Abstract
In order to improve the accuracy of short-term PM2.5 prediction, we proposed a new hybrid solution that combines several machine learning techniques. Firstly, a set of phase space features are obtained from PM2.5 historical data based on PSR technique and combined with numerical weather prediction (NWP) data to construct a pool of candidate features. Secondly, the optimal feature subset is selected and input to the multi-step ahead prediction model based on the RReliefF feature selection algorithm. Then, K-means clustering is used to divide the input instances into a number of subsets to train ANFIS. Finally, the particle swarm optimization (PSO) algorithm is used to optimize the ANFIS network’s parameters. In order to verify the effectiveness of the proposed method, two benchmark models (PSR-FS, PCA-FS) were established to compare with the hybrid model. The experimental results showed that the hybrid solution obtained the best prediction performance in short-term PM2.5 prediction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Byun, D., Schere, K.L.: Review of the governing equations, computational algorithms, and other components of the models-3 community multiscale air quality (CMAQ) modeling system. Appl. Mech. Rev. 59(2), 51–77 (2006)
Konopka, P., Groo, J.U., Günther, G.: Annual cycle of ozone at and above the tropical tropopause: observations versus simulations with the Chemical Lagrangian Model of the Stratosphere (CLa MS). Atmos. Chem. Phys. 10(1), 121–132 (2010)
Lee, H.M., Park, R.J., Henze, D.K.: PM2.5 source attribution for Seoul in May from 2009 to 2013 using GEOS-Chem and its adjoint model. Environ. Pollut. 221(1), 377–384 (2017)
Hu, Y.-S., Duan, H.-M.: Study on PM_(2.5) dispersion and prediction based on Gaussian plume and multiple linear regression model. Arid Zone Res. Environ. 29(6), 86–92 (2016)
Liu, T.: Time series forecasting of air quality based on regional numerical modeling in Hong Kong. J. Geophys. Res. Atmos. 123(8), 4175–4196 (2018)
Lili, L., Xuan, Z., Du, M.: Research on PM2.5 prediction based on generalized additive model. Math. Stat. Manag. 39(5), 811–823 (2020)
Liu, Q., Chen, H.Y.: PM_(2.5) mass concentration prediction based on empowered KNN-LSTM model. J. Hefei Univ. Technol. Nat. Sci. Ed. 44(12), 1690–1698 (2021)
Li, X., Luo, A., Li, J., Li, Y.: Air pollutant concentration forecast based on support vector regression and quantum-behaved particle swarm optimization. Environ. Model. Assess. 24(2), 205–222 (2018). https://doi.org/10.1007/s10666-018-9633-3
Jing, L.A.: Estimation of monthly 1 km resolution PM 2.5 concentrations using a random forest model over “2+26” cities, China. Urban Clim. 35(1), 95–109 (2021)
Jin, X.B., Zhang, J.F., Wang, S.Y.: Wavelet decomposition-based PM2.5 deep mixing prediction model. In: 31st China Process Control Conference (CPCC2020), Suzhou, China, vol. 63, pp. 1–9 (2021)
Teng, M., Li, S., Xing, J.: 24-Hour prediction of PM2.5 concentrations by combining empirical mode decomposition and bidirectional long short-term memory neural network. Sci. Total Environ. 821, 153276 (2022)
Qin, X.W.: PM2.5 prediction in Beijing based on overall empirical modal decomposition and support vector regression. J. Jilin University (Earth Sci. Ed.) 46(2), 563–568 (2016)
Lu, Z.-B., Cai, Z.-M., Jiang, K.-Y.: Parameter selection for phase space reconstruction based on improved C-C method. J. Syst. Simul. 19(11), 2527–2538 (2007)
Kim, H.S., Eykholt, R., Salas, J.D.: Nonlinear dynamics, delay times, and embedding windows. Physica D 127(1–2), 48–60 (1999)
Wu, J.H.: Complex network link classification based on RReliefF feature selection algorithm. Comput. Eng. 43(8), 208–214 (2017)
Yuting, K., Fuxiang, T., Xin, Z.: A review of K-means algorithm optimization research based on differential privacy. Comput. Sci. 49(2), 162–173 (2022)
Jang, J.-S.R.: ANFIS: adaptive- network- based fuzzy inference system. IEEE Trans. Syst. Man Cybern. 23(4), 665–685 (1993)
Bai, D.D., He, J.H., Wang, X.J.: Adaptive particle swarm support vector machine wind speed combined forecasting model. Acta energiae solaris sinica 36(4), 792–797 (2015)
Acknowledgments
This work is supported in part by Guangdong Province Key Construction Discipline Scientific Research Ability Promotion Project unser grant 2021ZDJS132, and in part by Guangdong Innovative Projects with Characteristics in Colleges and Universities under grants 2019KTSCX228 and 2021ZDZX4048.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Y., Yuan, J., Xu, Y., Chen, Y. (2023). Multi-step Ahead PM2.5 Prediction Based on Hybrid Machine Learning Techniques. In: Sun, Y., et al. Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2022. Communications in Computer and Information Science, vol 1681. Springer, Singapore. https://doi.org/10.1007/978-981-99-2356-4_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-2356-4_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2355-7
Online ISBN: 978-981-99-2356-4
eBook Packages: Computer ScienceComputer Science (R0)
