Time Series Analysis to Forecast Air Quality Indices in Thiruvananthapuram District, Kerala, India

Abstract

Cite this paper Get the citation in MLA, APA, or Chicago styles Downloaded from Academia.edu  Related papers St reet Level Modeling of Pollut ant s for Resident ial Areas anil vyas, Nit ish Rai S A Singular Spect rum Analysis Technique t o Elect ricit y Consumpt ion Forecast ing IJERA Journal Correlat ion bet ween Air Qualit y Index and Traffic Volume IJERA Journal Download a PDF Pack of t he best relat ed papers  Highlights  Air Quality Index (AQI) of Thiruvananthapuram city has been calculated  AQI forecasting using ARIMA and SARIMA model were introduced  Error between actual and predicted AQI has been reduced using optimization technique ABSTRACT Deterioration of air quality is an important issue faced by many cities in India. The increase in the number of vehicles, unrestrained burning of plastics, unacceptable construction and demolition activities and industrial activities are the main reasons for this deterioration. So it is necessary to assess the effectiveness of air quality monitoring programs for planning air pollution control actions by analyzing the trends in air quality regularly. In this study, the varying trends of ambient air quality were analyzed and forecasted in terms of Air Quality Index (AQI) based on the database monitored at different monitoring stations in Thiruvananthapuram District, Kerala, India. The air quality data from the Kerala State Pollution Control Board (KSPCB) shows that the responsible pollutant for AQI in all these stations were Respirable Suspended Particulate Matter (RSPM) due to its abundance in the atmosphere. By forecasting, we can predict the future air quality in terms of AQI or individual pollutants in order to reduce the pollutant concentration and exposure to air pollutants. For air quality forecasting, Auto Regressive Integrated Moving Average (ARIMA) and Seasonal Auto Regressive Integrated Moving Average (SARIMA) method was used. ARIMA models gave satisfactory results than the SARIMA models and these results can be combined with other models to create more accurate results.