This work presents a method of forecasting the level of PM10 with the use of artificial neural networks. Current level of particulate matter and meteorological data was taken into account in the construction of the model (checked the correlation of each variable and the future level of PM10), and unidirectional networks were used to implement it due to their ease of learning. Then, the configuration of the network (built on the basis of the developed model) was established, defining the number of layers and neurons, as well as the activation function. 4 methods of propagation (Back Propagation, Resilient Propagation, Manhattan Propagation and Scaled Conjugate Gradient) were applied in the network learning process to select the best method. The obtained results were then compared with real values and the complete network configuration (minimizing the forecast error) was determined. After completion of the learning process, the developed network was used to forecast the particulate matter levels in Gdansk.
Authors
- Arkadiusz Sarzyński link open in new tab ,
- prof dr. hab. inż. Cezary Orłowski
Additional information
- Category
- Aktywność konferencyjna
- Type
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language
- angielski
- Publication year
- 2014
