Atmospheric urban pollution: applications of an artificial neural network (ANN) to the city of Perugia

Viotti, Paolo; Liuti, G.; Genova, P Di

doi:10.1016/s0304-3800(01)00434-3

Cited by 141 publications

(74 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The selected input variables and their aggregation are presented in Table 1. In principle, it might be surprising to use a linear approach, i.e., cross-correlation analysis, in order to select the inputs of non-linear models; nevertheless, such a procedure leads generally to satisfactory outcomes and constitutes a de facto standard for this kind of studies (see, for instance, Viotti et al, 2002;Nunnari et al, 1998;Ziomas et al, 1995;Balaguer Ballester et al, 2002). The average goodness of the prediction is firstly evaluated by a series of indicators, such as the true/predicted correlation ρ, the mean absolute error MAE = (1/D)( |y(t) −ŷ(t)|), the mean bias error MBE = (1/D)( y(t) −ŷ(t)), and the index of agreement d = 1 − ( (y(t) −ŷ(t)) 2 / (|ŷ(t) − y(t)| − |y(t) −ȳ (t)|)).…”

Section: Results: Ozonementioning

confidence: 99%

“…The neural network approach proved to be viable also for ozone forecasting, outperforming alternative techniques in different case studies (Prybutok et al, 2000;Balaguer Ballester et al, 2002;Nunnari et al, 1998;Viotti et al, 2002). A remarkable intercomparison of statistical approaches -involving 15 different statistical techniques, 10 different sites across Europe and different forecast horizons -has been carried out (Schlink et al, 2003) in the context of the AP-PETISE project.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Corani

2005

Ecological Modelling

221

View full text Add to dashboard Cite

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.

show abstract

Section: Results: Ozonementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Corani

2005

Ecological Modelling

221

View full text Add to dashboard Cite

show abstract

“…ANNs are parallel-distributed systems made of many interconnected non-linear processing elements (PEs), called neurons (Hecht-Nielsen, 1991). 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;.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

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

2014

Global NEST Journal

View full text Add to dashboard Cite

In recent decades, there has been an increasing interest in the prognosis of maximum surface ozone concentrations due to the adverse effects on human health, animal population, agricultural productivity and forestry. The present study deals with the development and application of Artificial Neural Network (ANN) models in predicting the maximum daily surface ozone concentration in several locations within the greater Athens area (GAA), 24-hours in advance. Meteorological and air pollution data during the period 2001 to 2005 were provided by the network of the Hellenic Ministry of the Environment, Energy and Climate Change. Hourly values of barometric pressure and total solar irradiance for the same period have been recorded by the National Observatory of Athens. A training data set for the ANN prognostic model was generated by employing the superposed epoch analysis.The evaluation of the performance of the developed model, using appropriate statistical indices, clearly indicates that the risk of surface ozone values exceeding the European Union (EU) threshold for human health protection can be successfully predicted. This suggests that the proposed ANN model can be used to issue warnings for the general public and especially certain sensitive groups of the population.

show abstract

“…Models are used to generally assess particle concentration in a workplace environment under different meteorological conditions and its outputs are evaluated against the requirements of air quality regulations (Vardoulaki et al 2003;Viotti et al 2002;Cohn et al 2001). Majority of the models for estimation of the concentration of PM in a workplace environment are of empirical in nature where statistical approaches have been used to develop the model (Lal and Tripathy 2012;Vardoulaki et al 2003).…”

Section: Introductionmentioning

confidence: 99%

“…[PDF] 2002), soil analysis (Juang and Chen 1999), water treatment application (Baxter et al 2002), traffic and vehicular pollution (Nagendra and Khare 2004) and PM concentration prediction from the different sources in the opencast mines (Lal and Tripathy 2012). Earlier studies reported that ANN based air quality models give better results than other statistical models Lu et al 2003;Viotti et al 2002). The advantages of ANN model over statistical model are as follows: (i) it do not require detailed physical models, (ii) it is more compact than large experiment data, (iii) it requires few training points to accurately model the standards, (iv) it can be trained with only a few experiments data, and (v) it can be much more accurate than statistical models, when limited experimental data are available.…”

Section: Introductionmentioning

confidence: 99%

Prediction of particulate matter concentration profile in an opencast copper mine in India using an artificial neural network model

Patra

Gautam

Majumdar

et al. 2015

Air Qual Atmos Health

View full text Add to dashboard Cite

Springer Science+Business Media Dordrecht Particulate matter (PM) is a major pollutant in and around opencast mine areas. The problem of degradation of air quality due to opencast mine is more severe than those in underground mine. Prediction of dust concentration must be known to implement control strategies and techniques to control air quality degradation in the workplace environment. Limited studies have reported the dispersion profile and travel time of PM between the benches inside the mine. In this paper, PM concentration has been measured and modeled in Malanjkhand Copper Project (MCP), which is one of the deepest opencast copper mines in India. Meteorological parameters (wind speed, temperature, relative humidity) and PM concentration in seven size ranges (i.e., PM0.23–0.3, PM0.3–0.4, PM0.4–0.5, PM0.5–0.65, PM0.65–0.8, PM0.8–1, and PM1–1.6) have been measured for 8 days. The results of the field study provide an understanding of the dispersion of the PM generated due to mining activities. This research work presents an approach to assess the exposure of enhanced level of PM concentration on mine workers and its variation with depth. The correlations study shows that concentration of PM during its travel from source to surface is associated with depth. Empirical equations are developed to represent relationships between concentrations of PM and depth. Artificial neural network (ANN) model showing the relationship between PM concentration and meteorological parameters has been developed. The performance of the ANN model is evaluated in terms of the correlation coefficient between the real and the forecasted data. The results show strong agreement between the experimental data and the modeled output. The findings of this work are important in understanding fine PM variation inside the mine at the workplace and the associated exposure of mine workers

show abstract

Atmospheric urban pollution: applications of an artificial neural network (ANN) to the city of Perugia

Cited by 141 publications

References 5 publications

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

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

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

Prediction of particulate matter concentration profile in an opencast copper mine in India using an artificial neural network model

Contact Info

Product

Resources

About