Abstract
The prediction of \({\mathrm{PM}}_{2.5}\) concentration has attracted considerable research efforts in recent years. However, due to the lack of open dataset, the data processed by existing intelligent methods are only values at single stations or mean value in a small region, while the data in real applications are all gridded values in large regions. This incompatibility in data format makes intelligent methods cannot be integrated into the practical process of \({\mathrm{PM}}_{2.5}\) prediction. In this paper, first we build a large dataset with gridded data obtained from the numerical prediction field, then an intelligent prediction method with gridded data as the basic input and output format is proposed. To capture both the spatial and temporal characteristics in data, the ConvLSTM (convolutional long short term memory) model is applied, which can utilize the advantages of both the CNN (convolutional neural network) and LSTM models. However, ConvLSTM has defects in processing multi-feature data: the more features model uses, the worse the forecasting result will be. To improve the prediction accuracy of ConvLSTM further, the attention mechanism is applied, which can describe more accurately the importance of different features and different regions for the prediction accuracy. On the built large dataset of \({\mathrm{PM}}_{2.5}\) gridded concentrations, when we predict the next hour’s value using the past 6 h, the RMSE (root mean square error) of the conventional MLR (multi-linear regression) and ConvLSTM are respectively 6.44 \(\mu \mathrm{g}/{\mathrm{m}}^{3}\) and 6.24 \(\mu \mathrm{g}/{\mathrm{m}}^{3}\), when the attention mechanism is incorporated into ConvLSTM, the RMSE can be decreased to 4.79 \(\mu \mathrm{g}/{\mathrm{m}}^{3}\).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Charlson, R.J., Schwartz, S.E., Hales, J.M., Cess, R.D., Coakley, J.A., Hansen, J.E., Hofmann, D.J.: Climate forcing by anthropogenic aerosols. Science 255(5043), 423–430 (1992). https://doi.org/10.1126/science.255.5043.423
Chen, L,, Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., Chua, TS.: Sca-cnn: spatial and channel-wise attention in convolutional networks for image captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition 2017: 5659–5667 (2017)
Corbetta, M., Shulman, G.L.: Control of goal-directed and stimulus-driven attention in the brain. Nat Rev Neurosci 3(3), 201–215 (2002)
Dockery, D.W., Pope, C.A.R., Xu, X., Spengler, J.D., Ware, J.H., Fay, M.E., Ferris, B.G., Jr., Speizer, F.E.: An association between air pollution and mortality in six U.S. cities. N Engl J Med 329(24), 1753–1759 (1993). https://doi.org/10.1056/NEJM199312093292401
Genc, D.D., Yesilyurt, C., Tuncel, G.: Air pollution forecasting in Ankara, Turkey using air pollution index and its relation to assimilative capacity of the atmosphere. Environ Monit Assess 166, 11–27 (2010)
Graves, A.: Generating sequences with recur- rent neural networks. arXiv preprint. arXiv:1308.0850 (2013)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput 9(8), 1735–1780 (1997)
Hoi, K.V., Yuen, K.M.: Mok, Kalman filter based prediction system for wintertime PM10 concentrations in Macau. Glob NEST J 10, 140–150 (2008)
Hu. J., Shen, L., Sun, G.: Squeeze-and-ex- citation networks. arXiv preprint. arXiv:1709.01507 (2017)
Huang, C.J., Kuo, P.H.: A deep cnn-lstm model for particulate matter (PM2.5) forecasting in smart cities. Sensors 18(7), 2220 (2018)
Inness, A., Ades, M., Agusti-Panareda, A., Barre, J., Benedictow, A., Blechschmidt, A.M., Dominguez, J.J., Engelen, R., Eskes, H., Flemming, J., Huijnen, V., Jones, L., Kipling, Z., Massart, S., Parrington, M., Pench, V.H., Razinger, M., Remy, S., Schulz, M., Suttie, M.: The CAMS reanalysis of atmospheric composition. Atmos Chem Phys 19, 3515–3556 (2019)
Kingma, DP., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint. arXiv:1412.6980 (2014)
Kong, L., et al.: A six-year long (2013–2018) high-resolution air quality reanalysis dataset over China base on the assimilation of surface observations from CNEMC. Earth Syst Sci Data Discuss (2020). https://doi.org/10.5194/essd-13-529-2021
Kuo-lin, H., et al.: Self-organizing linear output map (SOLO): an artificial neural network suitable for hydrologic modeling and analysis. Water Resour Res 38(12), 38–1 (2002)
Laurent, I., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Machine Intel 20(11), 1254–1259 (1998)
Lecun, Y., et al.: Gradient-based learning applied to document recognition. Proc IEEE 86(11), 2278–2324 (1998)
Ma, J., Ding, Y., Gan, V.J.L., et al.: Spatiotemporal prediction of PM2.5 concentrations at different time granularities using IDW-BLSTM. IEEE Access 7, 107897–107907 (2019)
