Abstract
Environmental monitoring departments in China adopt multiple air quality prediction models, each behaving differently depending on the scenario. Integrated methods are needed to obtain an integrated model with higher accuracy and adaptability. In relation to this, the most similar interpolation algorithm is often used to deal with missing data. We assigned different weights to six existing models based on the most similar value and Pearson coefficient. Then, we used the bootstrap algorithm for data augmentation. Next, we used multiple air quality prediction models for the proposed integrated model called the SIM-PB-Wavelet model. The experiment results show that the mean square root error and the Theil inequality coefficient of the model are lower than those of the six other models. Specifically, the RMSE is reduced by 36% and the TIC is reduced by 33.3% compared with the best results of the six models, thus indicating the ability of the integrated model to improve prediction accuracy.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Garcia, A.R., Mar-Morales, B.E., Ruiz-Surez, L.G.: Numerical air quality forecast modeling system: Mexico case study. In: Recent Advances in Fluid Dynamics with Environmental Applications. Springer (2016)
Im, U., Bianconi, R., Solazzo, E., et al.: Evaluation of operational on-line-coupled regional air quality models over Europe and North America in the context of AQMEII phase 2. Part I: Ozone. Atmos. Environ. 115(2), 404–420 (2015)
Eckhardt, S., Quennehen, B., Olivi, D.J.L., et al.: Current model capabilities for simulating black carbon and sulfate concentrations in the Arctic atmosphere: a multi-model evaluation using a comprehensive measurement data set. Atmos. Chem. Phys. Discuss. 15(7), 10425–10477 (2015)
Holstein, S.V., Carlaxel, S.: An experiment in probabilistic weather forecasting. J. Appl. Meteorol. 10(4), 635–645 (1971)
Krishnamurti, T.N., Kishtawal, C.M., Larow, T.E., et al.: Improved weather and seasonal climate forecasts from multimodel superensemble. Science 285(5433), 1548 (1999)
Monache, L.D., Stull, R.B.: An ensemble air-quality forecast over western Europe during an ozone episode. Atmos. Environ. 37(25), 3469–3474 (2003)
Wang, Z.F., Wu, Q.Z., Gbaguidi, A., et al.: Ensemble air quality multi-model forecast system for Beijing (EMS-Beijing): model description and preliminary application. J. Nanjing Univ. Inf. Sci. Technol. 1, 19–26 (2009)
Huang, S., Zhang, M., Xie, B.G., et al.: Multi-model blending method and application on reducing the uncertainty of air quality models. In: EGU General Assembly Conference. EGU General Assembly Conference Abstracts (2017)
Chen, H., Wang, Z., Qizhong, W.U., et al.: Application of air quality multi-model forecast system in Guangzhou: model description and evaluation of PM10 forecast performance. Clim. Environ. Res. 18(4), 427–435 (2013)
Zhang, W., Wang, Z., Junling, A.N., et al.: Update the ensemble air quality modeling system with BP model during Beijing Olympics. Clim. Environ. Res. 15(5), 595–601 (2010)
Bai, Y., Li, Y., Wang, X., et al.: Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions. Atmos. Pollut. Res. 7(3), 557–566 (2016)
Chen, Y., Yang, B., Dong, J.: Time-series prediction using a local linear wavelet neural network. Neurocomputing 69(4–6), 449–465 (2006)
Gwo-Ching, L.: Hybrid improved differential evolution and wavelet neural network with load forecasting problem of air conditioning. Int. J. Electr. Power Energy Syst. 61(1), 673–682 (2014)
Wang, X., Zhang, Y., Zhao, S.: Air quality forecasting based on dynamic granular wavelet neural network. Comput. Eng. Appl. 49(6), 221–224 (2013)
Zhang, Q.G., Benveniste, A.: A wavelet networks. IEEE Trans. Neural Netw. 3(6), 889–898 (1992)
Goltsev, A.V., Dorogovtsev, S.N., Mendes, J.F.: k-core (bootstrap) percolation on complex networks: critical phenomena and nonlocal effects. Phys. Rev. E Stat. Nonlinear Soft Matter Phys. 73(5 Pt 2), 056101 (2006)
Yong, K.L., Lee, S.J., Park, J.: Tag-based object similarity computation using term space dimension reduction. In: International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 790–791. ACM (2009)
Benesty, J., Chen, J., Huang, Y., et al.: Pearson correlation coefficient. In: Noise Reduction in Speech Processing, pp. 1–4. Springer, Heidelberg (2009)
Chen, Z., Feng, T.J., Chen, G.: A kind of BP algorithm-learning wavelet neural network. J. Ocean Univ. Qingdao 1, 122–128 (2001)
Ul-Saufie, A., Yahya, A., Ramli, N.: Improving multiple linear regression model using principal component analysis for predicting PM10 concentration in Seberang Prai, Pulau Pinang. Int. J. Environ. Sci. 2, 403 (2011)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Zhao, H., Wang, Y. (2018). Integrated Model of the Wavelet Neural Network Based on the Most Similar Interpolation Algorithm and Pearson Coefficient. In: Barolli, L., Xhafa, F., Javaid, N., Spaho, E., Kolici, V. (eds) Advances in Internet, Data & Web Technologies. EIDWT 2018. Lecture Notes on Data Engineering and Communications Technologies, vol 17. Springer, Cham. https://doi.org/10.1007/978-3-319-75928-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-75928-9_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75927-2
Online ISBN: 978-3-319-75928-9
eBook Packages: EngineeringEngineering (R0)