Abstract
In this work, we used the convolutional neural network (CNN) method to invert sea surface height (SSH) from the Global Navigation Satellite System (GNSS) delayed Doppler map (DDM) data during 2009–2017 and compared the CNN inversion data with those obtained from traditional simple random forest (RF) method. SSH observations from the OSTM/Jason-2 satellite were used to judge the merits of the two methods. The results show that both methods yield good SSH inversion results, but when the training set is 9000, the root mean square errors of the SSH inversion results based on the CNN and the RF method are 16.78 and 15.96 respectively; as the training set increases above 9000, the accuracy of the CNN method is significantly better than that of the RF method. This suggests that SSH inversion based on the CNN method will become more advantageous as more data become available.
Similar content being viewed by others
REFERENCES
S. Lutz, M. Meindl, P. Steigenberger, et al., J. Geod. 90, 365–378 (2016).
C. D. Hall and R. A. Cordey, in Proc. IEEE Int. Geoscience and Remote Sensing Symp. “Remote Sensing: Moving Toward the 21st Century” (Edinburgh, 1988), Vol. 1, pp. 561–562.
G. Foti, C. Gommenginger, P. Jales, et al., Geophys. Res. Lett. 42 (13), 5435–5441 (2015).
Q. Wang, W. Zheng, F. Wu, et al., Remote Sens. 14 (13), 3161 (2022).
N. Zhu, J. Marais, D. Betaille, et al., Trans. Intellig. Transp. Syst. 19 (9), 2762–2778 (2018).
L. Alzubaidi, J. Zhang, A. J. Humaidi, et al., J. Big Data 8, 1–74 (2021).
L. C. Yan, B. Yoshua, and H. Geoffrey, Nature 521 (7553), 436–444 (2015).
M. P. Clarizia and C. S. Ruf, IEEE Trans. Geosci. Remote Sensing 54 (8), 4419–4432 (2016).
J. Lambin, R. Morrow, L. L. Fu, et al., Mar. Geod. 33 (S1), 4–25 (2010).
L. Breiman, Mach. Learn. 45, 5–32 (2001).
A. Cutler, D. R. Cutler, and J. R. Stevens, in Ensemble Machine Learning: Methods and Applications, Ed. by C. Zhang and Y. Ma (Springer, New York, 2012), pp. 157–175.
S. Fu, L. L. Zhao, G. P. Zank, et al., Sci. China Phys., Mech. Astron. 63, 1–12 (2020).
Funding
This work was funded by the National Natural Science Foundation of China (grant no. 12250012), the Science and Technology Development Fund of Macau (grant no. 0064/2023/ITP2), and the Faculty Research Grants of the Macau University of Science and Technology (grant no. FRG-23-032-SSI).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Publisher’s Note.
Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Su, Y., Fu, S., Jiao, B. et al. Application of Deep Learning in Sea Surface Height Estimation of GNSS Data Sets. Dokl. Earth Sc. (2024). https://doi.org/10.1134/S1028334X2360322X
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1134/S1028334X2360322X