Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki

Vlachogianni, A.; Kassomenos, Pavlos; Karppinen, Ari; Karakitsios, Spyros; Kukkonen, Jaakko

doi:10.1016/j.scitotenv.2010.12.040

Cited by 201 publications

(100 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At the urban traffic areas, there was an intensive seasonal variability, with higher concentrations of PM 10 , CO 8hr , O 3-1hr , NO 2 , and SO 2 during the winter months. This finding is similar to that of previous studies (Tsai et al, 2008;Juneng et al, 2009;Azmi et al, 2010;Rose et al, 2011;Vlachogianni et al, 2011).…”

Section: Seasonal Variationssupporting

confidence: 93%

“…Note that during the dry season, a weak influence from the highpressure ridge could be felt in BKK, which might reduce pollutant dispersion and cause a lack of rain scavenging (Kim Oanh et al, 2006;Chuersuwan et al, 2008). This pollutant variation was associated with the seasonal variation of the relevant meteorological dispersion, similar to the more common occurrence of stable and extremely stable low wind speed situations during the winter period (Vlachogianni et al, 2011). The O 3-1hr concentrations had a different seasonal pattern from the PM 10 , CO 8hr , NO 2 , and SO 2 concentrations.…”

Section: Seasonal Variationsmentioning

confidence: 98%

See 1 more Smart Citation

Temporal and Spatial Variations in Ambient Air Quality during 1996-2009 in Bangkok, Thailand

Watcharavitoon

Chio

Chan

2013

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

The severe air pollution in Bangkok (BKK) is an important issue in Thailand. The Bangkok air quality and meteorological data used in this study were collected by the Pollution Control Department of the Ministry of Natural Resources and Environment, Thailand, during 1996-2009. Measurements of hourly air quality and meteorological data were derived from 10 residential and seven roadside sites. Pearson's chi-square cross tabulation statistics show that the 24-hour mean PM 10 concentrations at both roadside and residential sites were to be significantly higher than the Thai National ambient air quality standards (NAAQS) and World Health Organization (WHO) guidelines. The daily 1-hour maximum O 3 (O 3-1hr ) concentration was higher than the Thai NAAQS at both sites. However, the concentrations of 8-hour time-weighting average of CO (CO 8hr ) were lower than the Thai NAAQS at both sites. The 24-hour average SO 2 concentration and the daily 1-hour mean concentration of NO 2 were higher than the WHO guidelines, but complied with the Thai NAAQS at both sites. A stepwise multiple linear regression model was used to analyze the significant factors affecting PM 10 , CO 8hr , O 3-1hr , NO 2 , and SO 2 levels at both sites, and the results showed a decreased association with meteorological parameters and an increased association with the area studied and seasons. In contrast, O 3-1hr levels exhibited a decreased association with the area studied. This study found that traffic emissions are the major factor causing the spatial variation in air pollutants in BKK, Thailand, while the meteorological parameters might be the main factors that affect the temporal variations. Our findings show the heterogeneously spatiotemporal characteristics of air pollution in BKK, and can be used to help mitigate this problem.

show abstract

Section: Seasonal Variationssupporting

confidence: 93%

Section: Seasonal Variationsmentioning

confidence: 98%

Temporal and Spatial Variations in Ambient Air Quality during 1996-2009 in Bangkok, Thailand

Watcharavitoon

Chio

Chan

2013

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

show abstract

“…and physical (emissions) parameters (e.g. McCollister and Wilson, 1975;Cobourn, 2007;Vlachogianni et al, 2011). The next step in evolution of RT-AQF systems was the use of sophisticated chemical transport models that represent all major processes (meteorological and chemical) that lead to the formation and accumulation of air pollutants.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the high resolution WRF-Chem (v3.4.1) air quality forecast and its comparison with statistical ozone predictions