Martin, S.T., Hung, H.M., Park, R.J., Jacob, D.J., Spurr, R.J.D., Chance, K.V., Chin, M.: Effects of the physical state of tropospheric ammonium-sulfate-nitrate particles on global aerosol direct radiative forcing. Atmos Chem Phys 4, 183–214 (2004). https://doi.org/10.5194/acp-4-183-2004
Miyazaki, K., Bowman, K., Sekiya, T., Eskes, H., Boersma, F., Worden, H., Livesey, N., Payne, V.H., Sudo, K., Kanaya, Y., Takigawa, M., Ogochi, K.: Updated tropospheric chemistry reanalysis and emission estimates, TCR-2, for 2005–2018. Earth Syst Sci Data 12, 2223–2259 (2020). https://doi.org/10.5194/essd-12-2223-2020
Nielsen, M.A.: Neural networks and deep learning. Determination press, San Francisco (2015)
Osowski, K.: Garanty, forecasting of the daily meteorological pollution using wavelets and support vector machine. Eng Appl Artif Intell 20, 745–755 (2007)
Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In ICML: 1310–1318 (2013)
Pérez, P., Reyes, J.: An integrated neural network model for PM10 forecasting. Atmos Environ 40, 2845–2851 (2006)
Qi, Y., Li, Q., Karimian, H., Liu, D.: A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory. Sci Total Environ 664, 1–10 (2019)
Randles, C.A., da Silva, A.M., Buchard, V., Colarco, P.R., Darmenov, A., Govindaraju, R., Smirnov, A., Holben, B., Ferrare, R., Hair, J., Shinozuka, Y., Flynn, C.J.: The MERRA-2 aerosol reanalysis, 1980 onward. Part I: system description and data assimilation evaluation. J Clim 30, 6823–6850 (2017)
Shad, R., Mohammad, S.M., Arefeh, S.: Predicting air pollution using fuzzy genetic linear membership kriging in GIS. Comput Environ Urban Syst 33(6), 472–481 (2009)
Shang, T., Deng, J.H., Duan, X.: A novel model for hourly PM2.5 concentration prediction based on CART and EELM. Sci Total Environ 651, 3043–3052 (2019)
Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Adv Neural Inf Process Syst 28, 802–810 (2015)
Sun, W., et al.: Prediction of 24-hour-average PM2.5 concentrations using a hidden Markov model with different emission distributions in Northern California. Sci Total Environ 443, 93–103 (2013)
Sutskever, I., Vinyals, O., Le, QV.: Sequence to sequence learning with neural networks. NIPS: 3104–3112 (2014)
Tang, X., Zhu, J., Wang, Z.F., Gbaguidi, A.: Improvement of ozone forecast over Beijing based on ensemble Kalman filter with simultaneous adjustment of initial conditions and emissions. Atmos Chem Phys 11, 12901–12916 (2011). https://doi.org/10.5194/acp-11-12901-2011
Wang, A.C., Bovik, H.R., Sheikh, and E. P. Simoncelli,: Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4), 600–612 (2004)
Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., Tang, X.: Residual attention network for image classification. arXiv preprint arXiv:1704.06904 (2017)
Woo, S., et al: Cbam: convolutional block attention module. Proceedings of the European conference on computer vision (ECCV) (2018)
Ye, X.N., Ma, Z., Zhang, J.C., Du, H.H., Chen, J.M., Chen, H., Yang, X., Gao, W., Geng, F.H.: Important role of ammonia on haze formation in Shanghai. Environ Res Lett 6, 024019 (2011). https://doi.org/10.1088/1748-9326/6/2/024019
Yi, X., Zhang, J., Wang, Z., Li, T., Zheng, Y.: Deep distributed fusion network for air quality prediction. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2018 Jul 19: 965–973 (2018)
Zhao, F., Deng, Y., Cai, Y., Chen, J.: Long short-term memory-Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. Chemosphere 220, 486–492 (2019)
Zheng, Y., Liu, F., Hsieh, HP.: U-air: when urban air quality inference meets big data. Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining 2013 Aug 11: 1436–1444 (2013)
Zheng, Y., Yi, X., Li, M., Li, R., Shan, Z., Chang, E., Li, T.: Forecasting fine-grained air quality based on big data. InProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2015 Aug 10: 2267–2276 (2015)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Appendix
Appendix
The dataset we used in this paper can been find in https://pan.baidu.com/s/14hXi1PgDhvcqKyXeAac-ww.(password: uewz).
For ease of presentation, Fig.
Comparison of different models, the horizontal axis represents the forecast for each hour and the vertical axis represents RMSE (unit is \({\upmu \text{g/m}}^{{\text{3}}}\))
9 only shows the comparison of the results of the three models, and more model prediction results are shown in Fig.
the comparison of the average predictions
10.
Figure 11 shows the pixel-by-pixel comparisons of different models' predictions, with two hours' results as the example.
Pixel-by-pixel comparison of the prediction
Rights and permissions
About this article
Cite this article
Liu, P., Yao, E., Liu, T. et al. Improvement of AI forecast of gridded PM2.5 forecast in China through ConvLSTM and Attention. CCF Trans. HPC 4, 104–119 (2022). https://doi.org/10.1007/s42514-021-00087-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42514-021-00087-4