Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities
Air pollution presents a serious health challenge in urban metropolises. While accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models have yet fully captured the complex interactions between the temporal characteristics of air pollution and the spatial ch...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9780279/ |
| _version_ | 1818241808746938368 |
|---|---|
| author | Qi Zhang Yang Han Victor O. K. Li Jacqueline C. K. Lam |
| author_facet | Qi Zhang Yang Han Victor O. K. Li Jacqueline C. K. Lam |
| author_sort | Qi Zhang |
| collection | DOAJ |
| description | Air pollution presents a serious health challenge in urban metropolises. While accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models have yet fully captured the complex interactions between the temporal characteristics of air pollution and the spatial characteristics of urban dynamics. Our proposed Deep-AIR fills this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast, by exploiting domain-specific features (including Air Pollution, Weather, Urban Morphology, Transport, and Time-sensitive features), with a hybrid CNN-LSTM structure to capture the spatio-temporal features, and <inline-formula> <tex-math notation="LaTeX">$1\times 1$ </tex-math></inline-formula> convolution layers to enhance the learning of temporal and spatial interaction. Deep-AIR outperforms compatible baselines by a higher accuracy of 1.5%, 2.7%, and 2.3% for Hong Kong and 1.4%, 1.4% and 3.3% for Beijing in fine-grained 1-hr pollution estimation, and 1-hr and 24-hr forecasts, respectively. Saliency analysis reveals that for Hong Kong, spatial features, including street canyon and road density, are the best predictors for NO<sub>2</sub>, while temporal features, including historical air pollutants and weather, are the best predictors for PM<sub>2.5</sub>. For Beijing, historical air pollutant data, traffic congestion, wind direction and seasonal indicator are the best predictors for all pollutants. PM<sub>10</sub> in Hong Kong is achieving the best estimation and forecast accuracy, whilst CO in Beijing is achieving the best results. |
| first_indexed | 2024-12-12T13:35:14Z |
| format | Article |
| id | doaj.art-f97ff8ae13714788a24773886c4b9dfc |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-12T13:35:14Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f97ff8ae13714788a24773886c4b9dfc2022-12-22T00:22:59ZengIEEEIEEE Access2169-35362022-01-0110558185584110.1109/ACCESS.2022.31748539780279Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan CitiesQi Zhang0https://orcid.org/0000-0001-6621-9273Yang Han1Victor O. K. Li2https://orcid.org/0000-0002-1380-9445Jacqueline C. K. Lam3https://orcid.org/0000-0002-8805-3574Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, The University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, The University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, The University of Hong Kong, Hong KongAir pollution presents a serious health challenge in urban metropolises. While accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models have yet fully captured the complex interactions between the temporal characteristics of air pollution and the spatial characteristics of urban dynamics. Our proposed Deep-AIR fills this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast, by exploiting domain-specific features (including Air Pollution, Weather, Urban Morphology, Transport, and Time-sensitive features), with a hybrid CNN-LSTM structure to capture the spatio-temporal features, and <inline-formula> <tex-math notation="LaTeX">$1\times 1$ </tex-math></inline-formula> convolution layers to enhance the learning of temporal and spatial interaction. Deep-AIR outperforms compatible baselines by a higher accuracy of 1.5%, 2.7%, and 2.3% for Hong Kong and 1.4%, 1.4% and 3.3% for Beijing in fine-grained 1-hr pollution estimation, and 1-hr and 24-hr forecasts, respectively. Saliency analysis reveals that for Hong Kong, spatial features, including street canyon and road density, are the best predictors for NO<sub>2</sub>, while temporal features, including historical air pollutants and weather, are the best predictors for PM<sub>2.5</sub>. For Beijing, historical air pollutant data, traffic congestion, wind direction and seasonal indicator are the best predictors for all pollutants. PM<sub>10</sub> in Hong Kong is achieving the best estimation and forecast accuracy, whilst CO in Beijing is achieving the best results.https://ieeexplore.ieee.org/document/9780279/Fine-grained air pollution estimation and forecastspatial-temporal datadeep learningCNN-LSTMstreet canyon effecttraffic speed |
| spellingShingle | Qi Zhang Yang Han Victor O. K. Li Jacqueline C. K. Lam Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities IEEE Access Fine-grained air pollution estimation and forecast spatial-temporal data deep learning CNN-LSTM street canyon effect traffic speed |
| title | Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities |
| title_full | Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities |
| title_fullStr | Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities |
| title_full_unstemmed | Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities |
| title_short | Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities |
| title_sort | deep air a hybrid cnn lstm framework for fine grained air pollution estimation and forecast in metropolitan cities |
| topic | Fine-grained air pollution estimation and forecast spatial-temporal data deep learning CNN-LSTM street canyon effect traffic speed |
| url | https://ieeexplore.ieee.org/document/9780279/ |
| work_keys_str_mv | AT qizhang deepairahybridcnnlstmframeworkforfinegrainedairpollutionestimationandforecastinmetropolitancities AT yanghan deepairahybridcnnlstmframeworkforfinegrainedairpollutionestimationandforecastinmetropolitancities AT victorokli deepairahybridcnnlstmframeworkforfinegrainedairpollutionestimationandforecastinmetropolitancities AT jacquelinecklam deepairahybridcnnlstmframeworkforfinegrainedairpollutionestimationandforecastinmetropolitancities |