Abstract
A number of studies have attempted to reduce the effect of observation errors on Global Navigation Satellite Systems positioning through empirical error models. However, due to the complex spatiotemporal characteristics of observation errors, the effects of these errors cannot be eliminated, resulting in the unmodeled error in the positioning results. Although many studies have been carried out on unmodeled error mitigation, most of which only focus on positioning model optimization and fail to make use of historical observation data. We explore the relationship between unmodeled error and observation features and develop a new data-driven approach based on machine learning. Historical observations of a specific station are used to predict the unmodeled error of a positioning model. Time–frequency analysis is used to evaluate the prediction results. The feasibility of applying the method to the precise point positioning (PPP) kinematic positioning is verified by using IGS station data. It is clear from the findings that the data-driven model can effectively predict the unmodeled errors in GNSS positioning, especially in low-frequency components. In addition, the influencing factors of the method are explored in detail and the relevant settings are recommended.
Similar content being viewed by others
Data availability
The raw/processed data required to reproduce the findings of this study are available from the International GNSS Service.
References
Abadi M et al (2016) Tensorflow: a system for large-scale machine learning. In: 12th symposium on operating systems design and implementation, Savannah, USA, 2–4 Nov 2016, pp 265–283
Addison PS (2017) The illustrated wavelet transform handbook: introductory theory and applications in science, engineering, medicine, and finance. CRC Press
Bevis M, Brown A (2014) Trajectory models and reference frames for crustal motion geodesy. J Geod 88:283–311. https://doi.org/10.1007/s00190-013-0685-5
Bevis M, Bedford J, Caccamise DJ II (2020) The art and science of trajectory modelling. In: Montillet JP, Bos M (eds) Geodetic time series analysis in earth sciences. Springer Geophysics. Springer, Cham. https://doi.org/10.1007/978-3-030-21718-1_1
Bos MS, Montillet JP, Williams SDP, Fernandes RMS (2020) Introduction to geodetic time series analysis. In: Montillet JP, Bos M (eds) Geodetic time series analysis in earth sciences. Springer Geophysics. Springer, Cham. https://doi.org/10.1007/978-3-030-21718-1_2
Buduma N, Locascio N (2017) Fundamentals of deep learning: designing next-generation machine intelligence algorithms. O’Reilly Media, Inc.
Chen L, Ali-LöyttyPiche´ SR, Wu L (2012) Mobile tracking in mixed line-of-sight/non-line-of-sight conditions: algorithm and theoretical lower bound. Wirel Pers Commun 65(4):753–771
Chen L, Piché R, Kuusniemi H, Chen R (2014) Adaptive mobile tracking in unknown non-line-of-sight conditions with application to digital TV networks EURASIP. J Adv Signal Process 1:22
Chen L et al (2017) Robustness, security and privacy in location-based services for future IoT: a survey. IEEE Access 5:8956–8977
Choi K, Bilich A, Larson KM, Axelrad P (2004) Modified sidereal filtering: implications for high-rate GPS positioning. Geophys Res Lett. https://doi.org/10.1029/2004GL021621
Dong D, Fang P, Bock Y, Webb F, Prawirodirdjo L, Kedar S, Jamason P (2006) Spatiotemporal filtering using principal component analysis and Karhunen–Loeve expansion approaches for regional GPS network analysis. J Geophys Res. https://doi.org/10.1029/2005JB003806C
Dong D, Wang M, Chen W, Zeng Z, Song L, Zhang Q, Cai M, Cheng Y, Lv J (2016) Mitigation of multipath effect in GNSS short baseline positioning by the multipath hemispherical map. J Geodesy 90(3):255–262
Engels O (2020) Stochastic modelling of geophysical signal constituents within a Kalman filter framework. In: Montillet JP, Bos M (eds) Geodetic time series analysis in earth sciences. Springer Geophysics. Springer, Cham. https://doi.org/10.1007/978-3-030-21718-1_8
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge
Gruszczynska M, Rosat S, Klos A et al (2018) Multichannel singular spectrum analysis in the estimates of common environmental effects affecting GPS observations. Pure Appl Geophys 175:1805–1822. https://doi.org/10.1007/s00024-018-1814-0
Gulli A, Pal S (2017) Deep learning with Keras. Packt Publishing Ltd, Birmingham
Hoque M, Jakowski N (2008) Mitigation of higher order ionospheric effects on GNSS users in Europe. GPS Solut 12(2):87–97
Hsu L-T (2017) GNSS multipath detection using a machine learning approach. In: 2017 IEEE 20th international conference on intelligent transportation systems (ITSC), Yokohama, Japan, 16–19 Aug 2017. IEEE
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: ICLR2015: international conference on learning representations 2015, Venue San Diego, CA, 7–9 May 2015
