Tools
Tools
Singh, Kumar Parakram (2022) Forecasting the air pollution in New Delhi using deep Learning methodology with Covid-19 lockdown focus. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration manual)
Download (3MB) | Preview |
Abstract
New Delhi has witnessed a sharp spike in industrialization within a very short time frame. The primary source of pollution in Delhi is the pollutants coming from meteorological activities, vehicles and heavy industries. In this study, pollutant data from four locations in Delhi - Anand Vihar, DTU, Bawana and Vivek Vihar have been analysed. In this paper, the dataset from the Delhi Air Pollution Control Board has been used.1 The critical reason for choosing the pollutant Particulate Matter 2.5 is because of its lethal nature. In this paper, multivariate analyses have been done with the help of Long Short Term Memory (LSTM) -deep learning methodologies. Recent versions of LSTM like the Encoder-Decoder-LSTM, Bi-Directional LSTM, and LSTM-Forward Neural Network have also been implemented and analysed. In terms of novelty, this paper implements the technique (ten steps ahead or multistep ahead) short-term air quality forecasting method. In this paper, one month’s future air pollutant Particulate Matter 2.5 predictions have been done. In addition, twelve predictor variables with eighty hours of data have been used. The accuracy of the models has been evaluated with the help of the Root Mean Square Error evaluation matrix. The impact of the Covid-19 lockdown in Delhi has also been investigated, and it was evaluated that the air quality deteriorated once the restrictions were relaxed. It was evaluated that the bi-directional LSTM with the least RMSE error was the best prediction model.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Industrial emissions; Multi-Step ahead method; Covid-19; Long Short Term Memory; Root Mean Square Error; Forecasting |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TD Environmental technology. Sanitary engineering Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 11 Mar 2023 14:34 |
| Last Modified: | 11 Mar 2023 14:34 |
| URI: | https://norma.ncirl.ie/id/eprint/6313 |
Actions (login required)
 |
View Item |