Traffic congestion and ozone precursor emissions in Bilbao (Spain)

Ibarra-Berastegi, Gabriel; Madariaga, I.

doi:10.1065/espr2003.08.170

Cited by 14 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the five pollutants analyzed, predictions are made using all the types of NNs [4][5][6][7][8][9][10]. However, it was necessary to analyze the effect that the spatial variability of pollutants' emissions have on the different models used at each location.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of air pollution levels using neural networks: influence of spatial variability

Ibarra-Berastegi¹,

Ηλίας²,

Barona³

et al. 2008

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

This work focuses on the prediction of hourly levels up to 8 hours ahead for five pollutants (SO 2 , CO, NO 2 , NO and O 3 ) and six locations in the area of Bilbao (Spain). To that end, 216 models based on neural networks (NN) have been built. Spatial variability for the five pollutants has been assessed using Principal Components Analysis and different behaviour has been detected for the nonreactive pollutant (SO 2 ) and the rest (CO, NO 2 , NO and O 3 ). This can be explained by the very local effects involved in the photochemical reactions. The inputs used to feed the NN models intended to predict forthcoming levels of these five pollutants, include a baseline based on autocorrelation plus a linear or nonlinear combination of different meteorological and traffic variables. The nature of these combinations is different depending on the sensor thus showing the importance of the spatial variability to build the models. The number of hourly cases, due to gaps in data predictions, can have a possible range from 11% to 38% depending on the sensor. Depending on the pollutant, location and number of hours ahead the prediction is made, different types of models have been selected. The use of these models based on NNs can provide Bilbao's air pollution network originally designed for diagnosis purposes, with short-term, real time forecasting capabilities. The performance of these models at the different sensors in the area range from a maximum value of R 2 =0.88 for the prediction of NO 2 1 hour ahead, to a minimum value of R 2 =0.15 for the prediction of ozone 8 hours ahead. These boundaries and the limitation in which the number of cases that predictions are possible represent the maximum forecasting capability that Bilbao's network can provide in real-life operating conditions.

show abstract

Section: Resultsmentioning

confidence: 99%

“…For this study, historical hourly records of the above mentioned variables corresponding to years 2000 and 2001 were available [4][5][6][7]. Data of year 2000 were used to build the different groups of candidate prognostic models while data belonging to year 2001 were reserved to test and select the best model.…”

Section: Databasementioning

confidence: 99%

Prediction of air pollution levels using neural networks: influence of spatial variability

Ibarra-Berastegi¹,

Ηλίας²,

Barona³

et al. 2008

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

show abstract

“…ILBAO is located North-central Spain (Europe) and as many other urban environments in the world has air pollution problems, mainly due to photochemical smog [1,2].…”

Section: Introductionmentioning

confidence: 99%

Using neural networks for short-term prediction of air pollution levels

Ibarra-Berastegi

Sáenz

Ezcurra

et al. 2009

2009 International Conference on Advances in Computational Tools for Engineering Applications

Self Cite

View full text Add to dashboard Cite

The present paper focuses on the prediction of hourly levels up to 8 hours ahead for five pollutants (SO2, CO, NO2, NO and O3) and six locations in the area of Bilbao (Spain. To that end, 216 models based on neural networks (NN) have been built. The database used to fit the NN`s has been historical records of the traffic, meteorological and air pollution networks existing in the area corresponding to year 2000. Then, the models have been tested on data from the same networks but corresponding to year 2001. At a first stage, for each of the 216 cases, 100 models based on different types of neural networks have been built using data corresponding to year 2000. The final identification of the best model has been made under the criteria of simultaneously having at a 95% confidence level the best values of R 2 , d1, FA2 and RMSE when applied to data of year 2001. The number of hourly cases in which due to gaps in data predictions have been possible range from 11% to 38% depending on the sensor. Depending on the pollutant, location and number of hours ahead the prediction is made, different types of models have been selected. The use of these models based on NN's can provide Bilbao`s air pollution network originally designed for diagnosis purposes, with short-term, real time forecasting capabilities. The performance of these models at the different sensors in the area range from a maximum value of R 2 =0.88 for the prediction of NO2 1 hour ahead, to a minimum value of R 2 =0.15 for the prediction of ozone 8 hours ahead. These boundaries and the limitation in the number of cases that predictions are possible represent the maximum forecasting capability that Bilbao's network can provide in real-life operating conditions.

show abstract

“…Bilbao's network is not an exception regarding these general trends (Ibarra-Berastegi et al [1][2][3][4][5]). Since 1977, throughout the whole ZONE B (Fig.…”

Section: Introductionmentioning

confidence: 99%

Identification of redundant sensors in an air pollution network using cluster analysis and SOM

Ibarra-Berastegi¹,

Sáenz²,

Ezcurra³

et al. 2010

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

An air pollution network monitors -among others -the sulfur dioxide (SO 2 ) levels at 4 locations in Bilbao city (Spain) and surroundings. The main objective of this work was to develop a practical methodology to identify redundant sensors and evaluate the network's capability to correctly represent SO 2 fields throughout the whole area. The methodology is developed and tested at this particular location, but it is general enough to be useable at other places as well, since it is not tied neither to the particular geographical characteristics of the place nor to the phenomenology of the air quality over the area. To that purpose, the combination of two different techniques has been used: Self-Organizing Maps (SOM) and cluster analysis (CA). The results show that both techniques yield the same results, but the information obtained via SOM can be helpful not only for that purpose but also to throw light on the major mechanisms involved. This might be used in future network optimization stages. The main advantage of CA and SOM is that they provide readily interpretable results.

show abstract

Traffic congestion and ozone precursor emissions in Bilbao (Spain)

Cited by 14 publications

References 18 publications

Prediction of air pollution levels using neural networks: influence of spatial variability

Prediction of air pollution levels using neural networks: influence of spatial variability

Using neural networks for short-term prediction of air pollution levels

Identification of redundant sensors in an air pollution network using cluster analysis and SOM

Contact Info

Product

Resources

About