Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning

Abstract

Ozone and PM 10 constitute the major concern for air quality of Milan. This paper addresses the problem of the prediction of such two pollutants, using to this end several statistical approaches. In particular, feed-forward neural networks (FFNNs), currently recognized as state-of-the-art approach for statistical prediction of air quality, are compared with two alternative approaches derived from machine learning: pruned neural networks (PNNs) and lazy learning (LL). PNNs constitute a parameterparsimonious approach, based on the removal of redundant parameters from fully connected neural networks; LL, on the other hand, is a local linear prediction algorithm, which performs a local learning procedure each time a prediction is required. All the three approaches are tested in the prediction of ozone and PM 10 ; predictors are trained to return at 9 a.m. the concentration estimated for the current day.No strong differences are found between the forecast accuracies of the different models; nevertheless, LL provides the best performances on indicators related to average goodness of the prediction (correlation, mean absolute error, etc.), while PNNs are superior to the other approaches in detecting of the exceedances of alarm and attention thresholds. In some cases, datadeseasonalization is found to improve the prediction accuracy of the models.Finally, some striking features of lazy learning deserve consideration: the LL predictor can be quickly designed, and, thanks to the simplicity of the local linear regressors, it both gets rid of overfitting problems and can be readily interpreted; moreover, it can be also easily kept up-to-date.

Prognosis of maximum daily surface ozone concentration within the greater Athens urban area, Greece

“…A renewal of scientific interest has grown exponentially since the last decade, mainly due to the availability of appropriate hardware that has made them convenient for fast data analysis and information processing (Viotti et al, 2002). Many ANN models have been developed in the last fifteen years for very different environmental purposes (Nunnari et al, 1998;Prybutok et al, 2000;Heymans and Baird, 2000;Karul et al, 2000;Antonic et al, 2001;Kolehmainen et al, 2001;Balaguer Ballester et al, 2002;Schlink et al, 2003;Corani, 2005;Slini et al, 2006;Dutot et al, 2007;Papanastasiou et al, 2007;Moustris et al, 2010a;.…”

Hybridization of Air Quality Forecasting Models Using Machine Learning and Clustering: An Original Approach to Detect Pollutant Peaks

“…Some authors use boosting, that is to say increase the frequency of such episodes in the training set (Kukkonen et al, 2003;Paschalidou et al, 2010), but it can lead to overfitting. Another way to improve the precision for high concentration is to build a forecasting model with the time series of maximum daily values of the pollutant as target (Corani, 2005;Lu et al, 2006;Perez, 2012); but working with daily values does not bring information on air quality evolution during the day, which is useful for operational use.…”

Variable Selection Based on Statistical Learning Approaches to Improve PM10 Concentration Forecasting

“…Moreover, Chaloulakou et al (2003) and Grivas and Chaloulakou (2006) compared the performance of neural networks and multiple regression model to forecast the daily average of PM10 concentration. Corani (2005) used local polynomial based nonparametric approach to estimate a nonlinear regression model in Milan where the PM10 pollution is important. Hoi et al (2009) proposed a time varying autoregressive model with exogenous input based on a Kalman filter in order to predict daily PM10 concentration.…”