Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone

Al-Alawi, S.M.; Abdul‐Wahab, Sabah A.; Bakheit, Charles S.

doi:10.1016/j.envsoft.2006.08.007

Cited by 172 publications

(83 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Quartz sand (SiO 2 , 20-50 µm), tetrabutyl orthotitanate (TBOT) (Ti(OBu) 4 , 97%), HNO 3 (nitric acid, 70 wt.%), absolute ethanol (C 2 H 5 OH, 99%) and NaOH (sodium hydroxide, 1 M)…”

Section: Raw Materialsmentioning

confidence: 99%

“…NOx gases are not only toxic in their own right but they contribute to the formation of other toxic atmospheric pollutants, such as ground level ozone, PAN (peroxyacytyl nitrate), etc. [1][2][3] . Consequently, EU and EPA guidelines for maximum atmospheric NO and NO 2 concentrations have been set but these are regularly exceeded in urban centers because the largest contribution to NOx gases in the urban atmosphere comes from automotive emissions [4][5][6][7] .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO₂: Basis for Engineering Nitrate Selectivity?

Yang

Hakki

Wang

et al. 2017

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

Abstract:The nitrate selectivity of TiO 2 has important consequences for its efficiency as a NOx depollution photocatalyst. Most emphasis is typically given to photocatalyst activity, a measure of the rate at which NOx concentrations are reduced, but a reduction in NOx concentration (mainly NO + NO 2 ) is not necessarily a reduction in atmospheric NO 2 concentration because the catalytic process itself generates NO 2 . With NO 2 being considerably more toxic than NO, more emphasis on nitrate selectivity, a measure of the NOx conversion to nitrate, and how to maximise it, should be given in engineering photocatalytic systems for improved urban air quality. This study, on the importance of adsorbed water in the photocatalytic oxidation of NOx, has identified important correlations which differentiate the role that water plays in the oxidation of NO and NO 2 . This observation is significant and offers insights into controlling nitrate selectivity on TiO 2 and the potential for increased effectiveness in environmental photocatalyst applications.

show abstract

“…Quartz sand (SiO 2 , 20-50 µm), tetrabutyl orthotitanate (TBOT) (Ti(OBu) 4 , 97%), HNO 3 (nitric acid, 70 wt.%), absolute ethanol (C 2 H 5 OH, 99%) and NaOH (sodium hydroxide, 1 M)…”

Section: Raw Materialsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO₂: Basis for Engineering Nitrate Selectivity?

Yang

Hakki

Wang

et al. 2017

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

show abstract

“…Observing the performance for other pollutants, we found that the performance of ICR was the worst than PCR and GLS model. Specifically for O 3 prediction, we did not obtain comparable performance as those measured by [8] showing that the use of PCR alone yielded R 2 of 0.965, assuming we care less of interval concentration of O 3 they used. However, if we compare the performance of ICR and PCR in the training set (internal validation), ICR performed better than PCR for O 3 and PM 10 on two stations.…”

Section: Resultsmentioning

confidence: 57%

“…Moreover, in a regression analysis, the correlation between independent variables (multicollinearity) may pose a serious difficulty in the interpretation of which predictors are the most influential to the response variables [8]. One way to remove such multicollinearity is using component analysis method, in this case widely used a Principal Component Analysis (PCA), and the newly emerged one Independent Component Analysis (ICA).…”

Section: Introductionmentioning

confidence: 99%

“…Even though these two methods have their own approach, the goal is similar is to build components that are statistically independent with each other. In regression analysis, this is particularly very useful and become good input as predictors in a regression model since they optimize spatial patterns and remove complexity due to multicollinearity [8], [9]. ICR and PCR have been widely used in particular for plant study [9], dam deformation study [10], air pollutants in subway [11], air quality management [2], [3], [12], and O 3 prediction [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction Model of Air Pollutant Levels Using Linear Model with Component Analysis

Syafei¹,

Fujiwara²,

Zhang³

2015

IJESD

View full text Add to dashboard Cite

Radial basis function neural networks based on projection pursuit approach and solvatochromic descriptors: single and full column prediction of gas chromatography retention behavior of polychlorinated biphenyls

Hassanzadeh

Ebrahimi

Kompany‐Zareh

et al. 2016

Journal of Chemometrics

View full text Add to dashboard Cite

The ultimate goal of projection methods is to search “interesting” projections in a low‐dimensional subspace that can uncover the natural structure of the data. The aim of this work is to compare the ability of projection pursuit (PP) and principal component analysis (PCA) in dimension reduction. For this purpose to be achieved, the scores of PP and PCA, by a different number of factors, were used as inputs of radial basis function (RBF) neural network. RBF neural network was used as a nonlinear regression method in a quantitative structure‐retention relationships study of 209 polychlorinated biphenyls (PCBs). The dependent variable was the high‐resolution gas chromatographic relative retention times of PCBs on 18 different stationary phases, and independent variables were solvatochromic solute descriptors. The results demonstrate that the dimension reduction ability of the PP is better than that of the PCA for both single and full column retention models.

show abstract

Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone

Cited by 172 publications

References 52 publications

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO₂: Basis for Engineering Nitrate Selectivity?

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO₂: Basis for Engineering Nitrate Selectivity?

Prediction Model of Air Pollutant Levels Using Linear Model with Component Analysis

Radial basis function neural networks based on projection pursuit approach and solvatochromic descriptors: single and full column prediction of gas chromatography retention behavior of polychlorinated biphenyls

Contact Info

Product

Resources

About

Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone

Cited by 172 publications

References 52 publications

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO2: Basis for Engineering Nitrate Selectivity?

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO2: Basis for Engineering Nitrate Selectivity?

Prediction Model of Air Pollutant Levels Using Linear Model with Component Analysis

Radial basis function neural networks based on projection pursuit approach and solvatochromic descriptors: single and full column prediction of gas chromatography retention behavior of polychlorinated biphenyls

Contact Info

Product

Resources

About

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO₂: Basis for Engineering Nitrate Selectivity?

Different Roles of Water in Photocatalytic DeNOx Mechanisms on TiO₂: Basis for Engineering Nitrate Selectivity?