present study covers only periods calendar (December, January, February) period 2002/2003–2016/2017. Inputs values and meteorological factors such as temperature, relative humidity, pressure, wind speed. The results network satisfactory coefficient determination (R2) for independent test set three sites ranged from 0.452 0.848. index agreement (IA) 0.693 0.957, fractional mean bias (FB) 0 or close root square error (RMSE) varied 8.80 23.56. It is concluded that ANNs have been proven be effective prediction pollution levels based on measured monitoring data.