Forecasting of Delhi Air Pollution With The Help of Performance Evaluation of Advanced Time Series Models

Memon, Mohammad Shahid (2018) Forecasting of Delhi Air Pollution With The Help of Performance Evaluation of Advanced Time Series Models. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (1MB) | Preview

Abstract

Air quality prediction is a hot topic for many researchers due to its effect on health. Researchers from every corner of the world are trying to develop the better model to predict the air quality. Delhi, the capital of India has been listed the most polluted cities on the earth by WHO,2014 which is a serious concern for the nation. This research evaluates the forecasting accuracy of the PM2.5 and PM10 fine particulate matter concentration in air by advanced time-series models. However, In Delhi air pollution, very limited work had been done in past. This research is accomplished using advanced time series models such as TBATS, ARIMA (Auto Regression Integrated Moving Averages), Simple Exponential Smoothing, Holt model and Neural Network. While this is the first research on forecasting the Delhi air pollutants such as PM10 and PM2.5 using TBATS, and Feedforward Neural Network. Throughout the research, it was found that neural network with feedforward single layer performing better than any other applied model but its execution time is very large, so it is only appropriate for short-term data whereas for long-term data ARIMA is the best model.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software G Geography. Anthropology. Recreation > GE Environmental Sciences > Environment
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	06 Nov 2018 11:41
Last Modified:	06 Nov 2018 11:41
URI:	https://norma.ncirl.ie/id/eprint/3442

Actions (login required)

View Item