Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, Indonesia
Air pollution in Jakarta, one of the most polluted cities globally, has reached critical levels, with PM<sub>2.5</sub> concentrations exceeding the WHO guidelines and posing significant health risks. Accurate forecasting of PM<sub>2.5</sub> is crucial for effective air qualit...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/1/23 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589105270095872 |
|---|---|
| author | Dinda Ayu Safira Heri Kuswanto Muhammad Ahsan |
| author_facet | Dinda Ayu Safira Heri Kuswanto Muhammad Ahsan |
| author_sort | Dinda Ayu Safira |
| collection | DOAJ |
| description | Air pollution in Jakarta, one of the most polluted cities globally, has reached critical levels, with PM<sub>2.5</sub> concentrations exceeding the WHO guidelines and posing significant health risks. Accurate forecasting of PM<sub>2.5</sub> is crucial for effective air quality management and public health interventions. PM<sub>2.5</sub> exhibits significant nonlinear fluctuations; thus, this study employed two machine learning approaches: self-exciting threshold autoregressive tree (SETAR-Tree) and long short-term memory (LSTM). The SETAR-Tree model integrates regime-switching capabilities with decision tree principles to capture nonlinear patterns, while LSTM models long-term dependencies in time-series data. The results showed that: (1) SETAR-Tree outperformed LSTM, achieving lower RMSE (0.1691 in-sample, 0.2159 out-sample) and MAPE (2.83% in-sample, 2.98% out-sample) compared to LSTM’s RMSE (0.2038 in-sample, 0.2399 out-sample) and MAPE (3.48% in-sample, 4.05% out-sample); (2) SETAR-Tree demonstrated better responsiveness to sudden regime changes, capturing complex pollution patterns influenced by meteorological and anthropogenic factors; (3) PM<sub>2.5</sub> in Jakarta often exceeds the WHO limits, highlighting this study’s importance in supporting strategic planning and providing an early warning system to reduce outdoor activity during extreme pollution. |
| format | Article |
| id | doaj-art-33c5eed6550e4b19a206932851d5af21 |
| institution | Kabale University |
| issn | 2073-4433 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj-art-33c5eed6550e4b19a206932851d5af212025-01-24T13:21:44ZengMDPI AGAtmosphere2073-44332024-12-011612310.3390/atmos16010023Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, IndonesiaDinda Ayu Safira0Heri Kuswanto1Muhammad Ahsan2Department of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya 60111, IndonesiaDepartment of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya 60111, IndonesiaDepartment of Statistics, Institut Teknologi Sepuluh Nopember, Surabaya 60111, IndonesiaAir pollution in Jakarta, one of the most polluted cities globally, has reached critical levels, with PM<sub>2.5</sub> concentrations exceeding the WHO guidelines and posing significant health risks. Accurate forecasting of PM<sub>2.5</sub> is crucial for effective air quality management and public health interventions. PM<sub>2.5</sub> exhibits significant nonlinear fluctuations; thus, this study employed two machine learning approaches: self-exciting threshold autoregressive tree (SETAR-Tree) and long short-term memory (LSTM). The SETAR-Tree model integrates regime-switching capabilities with decision tree principles to capture nonlinear patterns, while LSTM models long-term dependencies in time-series data. The results showed that: (1) SETAR-Tree outperformed LSTM, achieving lower RMSE (0.1691 in-sample, 0.2159 out-sample) and MAPE (2.83% in-sample, 2.98% out-sample) compared to LSTM’s RMSE (0.2038 in-sample, 0.2399 out-sample) and MAPE (3.48% in-sample, 4.05% out-sample); (2) SETAR-Tree demonstrated better responsiveness to sudden regime changes, capturing complex pollution patterns influenced by meteorological and anthropogenic factors; (3) PM<sub>2.5</sub> in Jakarta often exceeds the WHO limits, highlighting this study’s importance in supporting strategic planning and providing an early warning system to reduce outdoor activity during extreme pollution.https://www.mdpi.com/2073-4433/16/1/23SETAR-TreeLSTMPM<sub>2.5</sub>air pollutionforecastingnonlinear time series |
| spellingShingle | Dinda Ayu Safira Heri Kuswanto Muhammad Ahsan Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, Indonesia Atmosphere SETAR-Tree LSTM PM<sub>2.5</sub> air pollution forecasting nonlinear time series |
| title | Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, Indonesia |
| title_full | Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, Indonesia |
| title_fullStr | Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, Indonesia |
| title_full_unstemmed | Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, Indonesia |
| title_short | Improving the Forecast Accuracy of PM<sub>2.5</sub> Using SETAR-Tree Method: Case Study in Jakarta, Indonesia |
| title_sort | improving the forecast accuracy of pm sub 2 5 sub using setar tree method case study in jakarta indonesia |
| topic | SETAR-Tree LSTM PM<sub>2.5</sub> air pollution forecasting nonlinear time series |
| url | https://www.mdpi.com/2073-4433/16/1/23 |
| work_keys_str_mv | AT dindaayusafira improvingtheforecastaccuracyofpmsub25subusingsetartreemethodcasestudyinjakartaindonesia AT herikuswanto improvingtheforecastaccuracyofpmsub25subusingsetartreemethodcasestudyinjakartaindonesia AT muhammadahsan improvingtheforecastaccuracyofpmsub25subusingsetartreemethodcasestudyinjakartaindonesia |