A comprehensive study to predict the short-term air quality with the help of multiple deep learning models in Guangzhou city: China

Singh, Virender (2019) A comprehensive study to predict the short-term air quality with the help of multiple deep learning models in Guangzhou city: China. Masters thesis, Dublin, National College of Ireland.

Preview

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

Abstract

Air pollution is recognised as a worldwide risk to humans. Large cities in China particularly have experienced a marked degradation in air quality so residents are at particular risk. Prediction of the immediate future air quality is important as accurate warnings could assist residents and industries take measures to reduce exposure to and production of pollution when meteorological conditions are expected to increase the impact of pollutants. The research aims to establish whether patterns in the historic data can assist identify sets of occurrences that might combine to negatively impact air quality. The focus of this research is on levels of the principal pollutant, particulate matters 2.5 (pm2.5). These particles are particularly dangerous because of their tiny size, with a diameter of 2.5 microns or less these are the most significant cause of air quality related deaths. This research tested the following prediction methods; Convolutional Neural Networks (CNN), Gated Current Units (GRU), Multilayer perceptron (MLP) and Long-Short Term Memory (LSTM). A performance comparison completed with the historically executed Machine Learning (ML) models using the CRISP-DM methodology demonstrated that the methodologies can successfully predict the concentration level of pm2.5 and the correlation with meteorological factors that leads to air quality degradation.

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:	11 Oct 2019 12:38
Last Modified:	11 Oct 2019 12:39
URI:	https://norma.ncirl.ie/id/eprint/3845

Actions (login required)

View Item