Wavelet & Correlation Analysis of Air Pollution Parameters Using Haar Wavelet (Level 3)

Abstract

This paper deals with the wavelet and correlation analysis of air pollution parameters in Delhi, India. Hourly average value of air pollution parameters Carbon Monoxide (CO), Nitrogen Oxide (NO), Nitrogen Dioxide (NO2), Ozone (O3), Particulate Matters (PM2.5) and Sulphur Dioxide (SO2) have been studied. Discrete wavelet using Haar wavelet at level 3 and Continuous wavelet of air pollution parameters have been discussed. Discrete wavelet decomposition of each parameter presented in five parts namely s, a 3 , d1 , d2 , d3 . The first part “s” represents the signal or raw data and the second part “a3” corresponds to the amplitude of the signal. The next three parts d1 , d2 , d3 represent details of the signal or raw data at three different levels. 1D continuous wavelet decomposition of each parameter has four parts; first part on top represents the analyzed signal or raw data, second part contains the scalogram value. The third part shows the daily variation of coefficients. The fourth part depicts the local maximums of related parameters. It has been observed that all the pollutants have positive correlation with all the other pollutants except with O3. Ozone has negative correlation with all the pollutant parameters.