Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DSGNN: A Dual-View Supergrid-Aware Graph Neural Network for Regional Air Quality Estimation (2404.01975v1)

Published 2 Apr 2024 in cs.LG

Abstract: Air quality estimation can provide air quality for target regions without air quality stations, which is useful for the public. Existing air quality estimation methods divide the study area into disjointed grid regions, and apply 2D convolution to model the spatial dependencies of adjacent grid regions based on the first law of geography, failing to model the spatial dependencies of distant grid regions. To this end, we propose a Dual-view Supergrid-aware Graph Neural Network (DSGNN) for regional air quality estimation, which can model the spatial dependencies of distant grid regions from dual views (i.e., satellite-derived aerosol optical depth (AOD) and meteorology). Specifically, images are utilized to represent the regional data (i.e., AOD data and meteorology data). The dual-view supergrid learning module is introduced to generate supergrids in a parameterized way. Based on the dual-view supergrids, the dual-view implicit correlation encoding module is introduced to learn the correlations between pairwise supergrids. In addition, the dual-view message passing network is introduced to implement the information interaction on the supergrid graphs and images. Extensive experiments on two real-world datasets demonstrate that DSGNN achieves the state-of-the-art performances on the air quality estimation task, outperforming the best baseline by an average of 19.64% in MAE.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. J. Wei, Z. Li, J. Guo, L. Sun, W. Huang, W. Xue, T. Fan, and M. Cribb, “Satellite-derived 1-KM-resolution PM1 concentrations from 2014 to 2018 across China,” Environmental Science & Technology, vol. 53, no. 22, pp. 13 265–13 274, 2019.
  2. N. K. Arystanbekova, “Application of Gaussian plume models for air pollution simulation at instantaneous emissions,” Mathematics and Computers in Simulation, vol. 67, no. 4, pp. 451–458, 2004.
  3. M. J. Kim, R. J. Park, and J.-J. Kim, “Urban air quality modeling with full O3subscriptO3\text{O}_{3}O start_POSTSUBSCRIPT 3 end_POSTSUBSCRIPT–NOxsubscriptNO𝑥\text{NO}_{x}NO start_POSTSUBSCRIPT italic_x end_POSTSUBSCRIPT–VOC chemistry: Implications for O3subscriptO3\text{O}_{3}O start_POSTSUBSCRIPT 3 end_POSTSUBSCRIPT and PM air quality in a street canyon,” Atmospheric Environment, vol. 47, pp. 330–340, 2012.
  4. A. Rakowska, K. C. Wong, T. Townsend, K. L. Chan, D. Westerdahl, S. Ng, G. Močnik, L. Drinovec, and Z. Ning, “Impact of traffic volume and composition on the air quality and pedestrian exposure in urban street canyon,” Atmospheric Environment, vol. 98, pp. 260–270, 2014.
  5. H. Huang, R. Ooka, H. Chen, S. Kato, T. Takahashi, and T. Watanabe, “CFD analysis on traffic-induced air pollutant dispersion under non-isothermal condition in a complex urban area in winter,” Journal of Wind Engineering and Industrial Aerodynamics, vol. 96, no. 10, pp. 1774–1788, 2008.
  6. G. Hoek, R. Beelen, K. De Hoogh, D. Vienneau, J. Gulliver, P. Fischer, and D. Briggs, “A review of land-use regression models to assess spatial variation of outdoor air pollution,” Atmospheric Environment, vol. 42, no. 33, pp. 7561–7578, 2008.
  7. R. Shad, M. S. Mesgari, and A. Shad, “Predicting air pollution using fuzzy genetic linear membership kriging in GIS,” Computers, Environment and Urban Systems, vol. 33, no. 6, pp. 472–481, 2009.
  8. A. Jutzeler, J. Li, and B. Faltings, “A region-based model for estimating urban air pollution,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2014, pp. 424–430.
  9. Z. B. Patel, P. Purohit, H. M. Patel, S. Sahni, and N. Batra, “Accurate and scalable Gaussian processes for fine-grained air quality inference,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2022, pp. 12 080–12 088.
  10. J. J. Li, A. Jutzeler, B. Faltings, S. Winter, and C. Rizos, “Estimating urban ultrafine particle distributions with Gaussian process models,” Research@ Locate14, pp. 145–153, 2014.
  11. Y. Lin, Y.-Y. Chiang, F. Pan, D. Stripelis, J. L. Ambite, S. P. Eckel, and R. Habre, “Mining public datasets for modeling intra-city PM2.5 concentrations at a fine spatial resolution,” in Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2017, pp. 1–10.
  12. L. Chen, J. Wang, H. Wang, and T. Jin, “Urban air quality assessment by fusing spatial and temporal data from multiple study sources using refined estimation methods,” ISPRS International Journal of Geo-Information, vol. 11, no. 6, pp. 330–345, 2022.
