2010
DOI: 10.1504/ijep.2010.031752
|View full text |Cite
|
Sign up to set email alerts
|

A neural network-based approach for the prediction of urban SO<SUB align=right>2 concentrations in the Istanbul metropolitan area

Abstract: A three-layer Artificial Neural Network (ANN) model was developed to forecast air pollution levels. The subsequent SO 2 concentration (24-hour averaged) being the output parameter of this study was estimated by seven input parameters such as preceding SO 2 concentrations (24-hour averaged), average daily temperature, sea-level pressure, relative humidity, cloudiness, average daily wind speed and daily dominant wind direction. After Backpropagation training combined with Principal Component Analysis (PCA), the … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

3
21
0
1

Year Published

2010
2010
2018
2018

Publication Types

Select...
5
3

Relationship

4
4

Authors

Journals

citations
Cited by 33 publications
(25 citation statements)
references
References 27 publications
3
21
0
1
Order By: Relevance
“…Finally, in order to describe the overall performance of the proposed models, results were assessed with various descriptive statistics such as coefficient of determination (R 2 ), correlation coefficient (R), mean-absolute error (MAE), root mean-square error (RMSE), systematic and unsystematic RMSE (RMSE S and RMSE U , respectively), index of agreement (IA), mean bias (MB), fractional bias (FB), the factor of two (FA2), fractional variance (FV), intercept (a) and slope (b) of the adjusted line between observed and predicted values, and proportion of systematic error (PSE). Detailed definitions and calculations of these estimators can be found in several studies [19,26,[81][82][83][84]. The obtained results are summarized in Table 5.…”
Section: Tablementioning
confidence: 99%
See 1 more Smart Citation
“…Finally, in order to describe the overall performance of the proposed models, results were assessed with various descriptive statistics such as coefficient of determination (R 2 ), correlation coefficient (R), mean-absolute error (MAE), root mean-square error (RMSE), systematic and unsystematic RMSE (RMSE S and RMSE U , respectively), index of agreement (IA), mean bias (MB), fractional bias (FB), the factor of two (FA2), fractional variance (FV), intercept (a) and slope (b) of the adjusted line between observed and predicted values, and proportion of systematic error (PSE). Detailed definitions and calculations of these estimators can be found in several studies [19,26,[81][82][83][84]. The obtained results are summarized in Table 5.…”
Section: Tablementioning
confidence: 99%
“…Because of their speed and capability of learning, robustness, predictive capabilities and non-linear characteristics, several artificial intelligence-based modeling techniques, such as artificial neural networks [23][24][25][26], fuzzy-logic [27,28], adaptive neuro-fuzzy inference systems [19,29], have recently been conducted in the modeling of various real-life processes in environmental engineering field. Among these methods, fuzzy-logic methodology has been successfully applied in a variety of ecological and environmental applications, ranging from mapping to modeling, evaluation and prediction tasks [30].…”
Section: Introductionmentioning
confidence: 99%
“…Considering the complicated inter-relationships among a number of system factors in the dispersion and transport of atmospheric pollutants under several meteorological conditions, mathematical models have become essential tools to develop early-warning and control strategies, as well as to investigate future emission scenarios. Although statistical models may be able to establish a relationship between the input and the output variables without detailing the causes and effects in the formation of pollutants, however, they are not capable of capturing the inherent non-linear nature of the problem and forecasting short-term pollution levels (Agirre-Basurko et al, 2006;Barai et al, 2007;Akkoyunlu et al, 2010). Since the number of meteorological and pollution parameters implies highdimensional input space and high computational capacity, it is believed that artificial intelligence-based techniques may provide a good alternative to traditional techniques due to their speed, robustness and non-linear characteristics (Yetilmezsoy and Sapci-Zengin, 2009;Akkoyunlu et al, 2010).…”
Section: Introductionmentioning
confidence: 99%
“…Because of their non-parametric regression capabilities, generalization properties and easiness of working with high-dimensional data, several artificial intelligence-based methods, such as artificial neural networks (Abdul-Wahab and Al-Alawi, 2002;Yetilmezsoy, 2006;Yetilmezsoy and Saral, 2007;Akkoyunlu et al, 2010) and fuzzy-logic/neurofuzzy (Nunnari et al, 2004;Yildirim and Bayramoglu, 2006;Carnevale et al, 2009;Noori et al, 2010) methodology, have recently been utilized in the modeling of various reallife problems in air pollution field. There have also been other specific studies reporting the advantages and adaptability properties of artificial intelligence-based models for the prediction of daily and/or hourly particulate matter (PM 2.5 and PM 10 ) emissions in many urban and residential areas (Chaloulakou et al, 2003;Chelani, 2005;Grivas and Chaloulakou, 2006;Karaca et al, 2009).…”
Section: Introductionmentioning
confidence: 99%
“…Fuzzy logic, developed by Zadeh, has some advantages over mathematical models where complicated equations are used [33]. Artificial intelligence-based tools are a suitable substitute to conventional methods such as curve fitting due to their speed, robustness, and nonlinear characteristics [34]. Due to its high precision ability and flexibility in use, fuzzy logic has been applied in many of the environmental engineering problems from air pollution to water treatment systems.…”
Section: Introductionmentioning
confidence: 99%