Forecasting Air Quality of Delhi Using ARIMA Model

Air quality is a major issue that has been affecting the human health, flora, fauna and ecosystems since long. Vehicular pollution, burning of plastics, demolition and construction activities can be considered as the main reasons for degrading air quality. Therefore, it is necessary to devise a model using which we can analyse the air quality trends regularly on monthly and even seasonal basis. In this study, time series models are discussed to analyse future air quality used in modelling and forecasting monthly future air quality in New Delhi, India. By using time series, the study aims to analyse the air quality, and hence, predict the values for the future using ARIMA model and help in improving or at least controlling the degrading air quality. ARIMA stands for autoregressive integrated moving average model that is capable of analysing and representing stationary as well as non-stationary time series. Air pollutants data is analysed on daily basis using time series analysis. Comparison is made between the predicted and observed values of SO2 and NO2. By using ARIMA model, we get satisfactory and reliable results. It will help in getting information and thereon taking quick actions to monitor and control before the conditions get worse. The evaluation of performance is done by calculating mean square error, mean absolute error and root mean square error.

[1]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[2]  Krishan Kumar,et al.  Forecasting Daily Maximum Surface Ozone Concentrations in Brunei Darussalam—An ARIMA Modeling Approach , 2004, Journal of the Air & Waste Management Association.

[3]  Lim Ying Siew,et al.  ARIMA AND INTEGRATED ARFIMA MODELS FOR FORECASTING AIR POLLUTION INDEX IN SHAH ALAM, SELANGOR , 2008 .

[4]  Mohd Zamri Ibrahim,et al.  Forecasting and time series analysis of air pollutants in several area of Malaysia. , 2009 .

[5]  Ujjwal Kumar,et al.  ARIMA forecasting of ambient air pollutants (O3, NO, NO2 and CO) , 2010 .

[6]  Ayari Samia,et al.  A Hybrid ARIMA and Artificial Neural Networks Model to Forecast Air Quality in Urban Areas: Case of Tunisia , 2012 .

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

[8]  F. J. D. C. Juez,et al.  Forecasting SO 2 Pollution Incidents by means of Elman Artificial Neural Networks and ARIMA Models , 2013 .

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

[10]  Suhartono,et al.  Artificial neural networks and fuzzy time series forecasting: an application to air quality , 2014, Quality & Quantity.

[11]  P. Goyal,et al.  Artificial intelligence based approach to forecast PM2.5 during haze episodes: A case study of Delhi, India , 2015 .

[12]  Kafeel Ahmad,et al.  Time series analysis of aerosol optical depth over New Delhi using Box–Jenkins ARIMA modeling approach , 2016 .

[13]  Naveen,et al.  Time Series Analysis to Forecast Air Quality Indices in Thiruvananthapuram District, Kerala, India , 2017 .

[14]  Hong Zhang,et al.  A novel hybrid-Garch model based on ARIMA and SVM for PM2.5 concentrations forecasting , 2017 .

[15]  Deepa Gupta,et al.  Time Series Analysis of Air Pollution in Bengaluru Using ARIMA Model , 2018 .

[16]  Haiyan Lu,et al.  Air Pollution Forecasts: An Overview , 2018, International journal of environmental research and public health.