Double layer back propagation neural network based on restricted Boltzmann machines for forecasting daily particulate matter 2.5

• Date: 2017
• Main Authors: Fu, Minglei, Wang, Chen, Le, Zichun, Manko, Dmytro
• Format: Article
• Language: English
• Published: Інститут проблем реєстрації інформації НАН України 2017
• Subjects: Neural network; restricted Boltzmann machines; Particulate matter 25; Forecasting
• Online Access: http://drsp.ipri.kiev.ua/article/view/126541
• Journal Title: Data Recording, Storage & Processing

Particulate matter 2.5 (PM2.5) pollution is an actual problem in the modern world and forecasting of the daily concentration of PM25 is a challenging task for researchers. In this study, a novel neural network model that effec­tively forecasts daily PM2.5 in Hangzhou city was developed in the form of a restricted Boltzmann machines double layer back propagation neural net­work model (RBM-DL-BPNN). Air quality index, the air pollutants, e.g., particulate matter 10 (PM10), PM25, SO2, CO, NO2, O3, and meteorological parameters (temperature, dew point, humidity, pressure, wind speed, and precipitation) of Hangzhou city were used in this study to train and test three models: RBM-DL-BPNN, double layer back propagation neural network (DL-BPNN), and back propagation neural network (BPNN). The results of experiments and analyses performed indicate that RBM-DL-BPNN has a smaller mean absolute percent error (MAPE), smaller overall daily absolute percentage errors, and more results in terms of absolute percentage error within the range 0-50 % than DL-BPNN and BPNN.