Abstract
GNSS vertical time series are non-stationary, non-linear, noisy, etc. Based on the in-depth study of the Prophet prediction model and Empirical wavelet transform (EWT), Aiming at the poor effect of the decomposed trend item and the single cycle item in the Prophet prediction process, an improved Prophet prediction method using EWT is proposed. First, the original time series is decomposed by EWT. Then, prophet prediction is performed on every component and the predicted time series signal is reconstructed. Finally, the accuracy and reliability of the prediction result are verified. This paper uses the measured GNSS vertical time series data from BJFS, WUHN and URUM stations provided by China Earthquake Administration to conduct four short-term prediction experiments with different time spans. The results show that the improved model can better represent the change trend of the original time series. Compared with the single model, its prediction effect is increased by 31.5%, 35.03%, 19.32%, 10.76% in the root mean square error, respectively. The average percentage error increased by 32.76%, 43.61%, 29.28%, 14%, respectively. It shows that the improved model has better short-term prediction effect and better applicability.
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
Chang, T., Guo, Z., Xu, L., et al.: Scale prediction of AQI based on Prophet-random forest optimization model. Environ. Pollut. Control 41(07), 758–761+766 (2019)
Daubechies, I.: Ten Lectures on Wavelets. Society for Industrial and Applied Mathematics, Philadelphia (1992)
Dong, Y.: The error processing and trend prediction of GNSS deformation monitoring coordinate time series in strong interference environment. Wuhan University of Technology (2016)
Gilles, J.: Empirical wavelet transform. IEEE Trans. Sig. Process. 61(16), 3999–4010 (2013)
Ge, N., Sun, L., Shi, X., et al.: Research on sales prediction of Prophet-LSTM combination model. Comput. Sci. 46(S1), 446–451 (2019)
He, X., Hua, X., Lu, T., et al.: Effect of time span on GPS time series noise model and velocity estimation. J. Natl. Univ. Defense Technol. 39(06), 12–18 (2017)
Jiang, W., Wang, K., Li, Z., et al.: Prospect and theory of GNSS coordinate time series analysis. Geomat. Inf. Sci. Wuhan Univ. 43(12), 2112–2123 (2018)
Li, S., Sun, X., Yin, L., et al.: A GPS height time series prediction method based on chaos theory and LSTM. J. Navig. Position. 8(1), 65–73 (2020). https://doi.org/10.16547/j.cnki.10-1096.20200112
Li, L., Duan, G., Wang, J.: Reserve prediction of bank outlets based on prophet framework. J. Cent. South Univ. (Sci. Technol.) 50(01), 75–82 (2019)
Ming, F., Yang, Y., Zeng, A., Jing, Y.: Analysis of seasonal signals and long-term trends in the height time series of IGS sites in China. Sci. China Earth Sci. 59(6), 1283–1291 (2016). https://doi.org/10.1007/s11430-016-5285-9
Kai, N., Fanghua, H., Dong, F., et al.: Research on predictioning method of electric power material demand based on prophet algorithm. Sci. Technol. Innov. 33, 163–164 (2020)
Acharya, R., Roy, B., Sivaraman, M.R., Dasgupta, A.: Prediction of ionospheric total electron content using adaptive neural network with in-situ learning algorithm. Adv. Space Res. 47(1), 115–123 (2010)
Sun, G., Liang, Z., Yu, N., et al.: Short-term wind power probability density predictioning based on EWT and quantile regression forest. Electric Power Autom. Equip. 38(08), 158–165 (2018)
Su, L., Ding, X., Zhang, Y., et al.: Study on coordinate time series of Shaanxi continuous GPS reference stations. J. Geodesy Geodyn. 34(05), 106–109+113 (2014)
Taylor, S.J., Letham, B.: Predictioning at scale. Am. Stat. 72(1), 100–108 (2017)
Wang, X., Li, Q., Zheng, S.: Short-term wind power prediction based on EWT-ESN. Acta Energiae Solaris Sinica 39(03), 633–642 (2018)
Wang, Y.: Research on adaptive filter denoising method based on component decomposition. Harbin Institute of Technology (2017)
Zhang, H., Lu, D., Wen, H., et al.: Analysis method of IGS station height time series based on CEEMD. Remote Sens. Inf. 34(06), 1–5 (2019)
Zhang, M., Liu, P., Zhou, H., et al.: Comparison and analysis of the accuracy of two vertical coordinate predictioning models. Eng. Surv. Mapp. 28(04), 13–18 (2019)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tao, R., Lu, T., Cheng, Y., He, X., Wang, X. (2021). An Improved GNSS Vertical Time Series Prediction Model Using EWT. In: Yang, C., Xie, J. (eds) China Satellite Navigation Conference (CSNC 2021) Proceedings. Lecture Notes in Electrical Engineering, vol 774. Springer, Singapore. https://doi.org/10.1007/978-981-16-3146-7_28
Download citation
DOI: https://doi.org/10.1007/978-981-16-3146-7_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3145-0
Online ISBN: 978-981-16-3146-7
eBook Packages: EngineeringEngineering (R0)