ESANN2006 - A Cyclostationary Neural Network model for the prediction of the NO2 concentration
Download as PPT, PDF0 likes369 views
This document discusses the development of a cyclostationary neural network model for predicting nitrogen dioxide (NO2) concentrations, which are crucial for managing air quality in urban areas affected by traffic emissions. The model utilizes past NO and NO2 data in a cyclostationary manner to forecast future concentrations, aiming to provide early warnings independent of external data. It summarizes the experimental setup using real-time data from air pollution monitoring stations and outlines future work on enhancing the model's application across various datasets.
ESANN2006 - A Cyclostationary Neural Network model for the prediction of the NO2 concentration
- 1. A Cyclostationary Neural Network Model for the Prediction of the NO 2 Concentration Monica Bianchini, Ernesto Di Iorio, Marco Maggini, Chiara Mocenni, Augusto Pucci Dipartimento di Ingegneria dell’Informazione Via Roma 56, 53100 Siena (ITALY)
- 2. Air Pollution Problem Nitrogen oxide (NO x = NO + NO 2 ) emissions are among the most important factors affecting the air quality in urban areas Traffic is the main problem on a local urban scale Modeling efforts to predict and control the NO x concentrations Development of tools for pollution management
- 3. Project Goals Build an efficient neural based model for the prediction of the NO 2 concentration First prediction approximation for an early warning Independence from exogenous data Modeling the NO 2 time series only based on the past concentrations of NO and NO 2
- 4. The Cyclostationary Neural Network Model Correlation of past NO and current NO 2 (daily periodicity) NO 2 (t) follows a cyclostationary dynamics (period T = 24) CNN model composed by 24 MLP blocks one for each random variable of the cyclostationary process where T = 24 and f k with k = (t mod T) + 1 , represents the k–th approximation function realized by the k–th MLP block
- 6. Experimental Setup Data gathered by ARPA Lombardia (northern Italy) ARPA supplies a real–time air pollution monitoring system composed by mobile and fixed stations Dataset made up by NO and NO 2 concentrations detected hourly by the station number 649 (Brescia–Broletto) Performance measures: mean absolute error and mean square error
- 7. Experimental results – err 2 months
- 8. Experimental results – err 12 months
- 9. Experimental results – mse 2 months
- 10. Future Works CNN hardware implementation on NO x sensors Management of multiple data from different sensors Testing on other urban area datasets Testing on wider datasets