Performance of Multiple Linear Regression Model for Long-term PM10 Concentration Prediction Based on Gaseous and Meteorological Parameters

Ul-Saufie, Ahmad Zia; Yahaya, Ahmad Shukri; Ramli, NorAzam; Hamid, Haslinda Abdul

doi:10.3923/jas.2012.1488.1494

Cited by 35 publications

(43 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SO2 gas is generated from industrial processing activities as well as petrol fueled vehicles. While CO and NO2 gases are mainly released by motor vehicle and machinery that uses diesel fuel [13]. This may contribute to this positive correlation results.…”

Section: Correlation Analysismentioning

confidence: 93%

“…Apart from that, the gaseous pollutant which are formed as primary pollutant of SO2, NO2 and CO also reported to influence the PM10 concentrations distribution pattern [12]. Factory activities containing sulfur and petrol fueled vehicle motor emission are considered to be the major sources of SO2, meanwhile the NO2 and CO come from power plants and diesel fueled vehicle emission [13][14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The behavior of Particulate Matter (PM10) Concentrations at Industrial Sites in Malaysia

Raffee¹,

Rahmat²,

Hamid³

et al. 2019

IJIE

View full text Add to dashboard Cite

PM10 reportedly contributes about 0.8 million premature cases and 2.1 million deaths worldwide [6-7]. In Malaysia, the PM10 concentration is mostly influenced by industrial, power plants and transportation activities. While during haze events, the major regional source of PM10 is biomass burning during dry season from June to September each year [8-9]. Apart from emission sources, complex interactions in various processes such as emission itself, transport and transformation are the common factors that influence meteorological parameters in PM10

show abstract

Section: Correlation Analysismentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

The behavior of Particulate Matter (PM10) Concentrations at Industrial Sites in Malaysia

Raffee¹,

Rahmat²,

Hamid³

et al. 2019

IJIE

View full text Add to dashboard Cite

show abstract

“…Autocorrelation basically uncovers the capability of PM 10 concentration of current day to estimate the following day of PM 10 concentration. The test values can change in the vicinity of 0 and 4 with an estimation of 2 implying that the lingering is uncorrelated [19]. The D-W is given by:…”

Section: Multiple Linear Regression (Mlr)mentioning

confidence: 99%

“…The relationship between PM 10 concentration, meteorological factors and gaseous pollutants has been proven statistically by using several multivariate analyses, especially the development of Multiple Linear Regression (MLR) models to forecast PM 10 concentration [19][20][21]. Unfortunately, MLR relies on several assumptions, such as that the independent variables are linearly independent (multi-collinearity), that there is homogeneity of variance (homoscedasticity) and that the variables are normally distributed [22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Forecasting Particulate Matter Concentration Using Linear and Non-Linear Approaches for Air Quality Decision Support

et al. 2019

View full text Add to dashboard Cite

Air quality status on the East Coast of Peninsular Malaysia is dominated by Particulate Matter (PM10) throughout the years. Studies have affirmed that PM10 influence human health and the environment. Therefore, precise forecasting algorithms are urgently needed to determine the PM10 status for mitigation plan and early warning purposes. This study investigates the forecasting performance of a linear (Multiple Linear Regression) and two non-linear models (Multi-Layer Perceptron and Radial Basis Function) utilizing meteorological and gaseous pollutants variables as input parameters from the year 2000–2014 at four sites with different surrounding activities of urban, sub-urban and rural areas. Non-linear model (Radial Basis Function) outperforms the linear model with the error reduced by 78.9% (urban), 32.1% (sub-urban) and 39.8% (rural). Association between PM10 and its contributing factors are complex and non-linear in nature, best captured by an Artificial Neural Network, which generates more accurate PM10 compared to the linear model. The results are robust enough for precise next day forecasting of PM10 concentration on the East Coast of Peninsular Malaysia.

show abstract

“…In statistical tools, analysis of regression is commonly used to analyze data. The MLR is a traditional method based on the concept of Ordinary Least Square estimate (OLS) (Ul-Saufie et al, 2012). MLR is used to present the relationship between dependent variable and independent variables (Chatterjee and Hadi, 2006).…”

Section: Introductionmentioning

confidence: 99%

Three Days Ahead Prediction of Daily 12 Hour Ozone (O3) Concentrations for Urban Area in Malaysia

Muhamad

Ul-Saufie

Deni³

2015

J. of Environmental Science and Technology

View full text Add to dashboard Cite

Ground-level ozone (O 3 ) is a secondary pollutant and has an adverse effect on human health, agriculture and ecosystems. The aim of this study is to develop model and to predict future O 3 concentrations level in Shah Alam for next day (D+1), next two days (D+2) and next three days (D+3) using traditional method of Multiple Linear Regression (MLR) based on the concept of Ordinary Least Square estimate (OLS). This study uses daily average data of air pollutants (O 3 , NO x , NO, SO 2, NO 2 , CO) and meteorological variables (WS, T, RH) that was selected from 2002 until 2013 as independent variables. The performance indicator of the models are measured by accuracy measures (Prediction accuracy, Index agreement and Coefficient of determination) and error measures (Root mean square error, Normalized absolute value). The average accuracy measures (AI, PA and R 2 ) show that the prediction for D+1, D+2 and D+3 is 0.4492, 0.3797 and 0.304 respectively. Meanwhile, the average error measures (RMSE, NAE) show that the prediction for D+1, D+2 and D+3 is 0.1453, 0.1374 and 0.1302, respectively.

show abstract

Performance of Multiple Linear Regression Model for Long-term PM10 Concentration Prediction Based on Gaseous and Meteorological Parameters

Cited by 35 publications

References 8 publications

The behavior of Particulate Matter (PM10) Concentrations at Industrial Sites in Malaysia

The behavior of Particulate Matter (PM10) Concentrations at Industrial Sites in Malaysia

Forecasting Particulate Matter Concentration Using Linear and Non-Linear Approaches for Air Quality Decision Support

Three Days Ahead Prediction of Daily 12 Hour Ozone (O3) Concentrations for Urban Area in Malaysia

Contact Info

Product

Resources

About