Extracting Patterns and Variations in Air Quality of Four Tier I Cities in India

The cities in India are classified into Tier I, II and III based on population by RBI. Air pollution is a major concern of study as it has adverse impact on human health and ecosystem. Tier I cities in India have high levels of pollutants due to increased vehicles, industrial units etc. The air quality data collected for New Delhi, Mumbai, Chennai and Bengaluru has a large number of dimensions and after tests PCA (principal component analysis) has been found to be the best technique for dimensionality reduction. The results of PCA have been used to provide a useful description in terms of sources of air pollution. After removing seasonality from air quality data ARIMA and GARCH model has been applied to better understand the data and the results of ARIMA and GARCH are quite comparable. Earlier ARIMA has been applied only on static time sequence but in this study SDA (Streaming Data ARIMA) has been proposed that applies ARIMA model on streaming data and estimates how various parameters of ARIMA model change based on window size of streaming data. The results of SDA and ARIMA on static time sequence are compared and have been found to be very promising.

[1]  Sayanti Kar,et al.  Studies on Interrelations among SO2, NO2 and PM10 Concentrations and Their Predictions in Ambient Air in Kolkata , 2012 .

[2]  Suhartono,et al.  Seasonal ARIMA for forecasting air pollution index: a case study , 2012 .

[3]  S. Tiwari,et al.  Investigation into relationships among NO, NO2, NOx, O3, and CO at an urban background site in Delhi, India , 2015 .

[4]  Shu-Lung Kuo,et al.  Air Quality Time Series Based GARCH Model Analyses of Air Quality Information for a Total Quantity Control District , 2012 .

[5]  Maizah Hura Ahmad,et al.  A comparative study on box-jenkins and garch models in forecasting crude oil prices , 2011 .

[6]  Richard G. Derwent,et al.  Analysis and interpretation of air quality data from an urban roadside location in Central London over the period from July 1991 to July 1992 , 1995 .

[7]  Tapani Raiko,et al.  Tkk Reports in Information and Computer Science Practical Approaches to Principal Component Analysis in the Presence of Missing Values Tkk Reports in Information and Computer Science Practical Approaches to Principal Component Analysis in the Presence of Missing Values , 2022 .

[8]  Rakesh Kumar,et al.  Air Pollution Concentrations of PM2.5, PM10 and NO2 at Ambient and Kerbsite and Their Correlation in Metro City – Mumbai , 2006, Environmental monitoring and assessment.

[9]  James Morley,et al.  Bootstrap Tests of Stationarity , 2009 .

[10]  M. Valipour,et al.  Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir , 2013 .

[11]  M. Lawrence.  The relationship between relative humidity and the dewpoint temperature in moist air - A simple conversion and applications , 2005 .

[12]  Qin Jun,et al.  Impacts of Atmospheric Conditions on Influenza in Southern China. Part I. Taking Shenzhen City for Example , 2012 .

[13]  Inderjeet Kaushik,et al.  TIME SERIES ANALYSIS OF AMBIENT AIR QUALITY AT ITO INTERSECTION IN DELHI (INDIA) , 2012 .

[14]  Saptarsi Goswami,et al.  STUDY OF EFFECTIVENESS OF TIME SERIES M ODELI NG (ARIMA) INFORECASTING STOCK PRICES , 2014 .

[15]  E. Buringh,et al.  Application of principal component analysis to time series of daily air pollution and mortality , 2004 .

[16]  Borhan Mansouri,et al.  Study on ambient concentrations of air quality parameters (O3, SO2, CO and PM10) in different months in Shiraz city, Iran , 2011 .