Deep Spatio-Temporal Neural Network for Air Quality Reanalysis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908949937127424 |
|---|---|
| author | Kheder, Ammar Foreback, Benjamin Wang, Lili Liu, Zhi-Song Boy, Michael |
| author_facet | Kheder, Ammar Foreback, Benjamin Wang, Lili Liu, Zhi-Song Boy, Michael |
| contents | Air quality prediction is key to mitigating health impacts and guiding decisions, yet existing models tend to focus on temporal trends while overlooking spatial generalization. We propose AQ-Net, a spatiotemporal reanalysis model for both observed and unobserved stations in the near future. AQ-Net utilizes the LSTM and multi-head attention for the temporal regression. We also propose a cyclic encoding technique to ensure continuous time representation. To learn fine-grained spatial air quality estimation, we incorporate AQ-Net with the neural kNN to explore feature-based interpolation, such that we can fill the spatial gaps given coarse observation stations. To demonstrate the efficiency of our model for spatiotemporal reanalysis, we use data from 2013-2017 collected in northern China for PM2.5 analysis. Extensive experiments show that AQ-Net excels in air quality reanalysis, highlighting the potential of hybrid spatio-temporal models to better capture environmental dynamics, especially in urban areas where both spatial and temporal variability are critical. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11941 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Spatio-Temporal Neural Network for Air Quality Reanalysis Kheder, Ammar Foreback, Benjamin Wang, Lili Liu, Zhi-Song Boy, Michael Machine Learning Artificial Intelligence Air quality prediction is key to mitigating health impacts and guiding decisions, yet existing models tend to focus on temporal trends while overlooking spatial generalization. We propose AQ-Net, a spatiotemporal reanalysis model for both observed and unobserved stations in the near future. AQ-Net utilizes the LSTM and multi-head attention for the temporal regression. We also propose a cyclic encoding technique to ensure continuous time representation. To learn fine-grained spatial air quality estimation, we incorporate AQ-Net with the neural kNN to explore feature-based interpolation, such that we can fill the spatial gaps given coarse observation stations. To demonstrate the efficiency of our model for spatiotemporal reanalysis, we use data from 2013-2017 collected in northern China for PM2.5 analysis. Extensive experiments show that AQ-Net excels in air quality reanalysis, highlighting the potential of hybrid spatio-temporal models to better capture environmental dynamics, especially in urban areas where both spatial and temporal variability are critical. |
| title | Deep Spatio-Temporal Neural Network for Air Quality Reanalysis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.11941 |