et al. 2015

View full text Add to dashboard Cite

Abstract. An integrated modelling system based on the regional online coupled meteorology-atmospheric chemistry WRF-Chem model configured with two nested domains with horizontal resolutions of 11.1 and 3.7 km has been applied for numerical weather prediction and for air quality forecasts in Slovenia. In the study, an evaluation of the air quality forecasting system has been performed for summer 2013. In the case of ozone (O 3 ) daily maxima, the first-and second-day model predictions have been also compared to the operational statistical O 3 forecast and to the persistence. Results of discrete and categorical evaluations show that the WRFChem-based forecasting system is able to produce reliable forecasts which, depending on monitoring site and the evaluation measure applied, can outperform the statistical model. For example, the correlation coefficient shows the highest skill for WRF-Chem model O 3 predictions, confirming the significance of the non-linear processes taken into account in an online coupled Eulerian model. For some stations and areas biases were relatively high due to highly complex terrain and unresolved local meteorological and emission dynamics, which contributed to somewhat lower WRF-Chem skill obtained in categorical model evaluations. Applying a bias correction could further improve WRF-Chem model forecasting skill in these cases.

show abstract

“…More advanced techniques such as neural networks, Multi-Layer Perceptron and the support vector regression learning methods have also been used for forecasting air quality parameters (Kassomenos et al, 2006;Juhos et al, 2009;Paschalidou et al, 2011;Vlachogianni et al, 2011;Voukantsis et al, 2011;Kassomenos et al, 2013). However, methods of Computational Intelligence (CI) have only been scarcely applied in airborne pollen related studies.…”

Section: Introductionmentioning

confidence: 99%

Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe

Csépe

Makra

Voukantsis

et al. 2014

Science of The Total Environment

View full text Add to dashboard Cite

• For Szeged, MLP and tree-based models, while for Lyon only MLP performs well for predicting pollen concentration.• When predicting alarm levels, the performance of MLP is the best for both cities.• When forecasting high pollen episodes, the more complex CI methods prove better for both cities.• The selection of the optimal method depends on climate, as a function of geographical location and relief. a b s t r a c t a r t i c l e i n f o Forecasting ragweed pollen concentration is a useful tool for sensitive people in order to prepare in time for high pollen episodes. The aim of the study is to use methods of Computational Intelligence (CI) (Multi-Layer Perceptron, M5P, REPTree, DecisionStump and MLPRegressor) for predicting daily values of Ambrosia pollen concentrations and alarm levels for 1-7 days ahead for Szeged (Hungary) and Lyon (France), respectively. Ten-year daily mean ragweed pollen data (within 1997-2006) are considered for both cities. 10 input variables are used in the models including pollen level or alarm level on the given day, furthermore the serial number of the given day of the year within the pollen season and altogether 8 meteorological variables. The study has novelties as (1) daily alarm thresholds are firstly predicted in the aerobiological literature; (2) data-driven modelling methods including neural networks have never been used in forecasting daily Ambrosia pollen concentration; (3) algorithm J48 has never been used in palynological forecasts; (4) we apply a rarely used technique, namely factor analysis with special transformation, to detect the importance of the influencing variables in defining the pollen levels for 1-7 days ahead. When predicting pollen concentrations, for Szeged Multi-Layer Perceptron models deliver similar results with tree-based models 1 and 2 days ahead; while for Lyon only Multi-Layer Perceptron provides acceptable result. When predicting alarm levels, the performance of Multi-Layer Perceptron is the best for both cities. It is presented that the selection of the optimal method depends on climate, as a function of geographical location and relief. The results show that the more complex CI methods perform well, and their performance is case-specific for ≥2 days forecasting horizon. A determination coefficient of 0.98 (Ambrosia, Szeged, one day and two days ahead) using Multi-Layer Perceptron ranks this model the best one in the literature.

show abstract

Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki

Cited by 201 publications

References 35 publications

Temporal and Spatial Variations in Ambient Air Quality during 1996-2009 in Bangkok, Thailand

Temporal and Spatial Variations in Ambient Air Quality during 1996-2009 in Bangkok, Thailand

Evaluation of the high resolution WRF-Chem (v3.4.1) air quality forecast and its comparison with statistical ozone predictions

Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe

Contact Info

Product

Resources

About