1997
DOI: 10.1080/10473289.1997.10463925
|View full text |Cite
|
Sign up to set email alerts
|

Comparing Neural Networks and Regression Models for Ozone Forecasting

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

8
212
0
14

Year Published

2002
2002
2017
2017

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 373 publications
(234 citation statements)
references
References 3 publications
8
212
0
14
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%
“…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%
“…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%
“…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%