A study on air pollution Index in Sabah and Sarawak using principal component analysis and artificial neural network / Nur Ellisa Syazrina Zulkepli
Nowadays, the analysis of the level of air pollutants is very necessary for environmental science research. The increased air pollution in Sabah and Sarawak attracted the attention of all Malaysians. Extended exposure to air pollution would lead to health problems. This study focused on identifying...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/44419/1/FullText%2044419.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Nowadays, the analysis of the level of air pollutants is very necessary for environmental science research. The increased air pollution in Sabah and Sarawak attracted the attention of all Malaysians. Extended exposure to air pollution would lead to health problems. This study focused on identifying trends in air quality in Sabah and Sarawak based on data from the Department of Environment (DOE). There are five selected Malaysian monitoring stations in Sabah and Sarawak based on five air pollutants over four years (2015-2018). The aim of this study is to classify the indicator of variable predictors using the principal component analysis (PCA) method and to compare the best model for predicting air pollution index (API) in Sabah and Sarawak using the artificial neural network (ANN) model. The PCA environmental approach is used to identify sources of air pollution. ANN is used to compare the best model for predicting the API in Sabah and Sarawak. After the varimax rotation, only two pollutants (PM10 and NO2) were the most significant pollutants out of the other five pollutants. These two pollutants used as input layers in Model B and the five pollutants used as input layers in Model A. These two models were used to compare the best model in the ANN method. The output of the ANN models evaluated by the coefficient of determination (R2) and the root mean square error (RMSE). To identify the best model, declare the highest value of R2 and the smallest value of RMSE. The findings indicate that the ANN technique has been successfully implemented as a decision-making tool as well as problem-solving for proper management of the atmosphere. |
|---|