Analysis of Air Quality using Univariate and Multivariate Time Series Models

Due to the major consequences of air pollution on human health, this problem is resulting in a major public crisis which requires immediate attention. Nowadays, the prediction of air quality has been a potential research area. There exist a number of methods in literature, but the focus of this work...

Full description

Saved in:
Bibliographic Details
Published in2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence) pp. 823 - 827
Main Authors Sethi, Jasleen Kaur, Mittal, Mamta
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2020
Subjects
Air Qualiy Index
Atmospheric modeling
Autoregressive Integrated Moving Average (ARIMA)
Cloud computing
Computational modeling
Data models
Data science
Multivariate Time Series Analysis
Reactive power
Time series analysis
Univariate Time Series Analysis
Vector Autoregression (VAR)
Online AccessGet full text

Cover

More Information
Summary:Due to the major consequences of air pollution on human health, this problem is resulting in a major public crisis which requires immediate attention. Nowadays, the prediction of air quality has been a potential research area. There exist a number of methods in literature, but the focus of this work is based on the prediction of air quality using time series analysis. This analysis has been carried out using univariate and multivariate techniques namely Autoregressive Integrated Moving Average (ARIMA) and Vector Autoregression (VAR) models. To perform the experimental work, the dataset of Gurugram has been considered. Further, the performance of both the models has been evaluated based on a number of metrics and it has been observed that the ARIMA model produced better results in comparison to VAR model for the prediction of Air Quality Index (AQI).
DOI:10.1109/Confluence47617.2020.9058303