NORMA eResearch @NCI Library

Prediction an air quality index data using machine learning and deep learning

Patil, Ruchita (2021) Prediction an air quality index data using machine learning and deep learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Environment sustainability has now become an important aspect of daily life. Air pollution is one of the most serious risks to the environment’s long-term viability. Delhi, the national capital of India has been facing with the issue of poor air quality index for quite some years. The poor air quality has been negatively impacting the life of residents. As it is said, prevention is better than cure, it would be meaningful to predict the future scenarios beforehand to be better prepared to deal with it. This thesis uses various time series forecasting techniques to predict the Air Quality Index of Delhi for next few time periods. The pollutant levels for Particulate Matter (PM2.5, PM10), Sulphur Dioxide (SO2), Carbon Monoxide (CO), Nitrogen Dioxide (NO2) among other have been forecasted for a single chosen location in Delhi. The errors for various techniques have been reported. The findings of this research paper also include referring to other secondary sources that throws some light on the underlying issues of air pollution. This can thus be used for various future related studies that could come up in future and talks about Delhi’s air pollution. For the suggested design, two models were integrated. The first layer used Gated Recurrent Unit, and all data was passed to the Long Short-Term Memory layer, which was followed by two dense layers. This proposed model is evaluated in comparison to the Long Short-Term Memory, Gated Recurrent Unit, Decision Tree, and Linear Regression models. Mean Square Error, Root Mean Square Error, and Mean Absolute Error are performance measures that are used to calculate error rates. When two models are combined, the overall performance of some factors improves.

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: Clara Chan
Date Deposited: 11 Dec 2021 12:36
Last Modified: 11 Dec 2021 12:36

Actions (login required)

View Item View Item