In the GNSS-R remote sensing field, the prediction of mirror reflection points is the prerequisite for ground remote sensing detection. The prediction accuracy and computing speed will directly affect the reliability of the subsequent inversion results. The traditional geometric-based specular reflection point prediction methods have problems such as slow convergence speed and insufficient result stability. This paper constructs a multivariate time series prediction model using an improved LSTM network, with targeted optimization for the characteristics of river scene reflection point positioning. This paper optimize the LSTM’s dual-layer structure and training strategy to enhance its temporal feature extraction capability for GNSS-R observation data, which enables the model to outperform traditional algorithms in both prediction stability and positioning accuracy. Simulation test results verify that the proposed method achieves high-precision prediction in typical river scenarios, with a significant reduction in mean absolute error (MAE) compared to conventional methods, and the coefficient of determination (R2) reaches 0.951 6. The research results prove that it is feasible to replace the traditional geometric constraint solving method with a temporal feature learning framework for specular reflection point prediction, which can provide valuable theoretical and technical support for parameter inversion in river water level monitoring.
RUF C, GLEASONS. Spaceborne GNSS-R bistatic radar remote sensing,CYGNSS,and future missions[J]. Proceedings of the IEEE,2025,68(8):1-19.
[2]
YANGC, MAOK, GUOZ,et al. Review of GNSS-R technology for soil moisture inversion[J]. Remote Sensing,2024,16(7):1193.
[3]
LIW, RIUSA, FABRAF,et al. Revisiting the GNSS-R waveform statistics and its impact on altimetric retrievals[J]. IEEE Transactions on Geoscience and Remote Sensing,2018,56(5):2854-2871.
[4]
DUH, LIW, CARDELLACHE,et al. Deep residual fully connected network for GNSS-R wind speed retrieval and its interpretation[J]. Remote Sensing of Environment,2024,313:114375.
[5]
ZHANGY, BUJ, ZUOX,et al. Vegetation water content retrieval from spaceborne GNSS-R and multi-source remote sensing data using ensemble machine learning methods[J]. Remote Sensing,2024,16(15):10616-10619.
[6]
BAID, RUFC S, MOLLERD. Calibration of the polarimetric GNSS-R sensor in the rongowai mission[J]. IEEE Transactions on Geoscience and Remote Sensing,2025,63(10):1-18.
GLEASONS, HODGARTS, SUNY,et al. Detection and processing of bistatically reflected GPS signals from low earth orbit for the purpose of ocean remote sensing[J]. IEEE Transactions on Geoscience and Remote Sensing,2005,43(6):1229-1241.
[9]
WUS, MEEHANT, DUNNC,et al. The potential use of GPS signals as ocean altimetry observables[C]//Proceedings of the National Technical Meeting. Santa Monica:Institute of Navigation,1997:543-550.
WUF, ZHENGW, LIZ,et al. Improving the GNSS-R specular reflection point positioning accuracy using the gravity field normal projection reflection reference surface combination correction method[J]. Remote Sensing,2018,11(1):33.
[12]
ZHANGY, HUANGS, HANY,et al. Machine learning methods for spaceborne GNSS-R sea surface height measurement from TDS-1[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2021,15:1079-1088.
[13]
SOUTHWELLB J, DEMPSTERA G. A new approach to determine the specular point of forward reflected GNSS signals[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018,11(2):639-646.
[14]
JUANGJ C. On the determination of the specular reflection point in GNSS reflectometry[C]//Proceedings of the IEEE Specialist Meeting on Reflectometry using GNSS and Other Signals of Opportunity (GNSS+R). New York:IEEE,2021: 86-89.
[15]
LIMSUPAVANICHN, GUOB, FUX. Application of RNN on GNSS Reflectometry Sea level monitoring[J]. International Journal of Remote Sensing,2022,43(10):3592-3608.
[16]
TANGY, JIANGJ, LIUJ,et al. A GRU and AKF-based hybrid algorithm for improving INS/GNSS navigation accuracy during GNSS outage[J]. Remote Sensing,2022,14(3):752.
[17]
FANGW, JIANGJ, LUS,et al. A LSTM algorithm estimating pseudo measurements for aiding INS during GNSS signal outages[J]. Remote sensing,2020,12(2):256.