Forecasting Fine-Grained Air Quality for Locations without Monitoring Stations Based on a Hybrid Predictor with Spatial-Temporal Attention Based Network
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Quality Monitoring and Forecasting · Air Quality and Health Impacts · Vehicle emissions and performance
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, National Cheng Kung University, Tainan 70101, Taiwan
Institute of Computer, Communication Engineering, National Cheng Kung University, Tainan 70101, Taiwan
Department of Medical Imaging, Chi Mei Medical Center, Tainan 710402, Taiwan
Department of Health and Nutrition, Chia Nan University of Pharmacy and Science, Tainan 71710, Taiwan
Institute of Biomedical Sciences, National Sun Yat-sen University, Kaohsiung 80424, Taiwan
College of Arts and Humanities, Swansea University, Swansea SA2 8PP, UK
Research Center for Information Technology Innovation, Academia Sinica, Taipei 115201, Taiwan
Funding
Ministry of Science and Technology
References (27)
Show source-provided references
1. The impact of PM2.5 on the human respiratory system
2. Impact of lockdown measures to combat Covid-19 on air quality over western Europe10.1016/j.scitotenv.2020.140426 ↗
3. Spatial-temporal analysis and projection of extreme particulate matter (PM10 and PM2.5) levels using association rules: A case study of the Jing-Jin-Ji region, China10.1016/j.atmosenv.2015.09.006 ↗
4. Zheng, Y., Yi, X., Li, M., Li, R., Shan, Z., Chang, E., and Li, T. (2015, January 10–13). Forecasting fine-grained air quality based on big data. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia.10.1145/2783258.2788573 ↗
5. Hsieh, H.P., Lin, S.D., and Zheng, Y. (2015, January 10–13). Inferring air quality for station location recommendation based on urban big data. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia.10.1145/2783258.2783344 ↗
6. Le, V.D., Bui, T.C., and Cha, S.K. (2020, January 19–22). Spatiotemporal deep learning model for citywide air pollution interpolation and prediction. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Korea.10.1109/BigComp48618.2020.00-99 ↗
7. Forecasting daily maximum surface ozone concentrations in Brunei Darussalam—An ARIMA modeling approach10.1080/10473289.2004.10470949 ↗
8. On the use of numerical modelling for near-field pollutant dispersion in urban environments—A review10.1016/j.envpol.2015.07.039 ↗
9. Rybarczyk, Y., and Zalakeviciute, R. (2018). Machine learning approaches for outdoor air quality modelling: A systematic review. Appl. Sci., 8.10.3390/app8122570 ↗
10. Xayasouk, T., Lee, H., and Lee, G. (2020). Air pollution prediction using long short-term memory (LSTM) and deep autoencoder (DAE) models. Sustainability, 12.10.3390/su12062570 ↗
11. Zheng, Y., Liu, F., and Hsieh, H.P. (2013, January 11–14). U-air: When urban air quality inference meets big data. Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, USA.10.1145/2487575.2488188 ↗
12. Cheng, W., Shen, Y., Zhu, Y., and Huang, L. (2018, January 2–7). A neural attention model for urban air quality inference: Learning the weights of monitoring stations. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11871 ↗
13. Lin, Y., Mago, N., Gao, Y., Li, Y., Chiang, Y.Y., Shahabi, C., and Ambite, J.L. (2018, January 6–9). Exploiting spatiotemporal patterns for accurate air quality forecasting using deep learning. Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle, WA, USA.10.1145/3274895.3274907 ↗
14. Deep multi-task learning based urban air quality index modelling
15. A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory10.1016/j.scitotenv.2019.01.333 ↗
16. Deep air learning: Interpolation, prediction, and feature analysis of fine-grained air quality10.1109/TKDE.2018.2823740 ↗
17. Adaptive deep learning-based air quality prediction model using the most relevant spatial-temporal relations10.1109/ACCESS.2018.2849820 ↗
18. Li, L., Zhang, X., Holt, J.B., Tian, J., and Piltner, R. (2011, January 17–18). Spatiotemporal interpolation methods for air pollution exposure. Proceedings of the Ninth Symposium of Abstraction, Reformulation, and Approximation, Catalonia, Spain.
19. Comparison of spatial interpolation methods for the estimation of air quality data10.1038/sj.jea.7500338 ↗
20. Lin, Y., Chiang, Y.Y., Pan, F., Stripelis, D., Ambite, J.L., Eckel, S.P., and Habre, R. (2017, January 7–10). Mining public datasets for modeling intra-city PM2.5 concentrations at a fine spatial resolution. Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Redondo Beach, CA, USA.10.1145/3139958.3140013 ↗
21. Zhao, X., Xu, T., Fu, Y., Chen, E., and Guo, H. (2017, January 18–21). Incorporating spatio-temporal smoothness for air quality inference. Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA.10.1109/ICDM.2017.158 ↗
22. Wang, H. (2021, November 10). Air Pollution and Meteorological Data in Beijing 2016–2017. Available online: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/RGWV8X.
23. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
24. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–7). Attention is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
25. Srivastava, N., Mansimov, E., and Salakhudinov, R. (2015, January 6–11). Unsupervised learning of video representations using lstms. Proceedings of the International Conference on Machine Learning. PMLR, Lille, France.
26. Appice, A., Ciampi, A., Fumarola, F., and Malerba, D. (2014). Missing sensor data interpolation. Data Mining Techniques in Sensor Networks, Springer.10.1007/978-1-4471-5454-9 ↗
27. Greedy function approximation: A gradient boosting machine10.1214/aos/1013203451 ↗