  13. L. Chen, Y. Ding, D. Lyu, X. Liu, and H. Long, “Deep multi-task learning based urban air quality index modelling,” in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 3, no. 1, 2019, pp. 1–17.
  14. W. Cheng, Y. Shen, Y. Zhu, and L. Huang, “A neural attention model for urban air quality inference: Learning the weights of monitoring stations,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2018, pp. 2151–2158.
  15. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Proceedings of the Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 1–11.
  16. Q. Han, D. Lu, and R. Chen, “Fine-grained air quality inference via multi-channel attention model.” in Proceedings of the International Joint Conference on Artificial Intelligence, 2021, pp. 2512–2518.
  17. L. Chen, H. Long, J. Xu, B. Wu, H. Zhou, X. Tang, and L. Peng, “Deep citywide multisource data fusion-based air quality estimation,” IEEE Transactions on Cybernetics, pp. 1–12, 2023.
  18. V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A deep convolutional encoder-decoder architecture for image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 12, pp. 2481–2495, 2017.
  19. J. Song and M. E. Stettler, “A novel multi-pollutant space-time learning network for air pollution inference,” Science of The Total Environment, vol. 811, pp. 152 254–152 265, 2022.
  20. J. Dai, Y. Li, K. He, and J. Sun, “R-FCN: Object detection via region-based fully convolutional networks,” in Proceedings of the Advances in Neural Information Processing Systems, vol. 29, 2016, pp. 1–9.
  21. C. Carnevale, G. Finzi, E. Pisoni, and M. Volta, “Neuro-fuzzy and neural network systems for air quality control,” Atmospheric Environment, vol. 43, no. 31, pp. 4811–4821, 2009.
  22. B. Lv, Y. Hu, H. H. Chang, A. G. Russell, J. Cai, B. Xu, and Y. Bai, “Daily estimation of ground-level PM2.5 concentrations at 4-KM resolution over Beijing-Tianjin-Hebei by fusing MODIS AOD and ground observations,” Science of the Total Environment, vol. 580, pp. 235–244, 2017.
  23. C.-R. Jung, W.-T. Chen, and S. F. Nakayama, “A national-scale 1-KM resolution PM2.5 estimation model over Japan using MAIAC AOD and a two-stage random forest model,” Remote Sensing, vol. 13, no. 18, pp. 3657–3673, 2021.
  24. D. L. Goldberg, P. Gupta, K. Wang, C. Jena, Y. Zhang, Z. Lu, and D. G. Streets, “Using gap-filled MAIAC AOD and WRF-Chem to estimate daily PM2.5 concentrations at 1-KM resolution in the Eastern United States,” Atmospheric Environment, vol. 199, pp. 443–452, 2019.
  25. J. Wei, Z. Li, M. Cribb, W. Huang, W. Xue, L. Sun, J. Guo, Y. Peng, J. Li, A. Lyapustin, L. Liu, H. Wu, and Y. Song, “Improved 1-KM resolution PM2.5 estimates across China using enhanced space–time extremely randomized trees,” Atmospheric Chemistry and Physics, vol. 20, no. 6, pp. 3273–3289, 2020.
  26. G. Geng, Q. Xiao, S. Liu, X. Liu, J. Cheng, Y. Zheng, T. Xue, D. Tong, B. Zheng, and Y. Peng, “Tracking air pollution in China: Near real-time PM2.5 retrievals from multisource data fusion,” Environmental Science & Technology, vol. 55, no. 17, pp. 12 106–12 115, 2021.
  27. T. Jiang, B. Chen, Z. Nie, Z. Ren, B. Xu, and S. Tang, “Estimation of hourly full-coverage PM2.5 concentrations at 1-KM resolution in China using a two-stage random forest model,” Atmospheric Research, vol. 248, pp. 105 146–105 157, 2021.
  28. J. Han, H. Liu, H. Xiong, and J. Yang, “Semi-supervised air quality forecasting via self-supervised hierarchical graph neural network,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 5, pp. 5230–5243, 2022.
  29. J. Han, H. Liu, H. Zhu, and H. Xiong, “Kill two birds with one stone: A multi-view multi-adversarial learning approach for joint air quality and weather prediction,” IEEE Transactions on Knowledge and Data Engineering, pp. 11 515–11 528, 2023.
  30. Z. Li, H. Zhang, Y.-H. Juan, C.-Y. Wen, and A.-S. Yang, “Effects of building setback on thermal comfort and air quality in the street canyon,” Building and Environment, vol. 208, pp. 108 627–108 639, 2022.
