Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909870800764928 |
|---|---|
| author | Naeini, Amirali Ataee Naeini, Arshia Ataee Mohammadi, Fatemeh Karami Ghaffarpasand, Omid |
| author_facet | Naeini, Amirali Ataee Naeini, Arshia Ataee Mohammadi, Fatemeh Karami Ghaffarpasand, Omid |
| contents | Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approaches struggle to maintain prediction stability beyond 48 hours, especially in cities with sparse monitoring networks. This paper presents a deep learning framework that combines Dynamic Time Warping (DTW) for intelligent station similarity selection with a CNN-GRU architecture to enable extended-horizon PM2.5 forecasting in Isfahan, Iran, a city characterized by complex pollution dynamics and limited monitoring coverage. Unlike existing approaches that rely on computationally intensive transformer models or external simulation tools, our method integrates three key innovations: (i) DTW-based historical sampling to identify similar pollution patterns across peer stations, (ii) a lightweight CNN-GRU architecture augmented with meteorological features, and (iii) a scalable design optimized for sparse networks. Experimental validation using multi-year hourly data from eight monitoring stations demonstrates superior performance compared to state-of-the-art deep learning methods, achieving R2 = 0.91 for 24-hour forecasts. Notably, this is the first study to demonstrate stable 10-day PM2.5 forecasting (R2 = 0.73 at 240 hours) without performance degradation, addressing critical early-warning system requirements. The framework's computational efficiency and independence from external tools make it particularly suitable for deployment in resource-constrained urban environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22863 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model Naeini, Amirali Ataee Naeini, Arshia Ataee Mohammadi, Fatemeh Karami Ghaffarpasand, Omid Machine Learning Artificial Intelligence Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approaches struggle to maintain prediction stability beyond 48 hours, especially in cities with sparse monitoring networks. This paper presents a deep learning framework that combines Dynamic Time Warping (DTW) for intelligent station similarity selection with a CNN-GRU architecture to enable extended-horizon PM2.5 forecasting in Isfahan, Iran, a city characterized by complex pollution dynamics and limited monitoring coverage. Unlike existing approaches that rely on computationally intensive transformer models or external simulation tools, our method integrates three key innovations: (i) DTW-based historical sampling to identify similar pollution patterns across peer stations, (ii) a lightweight CNN-GRU architecture augmented with meteorological features, and (iii) a scalable design optimized for sparse networks. Experimental validation using multi-year hourly data from eight monitoring stations demonstrates superior performance compared to state-of-the-art deep learning methods, achieving R2 = 0.91 for 24-hour forecasts. Notably, this is the first study to demonstrate stable 10-day PM2.5 forecasting (R2 = 0.73 at 240 hours) without performance degradation, addressing critical early-warning system requirements. The framework's computational efficiency and independence from external tools make it particularly suitable for deployment in resource-constrained urban environments. |
| title | Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.22863 |