Comparison of Air Pollution in Delhi using open air in R


  • Ms. Radhika Goyal, Ms. Meenal Kakkar


With an immense growth in development followed by the concept of urbanization, there is a drastic increase in the level of pollution, especially in metro cities. One such case is in Delhi where there has been a drastic increase in the pollutant level in the air causing many hazardous diseases and breathing problems. There are many sources of air pollution broadly categorized into natural sources like an eruption of Volcano, sea salts, etc. and the anthropogenic sources like emission from the industries, mobile sources mainly the vehicular emissions, etc. causing the degradation in the quality of air.

The paper consists of the comparison between the pollution level in the month of (June-July) with that of in the month of October for the year 2019 to determine the rise in the pollution level because of the bursting of firecrackers and more usage of transportation during festive days that indulges in the high emission of harmful gases. For the comparison of the data, the descriptive analysis is done using RStudio since it consists of a package that is specially designed for the calculation and representation of air pollution.

The openair is the R package that was mainly developed to analyze the air pollution measurement data and further can be used in atmospheric sciences. The package contains many tools allowing the import and manipulation of the collected data so that one can achieve a better understanding of the current status & the trend following with the quality of the air one intakes. 

For the comparison of the pollution, the data of the two most polluted places out of the 35 monitoring locations in Delhi namely Anand Vihar and Mandir Marg is collected for all 10 different types of pollutants or gas concentrations (Ammonia, Benzene, Nitrogen Oxide, Nitrogen Dioxide, Oxides of Nitrogen, Ozone, P-Xylene, Sulphur Dioxide, Toluene, and Carbon Monoxide) present in the air for the period of two months (June and July) during the time slot of peak office hours when the rush is most on the streets along with the data collected for the month of October for same hours to determine the impact of festivals that causes the increase in the traffic and the impact of crackers on the environment causing many diseases.

A set of patterns and trends is extracted from the analysis. The comparison is done using the statistical tool R where many inbuilt functions help in the conversion of the numeric data and then generate the results for ease in the interpretation of the pattern followed.The representation of the results is done graphically using the openair in RStudio.