Forecasting PM2.5 in Malaysia Using a Hybrid Model
Abstract Predicting future PM2.5 concentrations based on knowledge obtained from past observational data is very useful for predicting air pollution. This paper aims to develop a hybrid forecasting model using an Artificial Neural Network (ANN) and Triple Exponential Smoothing (TES) on clustered PM2...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-06-01
|
| Series: | Aerosol and Air Quality Research |
| Subjects: | |
| Online Access: | https://doi.org/10.4209/aaqr.230006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862811872198656 |
|---|---|
| author | Ezahtulsyahreen Ab. Rahman Firdaus Mohamad Hamzah Mohd Talib Latif Azman Azid |
| author_facet | Ezahtulsyahreen Ab. Rahman Firdaus Mohamad Hamzah Mohd Talib Latif Azman Azid |
| author_sort | Ezahtulsyahreen Ab. Rahman |
| collection | DOAJ |
| description | Abstract Predicting future PM2.5 concentrations based on knowledge obtained from past observational data is very useful for predicting air pollution. This paper aims to develop a hybrid forecasting model using an Artificial Neural Network (ANN) and Triple Exponential Smoothing (TES) on clustered PM2.5 data from a HPR (High Pollution Region), MPR (Medium Pollution Region), and LPR (Low Pollution Region) in Malaysia. Historical PM2.5 concentrations in Malaysia from January 2018 to December 2019 were used to develop a hybrid model. The proposed hybrid model was then evaluated in terms of Mean Absolute Percentage Error (MAPE) values by comparing them with real PM2.5 data from the year 2020 in the HPR, MPR and LPR. The results showed that the hybrid model of ANN and TES presented the lowest RMSE (Root Mean Squared Error) (4.25–8.56 µg m−3), MAE (Mean Absolute Error) (2.51–4.95 µg m−3), MAPE (0.13–0.2%), and MASE (Mean Absolute Scaled Error) (1.45–2.01) in different areas of pollution compared with other models. The comparison between the ANN and TES hybrid models and the real PM2.5 data in 2020 showed that the models gave sufficient accuracy in the HPR and MPR with MAPE values of between 20% and 50%, while the LPR showed less accuracy due to the high value of MAPE of more than 50%. Overall, the hybrid model developed in this study opens up a new prediction method for air quality forecasting and is sufficiently accurate to be used as a tool for air quality management. |
| format | Article |
| id | doaj-art-64c49d6983b348d982c1ad39b53f5558 |
| institution | Kabale University |
| issn | 1680-8584 2071-1409 |
| language | English |
| publishDate | 2023-06-01 |
| publisher | Springer |
| record_format | Article |
| series | Aerosol and Air Quality Research |
| spelling | doaj-art-64c49d6983b348d982c1ad39b53f55582025-02-09T12:23:19ZengSpringerAerosol and Air Quality Research1680-85842071-14092023-06-0123911810.4209/aaqr.230006Forecasting PM2.5 in Malaysia Using a Hybrid ModelEzahtulsyahreen Ab. Rahman0Firdaus Mohamad Hamzah1Mohd Talib Latif2Azman Azid3Air Division, Department of EnvironmentCentre for Defence Foundation Studies, Universiti Pertahanan Nasional MalaysiaDepartment of Earth Sciences and Environment, Faculty of Science and Technology, Universiti Kebangsaan MalaysiaSchool of Animal Science, Aquatic Science & Environment, Faculty of Bioresources and Food Industry, Universiti Sultan Zainal AbidinAbstract Predicting future PM2.5 concentrations based on knowledge obtained from past observational data is very useful for predicting air pollution. This paper aims to develop a hybrid forecasting model using an Artificial Neural Network (ANN) and Triple Exponential Smoothing (TES) on clustered PM2.5 data from a HPR (High Pollution Region), MPR (Medium Pollution Region), and LPR (Low Pollution Region) in Malaysia. Historical PM2.5 concentrations in Malaysia from January 2018 to December 2019 were used to develop a hybrid model. The proposed hybrid model was then evaluated in terms of Mean Absolute Percentage Error (MAPE) values by comparing them with real PM2.5 data from the year 2020 in the HPR, MPR and LPR. The results showed that the hybrid model of ANN and TES presented the lowest RMSE (Root Mean Squared Error) (4.25–8.56 µg m−3), MAE (Mean Absolute Error) (2.51–4.95 µg m−3), MAPE (0.13–0.2%), and MASE (Mean Absolute Scaled Error) (1.45–2.01) in different areas of pollution compared with other models. The comparison between the ANN and TES hybrid models and the real PM2.5 data in 2020 showed that the models gave sufficient accuracy in the HPR and MPR with MAPE values of between 20% and 50%, while the LPR showed less accuracy due to the high value of MAPE of more than 50%. Overall, the hybrid model developed in this study opens up a new prediction method for air quality forecasting and is sufficiently accurate to be used as a tool for air quality management.https://doi.org/10.4209/aaqr.230006PM2.5Artificial neural networkExponential smoothingHybrid model |
| spellingShingle | Ezahtulsyahreen Ab. Rahman Firdaus Mohamad Hamzah Mohd Talib Latif Azman Azid Forecasting PM2.5 in Malaysia Using a Hybrid Model Aerosol and Air Quality Research PM2.5 Artificial neural network Exponential smoothing Hybrid model |
| title | Forecasting PM2.5 in Malaysia Using a Hybrid Model |
| title_full | Forecasting PM2.5 in Malaysia Using a Hybrid Model |
| title_fullStr | Forecasting PM2.5 in Malaysia Using a Hybrid Model |
| title_full_unstemmed | Forecasting PM2.5 in Malaysia Using a Hybrid Model |
| title_short | Forecasting PM2.5 in Malaysia Using a Hybrid Model |
| title_sort | forecasting pm2 5 in malaysia using a hybrid model |
| topic | PM2.5 Artificial neural network Exponential smoothing Hybrid model |
| url | https://doi.org/10.4209/aaqr.230006 |
| work_keys_str_mv | AT ezahtulsyahreenabrahman forecastingpm25inmalaysiausingahybridmodel AT firdausmohamadhamzah forecastingpm25inmalaysiausingahybridmodel AT mohdtaliblatif forecastingpm25inmalaysiausingahybridmodel AT azmanazid forecastingpm25inmalaysiausingahybridmodel |