Kirby M, Sirovich L (1990) Application of the Karhunen-Loeve procedure for the characterization of human faces. IEEE Trans Pattern Anal Mach Intell 12(1):103–108
Kouba J, Héroux P (2001) Precise point positioning using IGS orbit and clock products. GPS Solut 5(2):12–28
Langbein J (2017) Improved efficiency of maximum likelihood analysis of time series with temporally correlated errors. J Geod 91:985–994. https://doi.org/10.1007/s00190-017-1002-5
Lau L, Cross P (2006) A new signal-to-noise-ratio based stochastic model for GNSS high-precision carrier phase data processing algorithms in the presence of multipath errors. In: Proceedings of ION GNSS 2006, Institute of navigation, Fort worth, TX, 26–29 Sep 2006, pp 276–285
Lau L, Cross P (2007) Development and testing of a new ray-tracing approach to GNSS carrier-phase multipath modeling. J Geodesy 81(11):713–732
LeCun Y, Bengio Y (1998) Convolutional networks for images, speech, and time series. In: Arbib MA (ed) The handbook of brain theory and neural networks. MIT Press, pp 255–258
Li Y, Xu C, Yi L (2017) Denoising effect of multiscale multiway analysis on high-rate GPS observations. GPS Solut 21(1):31–41
Li B, Zhang Z, Shen Y, Yang L (2018a) A procedure for the significance testing of unmodeled errors in GNSS observations. J Geodesy 92(10):1171–1186
Li Y, Xu C, Yi L, Fang R (2018b) A data-driven approach for denoising GNSS position time series. J Geodesy 92(8):905–922
Malys S, Jensen PA (1990) Geodetic point positioning with GPS carrier beat phase data from the CASA UNO Experiment. Geophys Res Lett 17(5):651–654
Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning, Haifa, Israel, 21–24 June 2010, pp 807–814
Olivares-Pulido G, Teferle FN, Hunegnaw A (2020) Markov chain monte carlo and the application to geodetic time series analysis. In: Montillet JP, Bos M (eds) Geodetic time series analysis in earth sciences. Springer Geophysics. Springer, Cham. https://doi.org/10.1007/978-3-030-21718-1_3
Prechelt L (1998) Early stopping-but when? In: Montavon G, Orr GB, Müller KR (eds) Neural Networks: tricks of the trade. Lecture notes in computer science, vol 7700. Springer, Berlin, Heidelberg, pp 55–69
Quan Y, Lau L, Roberts GW, Meng X, Zhang C (2018) Convolutional neural network based multipath detection method for static and kinematic GPS high precision positioning. Remote Sens 10(12):2052
Ragheb AE, Clarke PJ, Edwards SJ (2007) GPS sidereal filtering: coordinate and carrier-phase-level strategies. J Geodesy 81(5):325–335
Ruch DK, Van Fleet PJ (2009) Wavelet theory: an elementary approach with applications. John Wiley & Sons
Rumelhart DE, Hinton GE, Williams RJ (1988) Learning representations by back-propagating errors. Nature 323(6088):533–536
Shen N, Chen L, Wang L, Lu X, Tao T, Yan J, Chen R (2020) Site-specific real-time GPS multipath mitigation based on coordinate time series window matching. GPS Solut 24(3):82
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Takasu T (2011) Rtklib: An open source program package for GNSS positioning. Tech Rep, 2013 Software and documentation
Teunissen PJG, Amiri-Simkooei AR (2008) Least-squares variance component estimation. J Geod 82:65–82. https://doi.org/10.1007/s00190-007-0157-x
Wang L, Feng Y, Wang C (2013) Real-time assessment of GNSS observation noise with single receivers. J Glob Position Sys 12(1):73–82
Wdowinski S, Bock Y, Zhang J, Fang P, Genrich J (1997) Southern California permanent GPS geodetic array: spatial filtering of daily positions for estimating coseismic and postseismic displacements induced by the 1992 landers earthquake. J Geophys Res 102(8):18057–18070
Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2(1–3):37–52
Zhang Z, Li B (2020) Unmodeled error mitigation for single-frequency multi-GNSS precise positioning based on multi-epoch partial parameterization. Meas Sci Technol 31(2):25008
Zhang Z, Li B, Shen Y (2017) Comparison and analysis of unmodelled errors in GPS and BeiDou signals. Geod Geodyn 8(1):41–48
Zhang Z, Li B, Shen Y, Gao Y, Wang M (2018) Site-specific unmodeled error mitigation for GNSS positioning in urban environments using a real-time adaptive weighting model. Remote Sens 10(7):1157
Acknowledgements
This work is supported by the Natural Science Foundation of Jiangsu Province under Grant number BK20220367, University the Open Research Fund Program of LIESMARS under grant number 22P04, the National Natural Science Foundation of China under Grant number 42171417, 42271420, the Key Research and Development Program of Hubei Province under Grant number 2021BAA166, the Special Fund of Hubei Luojia Laboratory, the Special Research Fund of LIESMARS.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Shen, N., Chen, L., Wang, L. et al. GNSS Site unmodeled error prediction based on machine learning. GPS Solut 27, 77 (2023). https://doi.org/10.1007/s10291-023-01411-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10291-023-01411-x