『Abstract
The problem of air pollution is a frequently recurring situation
and its management has social and economic considerable effects.
Given the interaction of the numerous factors involved in the
raising of the atmospheric pollution rates, it should be considered
that the relation between the intensity of emission produced by
the polluting source and the resulting pollution is not immediate.
The aim of this study was to realise and to compare two support
decision system (neural networks and multivariate regression model)
that, correlating the air quality data with the meteorological
information, are able to predict the critical pollution events.
The development of a back-propagation neural network is presented
to predict the daily PM10 concentration q,
2 and 3 days early. The measurements obtained by the territorial
monitoring stations are one of the primary data sources; the forecasting
of the major weather parameters available on the website and the
forecasting of the Saharan dust obtained by the “Centro Nacional
de Supercompactacion（後のoの頭に｀）” website, satellite
images and back trajectories analysis are used for the weather
input data. The results obtained with the neural network were
compared with those obtained by a multivariate linear regression
model for 1 and 2 days forecasting. The relative root mean square
error for both methods shows that the artificial neural networks
(ANN) gives more accurate results than the multivariate linear
regression model mostly for 1 day forecasting; moreover, the regression
model used, in spite of ANN, failed when it had to fit spiked
high values of PM10 concentration.
Keywords: PM10; Forecast; Neural network;
Multivariate linear regression 』
1. Introduction
2. Application of feedforward neural networks on automatic PM10 data
2.1. Feedforward neural networks
2.2. Input data
2.3. Training and optimisation of the network
3. Results and discussion
3.1. Comparison between the ANN and a radial basis function
network for 1 day forecasting
3.2. Comparison between the ANN and a multivariate linear regression
model
4. Conclusions
References