  31. K. Shukla, P. Kumar, G. S. Mann, and M. Khare, “Mapping spatial distribution of particulate matter using kriging and inverse distance weighting at supersites of megacity Delhi,” Sustainable Cities and Society, vol. 54, pp. 101 997–102 007, 2020.
  32. Y. Zheng, F. Liu, and H.-P. Hsieh, “U-Air: When urban air quality inference meets big data,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2013, pp. 1436–1444.
  33. L. Chen, Y. Cai, Y. Ding, M. Lv, C. Yuan, and G. Chen, “Spatially fine-grained urban air quality estimation using ensemble semi-supervised learning and pruning,” in Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2016, pp. 1076–1087.
  34. M. Lv, Y. Li, L. Chen, and T. Chen, “Air quality estimation by exploiting terrain features and multi-view transfer semi-supervised regression,” Information Sciences, vol. 483, pp. 82–95, 2019.
  35. A. Blum and T. Mitchell, “Combining labeled and unlabeled data with co-training,” in Proceedings of the Conference on Computational Learning Theory, 1998, pp. 92–100.
  36. S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345–1359, 2009.
  37. H. Cai, V. W. Zheng, and K. C.-C. Chang, “A comprehensive survey of graph embedding: Problems, techniques, and applications,” IEEE Transactions on Knowledge and Data Engineering, vol. 30, no. 9, pp. 1616–1637, 2018.
  38. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016.
  39. E. R. Bonet, T. H. Do, X. Qin, J. Hofman, V. P. La Manna, W. Philips, and N. Deligiannis, “Explaining graph neural networks with topology-aware node selection: Application in air quality inference,” IEEE Transactions on Signal and Information Processing over Networks, vol. 8, pp. 499–513, 2022.
  40. Q. Zhang, Y. Han, V. O. Li, and J. C. Lam, “Deep-AIR: A hybrid CNN-LSTM framework for fine-grained air pollution estimation and forecast in metropolitan cities,” IEEE Access, vol. 10, pp. 55 818–55 841, 2022.
  41. L. Chen, W. Shao, M. Lv, W. Chen, Y. Zhang, and C. Yang, “AARGNN: An attentive attributed recurrent graph neural network for traffic flow prediction considering multiple dynamic factors,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 10, pp. 17 201–17 211, 2022.
  42. Y. Zhao, X. Luo, W. Ju, C. Chen, X.-S. Hua, and M. Zhang, “Dynamic hypergraph structure learning for traffic flow forecasting,” in Proceedings of the IEEE International Conference on Data Engineering, 2023, pp. 2303–2316.
  43. Y. Yang, C. Huang, L. Xia, Y. Liang, Y. Yu, and C. Li, “Multi-behavior hypergraph-enhanced transformer for sequential recommendation,” in Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 2263–2274.
  44. H.-F. Yu, N. Rao, and I. S. Dhillon, “Temporal regularized matrix factorization for high-dimensional time series prediction,” in Proceedings of the Advances in Neural Information Processing Systems, vol. 29, 2016, pp. 1–9.
  45. R. Sen, H.-F. Yu, and I. S. Dhillon, “Think globally, act locally: A deep neural network approach to high-dimensional time series forecasting,” in Proceedings of the Advances in Neural Information Processing Systems, vol. 32, 2019, pp. 101–109.
  46. M. Roughan, Y. Zhang, W. Willinger, and L. Qiu, “Spatio-temporal compressive sensing and internet traffic matrices (extended version),” IEEE/ACM Transactions on Networking, vol. 20, no. 3, pp. 662–676, 2012.
  47. Z. Zhang, J. Bu, M. Ester, J. Zhang, Z. Li, C. Yao, H. Dai, Z. Yu, and C. Wang, “Hierarchical multi-view graph pooling with structure learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 1, pp. 545–559, 2021.
  48. M. Stafoggia, T. Bellander, S. Bucci, M. Davoli, K. De Hoogh, F. De’Donato, C. Gariazzo, A. Lyapustin, P. Michelozzi, and M. Renzi, “Estimation of daily PM10 and PM2.5 concentrations in Italy, 2013–2015, using a spatiotemporal land-use random-forest model,” Environment International, vol. 124, pp. 170–179, 2019.
  49. Q. Xiao, Y. Wang, H. H. Chang, X. Meng, G. Geng, A. Lyapustin, and Y. Liu, “Full-coverage high-resolution daily PM2.5 estimation using MAIAC AOD in the Yangtze River Delta of China,” Remote Sensing of Environment, vol. 199, pp. 437–446, 2017.
  50. L. Breiman, “Random Forests,” Machine Learning, vol. 45, pp. 5–32, 2001.
  51. Z. Wu, S. Pan, G. Long, J. Jiang, X. Chang, and C. Zhang, “Connecting the dots: Multivariate time series forecasting with graph neural networks,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2020, pp. 753–763.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets