Comparing Neural Networks and Regression Models for Ozone Forecasting

Comrie, Andrew C.

doi:10.1080/10473289.1997.10463925

Cited by 373 publications

(234 citation statements)

References 3 publications

Supporting

Mentioning

212

Contrasting

Unclassified

Order By: Relevance

“…Ozone concentrations in the Southwest are less dependent on the occurrence of particular synoptic weather patterns than other regions such as the eastern United States (Comrie, 1997). Previous studies (Wise and Comrie, 2005a,b) found that temperature and mixing height have the greatest influence on ozone conditions in the Southwest, while moisture levels (particularly relative humidity) are the strongest predictors of PM concentrations.…”

Section: Climate Controls On Ozone and Pm In The Southwestmentioning

confidence: 98%

Climate‐based sensitivity of air quality to climate change scenarios for the southwestern United States

Wise

2008

Intl Journal of Climatology

View full text Add to dashboard Cite

ABSTRACT:The need to understand future trends in air quality is an issue that is frequently raised by air quality planners and managers. The potential for extreme events is of particular interest, but forecasts are difficult using traditional methods and further complicated by predictions of future climate change. This study aims to address this research need through a climate-based sensitivity study of ground-level ozone and particulate matter (PM) in the U.S. Southwest. Extreme value methods were used to examine ozone and PM in Tucson, Arizona, over the time period 1990-2001. A Statistical DownScaling Model (SDSM) was employed to build regression-based models between gridded meteorological data and point time series of ozone and PM. Following model calibration and verification, future climate-based ozone and PM scenarios were created for 2002-2050 and 2051-2099. Daily output of projected ozone and PM were then subjected to extreme value methods in order to estimate climate-based changes in ozone and PM extremes over the next century. Results indicate that monthly mean and extreme ozone values are sensitive to predicted increases in temperature, particularly in the summer months. PM results are less certain but suggest that PM may be sensitive to changing moisture conditions.

show abstract

Section: Climate Controls On Ozone and Pm In The Southwestmentioning

confidence: 98%

Climate‐based sensitivity of air quality to climate change scenarios for the southwestern United States

Wise

2008

Intl Journal of Climatology

View full text Add to dashboard Cite

show abstract

“…The previous studies have shown that the performance of ANNs could be improved by including persistence information as an input [14,20,36]. Therefore, current day's ozone concentrations (daily average and maximum 1-h concentrations) were used as input parameters.…”

Section: Resultsmentioning

confidence: 99%

“…While the performance of AR-NN model was better compared with the ordinary autoregressive model of same order [12], ARIMA model in the form of ARIMA (0, 2, 2) had maximum prediction capacity among the three ARIMA and 11 AR-ANN models [13]. When only average daily meteorological data were used as input, Comrie [14] and Spellman [15] reported that the difference between the performances of neural network technique and regression model was not remarkable. In recent studies, ANN technique has been applied to predict tropospheric ozone levels in several European cities: five locations in United Kingdom (Central London, Harwell, Birmingham, Leeds, and Strath Vaich [15], and Bristol, Edinburgh, Eskdalemuir, Leeds, and Southampton [16]), Valencia, Spain [17,18], Oporto, Portugal [19], and Orleans, France [20].…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network Prediction of Tropospheric Ozone Concentrations in Istanbul, Turkey

İnal

2010

CLEAN Soil Air Water

View full text Add to dashboard Cite

Artificial Neural Network Prediction of Tropospheric Ozone Concentrations in Istanbul, TurkeyTropospheric (ground-level) ozone has adverse effects on human health and environment. In this study, next day's maximum 1-h average ozone concentrations in Istanbul were predicted using multi-layer perceptron (MLP) type artificial neural networks (ANNs). Nine meteorological parameters and nine air pollutant concentrations were utilized as inputs. The total 578 datasets were divided into three groups: training, crossvalidation, and testing. When all the 18 inputs were used, the best performance was obtained with a network containing one hidden layer with 24 neurons. The transfer function was hyperbolic tangent. The correlation coefficient (R), mean absolute error (MAE), root mean squared error (RMSE), and index of agreement or Willmott's Index (d 2 ) for the testing data were 0.90, 8.78 mg/m 3 , 11.15 mg/m 3 , and 0.95, respectively. Sensitivity analysis has indicated that the persistence information (current day's maximum and average ozone concentrations), NO concentration, average temperature, PM 10 , maximum temperature, sunshine time, wind direction, and solar radiation were the most important input parameters. The values of R, MAE, RMSE, and d 2 did not change considerably for the MLP model using only these nine inputs. The performances of the MLP models were compared with those of regression models (i.e., multiple linear regression and multiple non-linear regression). It has been found that there was no significant difference between the ANN and regression modeling techniques for the forecasting of ozone concentrations in Istanbul. IntroductionOzone (O 3 ) is a secondary pollutant and formed in the lower atmosphere (troposphere) by the complex reactions of nitrogen oxides (NO x ) and volatile organic compounds (VOCs) in the presence of solar radiation. Ozone formation in the troposphere is a rapid photochemical cycle and a non-linear process depending on the concentrations of precursors, meteorological parameters, and the sunlight intensity and spectral distribution [1,2]. Briefly, it involves the photolysis of nitrogen dioxide (NO 2 ) by solar radiation to form nitric oxide (NO) and a ground-state oxygen atom (O).The major reaction forming O 3 in the troposphere includes the reaction of oxygen atom with oxygen molecule (O 2 ). Collision of recently formed O 3 with a third body (i.e., a molecule from the surrounding air) removes the excess energy of ozone and allows it to stabilize.O 3 is removed by the reaction with NO to reform NO 2 ;However, reactions between NO and reactive radical species that are formed by the oxidation of reactive VOCs can also oxidize NO to NO 2 without the involvement of ozone, NO ÀÀÀÀÀÀÀ!

show abstract

“…The population, especially in large cities and in suburban zones which suffer from summer smog, wants to be warned of high pollutant concentrations in advance. Statistical ozone modelling and more particularly regression models have been widely studied, see Comrie (1997), Gardner and Dorling (1998). Generally, linear models do not seem to capture all the complexity of this phenomenon.…”

Section: Application To Real Time Series: Pollution Of Ozonementioning

confidence: 99%

Estimation and Test for Multi-Dimensional Regression Models

Rynkiewicz

2007

Communications in Statistics - Theory and Methods

View full text Add to dashboard Cite

This work is concerned with the estimation of multidimensional regression and the asymptotic behaviour of the test involved in selecting models. The main problem with such models is that we need to know the covariance matrix of the noise to get an optimal estimator. We show in this paper that if we choose to minimise the logarithm of the determinant of the empirical error covariance matrix, then we get an asymptotically optimal estimator. Moreover, under suitable assumptions, we show that this cost function leads to a very simple asymptotic law for testing the number of parameters of an identifiable and regular regression model. Numerical experiments confirm the theoretical results.

show abstract

Comparing Neural Networks and Regression Models for Ozone Forecasting

Cited by 373 publications

References 3 publications

Climate‐based sensitivity of air quality to climate change scenarios for the southwestern United States

Climate‐based sensitivity of air quality to climate change scenarios for the southwestern United States

Artificial Neural Network Prediction of Tropospheric Ozone Concentrations in Istanbul, Turkey

Estimation and Test for Multi-Dimensional Regression Models

Contact Info

Product

Resources

About