Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network
Air pollution in cities is a severe and worrying problem because it causes threats to economic development and health. Furthermore, with the development of industry and technology, rapid population growth, and the massive expansion of cities, the total amount of pollution emissions continue to incre...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4268 |
| _version_ | 1797505732347691008 |
|---|---|
| author | Hsun-Ping Hsieh Su Wu Ching-Chung Ko Chris Shei Zheng-Ting Yao Yu-Wen Chen |
| author_facet | Hsun-Ping Hsieh Su Wu Ching-Chung Ko Chris Shei Zheng-Ting Yao Yu-Wen Chen |
| author_sort | Hsun-Ping Hsieh |
| collection | DOAJ |
| description | Air pollution in cities is a severe and worrying problem because it causes threats to economic development and health. Furthermore, with the development of industry and technology, rapid population growth, and the massive expansion of cities, the total amount of pollution emissions continue to increase. Hence, observing and predicting the air quality index (AQI), which measures fatal pollutants to humans, has become more and more critical in recent years. However, there are insufficient air quality monitoring stations for AQI observation because the construction and maintenance costs are too high. In addition, finding an available and suitable place for monitoring stations in cities with high population density is difficult. This study proposes a spatial-temporal model to predict the long-term AQI in a city without monitoring stations. Our model calculates the spatial-temporal correlation between station and region using an attention mechanism and leverages the distance information between all existing monitoring stations and target regions to enhance the effectiveness of the attention structure. Furthermore, we design a hybrid predictor that can effectively combine the time-dependent and time-independent predictors using the dynamic weighted sum. Finally, the experimental results show that the proposed model outperforms all the baseline models. In addition, the ablation study confirms the effectiveness of the proposed structures. |
| first_indexed | 2024-03-10T04:23:04Z |
| format | Article |
| id | doaj.art-9aa4a78a62794513b534d49661668397 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:23:04Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9aa4a78a62794513b534d496616683972023-11-23T07:46:38ZengMDPI AGApplied Sciences2076-34172022-04-01129426810.3390/app12094268Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based NetworkHsun-Ping Hsieh0Su Wu1Ching-Chung Ko2Chris Shei3Zheng-Ting Yao4Yu-Wen Chen5Department of Electrical Engineering, National Cheng Kung University, Tainan 70101, TaiwanDepartment of Electrical Engineering, National Cheng Kung University, Tainan 70101, TaiwanDepartment of Medical Imaging, Chi Mei Medical Center, Tainan 710402, TaiwanCollege of Arts and Humanities, Swansea University, Swansea SA2 8PP, UKInstitute of Computer, Communication Engineering, National Cheng Kung University, Tainan 70101, TaiwanResearch Center for Information Technology Innovation, Academia Sinica, Taipei 115201, TaiwanAir pollution in cities is a severe and worrying problem because it causes threats to economic development and health. Furthermore, with the development of industry and technology, rapid population growth, and the massive expansion of cities, the total amount of pollution emissions continue to increase. Hence, observing and predicting the air quality index (AQI), which measures fatal pollutants to humans, has become more and more critical in recent years. However, there are insufficient air quality monitoring stations for AQI observation because the construction and maintenance costs are too high. In addition, finding an available and suitable place for monitoring stations in cities with high population density is difficult. This study proposes a spatial-temporal model to predict the long-term AQI in a city without monitoring stations. Our model calculates the spatial-temporal correlation between station and region using an attention mechanism and leverages the distance information between all existing monitoring stations and target regions to enhance the effectiveness of the attention structure. Furthermore, we design a hybrid predictor that can effectively combine the time-dependent and time-independent predictors using the dynamic weighted sum. Finally, the experimental results show that the proposed model outperforms all the baseline models. In addition, the ablation study confirms the effectiveness of the proposed structures.https://www.mdpi.com/2076-3417/12/9/4268air quality predictiondeep learningspatial-temporal attention |
| spellingShingle | Hsun-Ping Hsieh Su Wu Ching-Chung Ko Chris Shei Zheng-Ting Yao Yu-Wen Chen Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network Applied Sciences air quality prediction deep learning spatial-temporal attention |
| title | Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network |
| title_full | Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network |
| title_fullStr | Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network |
| title_full_unstemmed | Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network |
| title_short | Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network |
| title_sort | forecasting fine grained air quality for locations without monitoring stations based on a hybrid predictor with spatial temporal attention based network |
| topic | air quality prediction deep learning spatial-temporal attention |
| url | https://www.mdpi.com/2076-3417/12/9/4268 |
| work_keys_str_mv | AT hsunpinghsieh forecastingfinegrainedairqualityforlocationswithoutmonitoringstationsbasedonahybridpredictorwithspatialtemporalattentionbasednetwork AT suwu forecastingfinegrainedairqualityforlocationswithoutmonitoringstationsbasedonahybridpredictorwithspatialtemporalattentionbasednetwork AT chingchungko forecastingfinegrainedairqualityforlocationswithoutmonitoringstationsbasedonahybridpredictorwithspatialtemporalattentionbasednetwork AT chrisshei forecastingfinegrainedairqualityforlocationswithoutmonitoringstationsbasedonahybridpredictorwithspatialtemporalattentionbasednetwork AT zhengtingyao forecastingfinegrainedairqualityforlocationswithoutmonitoringstationsbasedonahybridpredictorwithspatialtemporalattentionbasednetwork AT yuwenchen forecastingfinegrainedairqualityforlocationswithoutmonitoringstationsbasedonahybridpredictorwithspatialtemporalattentionbasednetwork |