Short-term Predictions of PM10 Using Bayesian Regression Models
One of the air pollutants that poses the greatest threat to human health is PM10. The objectives of this study are to develop a prediction model for PM10. The Multiple Linear Regression (MLR) and Bayesian Regression (BRM) models were constructed to forecast the following day’s (Day 1) and next two d...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2023-01-01
|
Series: | E3S Web of Conferences |
Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/74/e3sconf_icongeet2023_01006.pdf |
_version_ | 1797658505076801536 |
---|---|
author | Ramli Norazrin Abdul Hamid Hazrul Yahaya Ahmad Shukri Noor Norazian Mohamed Elena Holban |
author_facet | Ramli Norazrin Abdul Hamid Hazrul Yahaya Ahmad Shukri Noor Norazian Mohamed Elena Holban |
author_sort | Ramli Norazrin |
collection | DOAJ |
description | One of the air pollutants that poses the greatest threat to human health is PM10. The objectives of this study are to develop a prediction model for PM10. The Multiple Linear Regression (MLR) and Bayesian Regression (BRM) models were constructed to forecast the following day’s (Day 1) and next two days’ (Day 2) PM10 concentration. To choose the optimal model, the performance metrics (NAE, RMSE, PA, IA, and R2) are applied to each model. Jerantut, Nilai, Shah Alam, and Klang were chosen as monitoring sites. Data from the Department of Environment Malaysia (DOE) was utilised as a case study for five years, with seven parameters (PM10, temperature, relative humidity, NO2, SO2, CO, and O3) chosen. According to the findings, the key factors responsible for the unhealthy levels of air quality at the Klang station include carbon monoxide (CO), nitrogen dioxide (NO2), sulphur dioxide (SO2), and ozone (O3) from industrial and maritime activities, which are thought to influence PM10 concentrations in the area. When compared to MLR models, the results demonstrate that BRM are the best model for predicting the next day and next two days PM10 concentration at all locations. |
first_indexed | 2024-03-11T18:01:01Z |
format | Article |
id | doaj.art-55272137077c41a590412ef6e5adc683 |
institution | Directory Open Access Journal |
issn | 2267-1242 |
language | English |
last_indexed | 2024-03-11T18:01:01Z |
publishDate | 2023-01-01 |
publisher | EDP Sciences |
record_format | Article |
series | E3S Web of Conferences |
spelling | doaj.art-55272137077c41a590412ef6e5adc6832023-10-17T08:53:04ZengEDP SciencesE3S Web of Conferences2267-12422023-01-014370100610.1051/e3sconf/202343701006e3sconf_icongeet2023_01006Short-term Predictions of PM10 Using Bayesian Regression ModelsRamli Norazrin0Abdul Hamid Hazrul1Yahaya Ahmad Shukri2Noor Norazian Mohamed3Elena Holban4Faculty of Civil Engineering & Technology, Universiti Malaysia Perlis, JejawiSchool of Distance Education, Universiti Sains MalaysiaSchool of Civil Engineering, Engineering Campus, Universiti Sains MalaysiaFaculty of Civil Engineering & Technology, Universiti Malaysia Perlis, JejawiNational Instiute for Research and Development in Environmental ProtectionOne of the air pollutants that poses the greatest threat to human health is PM10. The objectives of this study are to develop a prediction model for PM10. The Multiple Linear Regression (MLR) and Bayesian Regression (BRM) models were constructed to forecast the following day’s (Day 1) and next two days’ (Day 2) PM10 concentration. To choose the optimal model, the performance metrics (NAE, RMSE, PA, IA, and R2) are applied to each model. Jerantut, Nilai, Shah Alam, and Klang were chosen as monitoring sites. Data from the Department of Environment Malaysia (DOE) was utilised as a case study for five years, with seven parameters (PM10, temperature, relative humidity, NO2, SO2, CO, and O3) chosen. According to the findings, the key factors responsible for the unhealthy levels of air quality at the Klang station include carbon monoxide (CO), nitrogen dioxide (NO2), sulphur dioxide (SO2), and ozone (O3) from industrial and maritime activities, which are thought to influence PM10 concentrations in the area. When compared to MLR models, the results demonstrate that BRM are the best model for predicting the next day and next two days PM10 concentration at all locations.https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/74/e3sconf_icongeet2023_01006.pdf |
spellingShingle | Ramli Norazrin Abdul Hamid Hazrul Yahaya Ahmad Shukri Noor Norazian Mohamed Elena Holban Short-term Predictions of PM10 Using Bayesian Regression Models E3S Web of Conferences |
title | Short-term Predictions of PM10 Using Bayesian Regression Models |
title_full | Short-term Predictions of PM10 Using Bayesian Regression Models |
title_fullStr | Short-term Predictions of PM10 Using Bayesian Regression Models |
title_full_unstemmed | Short-term Predictions of PM10 Using Bayesian Regression Models |
title_short | Short-term Predictions of PM10 Using Bayesian Regression Models |
title_sort | short term predictions of pm10 using bayesian regression models |
url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/74/e3sconf_icongeet2023_01006.pdf |
work_keys_str_mv | AT ramlinorazrin shorttermpredictionsofpm10usingbayesianregressionmodels AT abdulhamidhazrul shorttermpredictionsofpm10usingbayesianregressionmodels AT yahayaahmadshukri shorttermpredictionsofpm10usingbayesianregressionmodels AT noornorazianmohamed shorttermpredictionsofpm10usingbayesianregressionmodels AT elenaholban shorttermpredictionsofpm10usingbayesianregressionmodels |