As the largest groundwater drainage region in China, the per capita water resources in the North China Plain (NCP) account for only one-seventh of the country’s available water resources. Currently, the NCP is experiencing a serious water shortage due to the overexploitation of groundwater resources and a subsequent series of natural disasters. Thus, accurate regional assessments and effective water resource management policies are of critical importance. To accomplish this phenomenon, the daily terrestrial water storage anomaly (TWSA) over the NCP is calculated from the combination of the GNSS vertical deformation sequences (seasonal items) and GRACE (trend items). The groundwater storage anomaly (GWSA) in the NCP is obtained by subtracting the canopy water, soil water, and snow water equivalent components from the TWSA. The inversion results of this study are verified by comparisons with the Global Land Data Assimilation System (GLDAS) data products. The elevated annual amplitude areas are located in Beijing and Tianjin, and the Pearson correlation coefficient (PCC), root mean square error (RMSE), and Nash–Sutcliffe efficiency (NSE) between the two GWSA results are 0.67, 4.01 cm, and 0.61, respectively. This indicates that the methods proposed in this study are reliable. Finally, the groundwater drought index was calculated for the period from 2011 to 2021, and the results showed that 2019 was the driest year, with a drought severity index value of −0.12, indicative of slightly moderate drought conditions. By calculating and analyzing the annual GWSA, this work shows that the South–North Water Transfer Project does provide some regional drought mitigation.

Traditional spaceborne Global Navigation Satellite Systems Reflectometry (GNSS-R) sea surface height (SSH) retrieval methods have the disadvantages of complicated error models, low retrieval accuracy, and difficulty using full DDM information. To compensate for these deficiencies while considering the heterogeneity of the input data, this paper proposes an end-to-end Modified Residual Multimodal Deep Learning (MRMDL) method that can utilize the entire range of DDM information. First, the MRMDL method is constructed based on the modified Residual Net (MResNet) and Multi-Hidden layer neural network (MHL-NN). The MResNet applicable to DDM structures is used to adaptively capture productive features of the full DDM and to convert the two-dimensional DDM data into one-dimensional numerical form. Then, the extracted features and auxiliary parameters are fused as the input data for MHL-NN to retrieve the SSH. Second, the reliability of the model is verified using SSH with tide-corrected DTU Sea Surface Height 18 (DTU18) and spaceborne radar altimeters (Jason3, HY-2C, HY-2B). Compared to the SSH provided by the DTU18 validation model and the spaceborne radar altimeter, the Pearson correlation coefficients (PCC) are 0.98 and 0.97, respectively. However, the CYGNSS satellite is not primarily employed for ocean altimetry, and the mean absolute differences (MAD) are 3.92 m and 4.32 m, respectively. Finally, the retrieval accuracy of the MRMDL method and the HALF retracking approach are compared and analyzed. Finally, this study also implements the HALF retracking algorithm to derive the SSH, and the results are compared with those computed by the MRMDL method. The MRMDL method is more accurate than the HALF retracking approach according to MAD, Root-Mean-Square Error (RMSE), and PCC, with an improvement of 35.21%, 17.25%, and 2.08%, respectively. The MRMDL method will contribute a new theoretical and methodological reference for future GNSS-R altimetry satellites with high spatiotemporal SSH retrieval.

The altimetry precision of conventional spaceborne Global Navigation Satellite Systems Reflectometry (GNSS-R) is limited, and the error models are complicated. To compensate for the shortcomings of conventional methods, we present a new grid search multihidden layer neural network feature optimization method (GSMHLFO) for sea surface height (SSH) retrieval. Firstly, the GSMHLFO is constructed by combining the multihidden layer neural network, feature engineering, and a grid search algorithm. Moreover, the retrieval performance of the GSMHLFO and its sensitivity to various features are analyzed. By analyzing 14 feature sets with different information details, we concluded that the elevation, signal-to-noise ratio (SNR), atmospheric delay, and ocean wind speed can provide essential contributions to the SSH retrieval based on GSMHLFO. Secondly, the Technical University of Denmark 18 mean sea surface (DTU18 MSS), which is corrected by the TPXO8 global tide model, was used to verify the GSMHLFO. The number of hidden layers and neurons was optimized using the grid search algorithm. The experimental results show that the proposed GSMHLFO with four hidden layers and 200 neurons per layer has a better retrieval performance. Compared with DTU18, the mean absolute difference (MAD), the root mean square error (RMSE), and the Pearson correlation coefficient (PCC) equal 4.23 m, 5.94 m, and 0.98, respectively. The retrieval precision obtained is significantly improved compared to that reported in the literature for the TDS-1 SSH retrieval. Finally, the retrieval performance of the GSMHLFO and the traditional HALF single-point retracking method were compared. The precision of GSMHLFO is higher than that of traditional retracking method according to MAD, RMSE, and PCC, which are increased by 32.86, 25.00, and 8.99%. The GSMHLFO will provide innovative theoretical and methodological support for the high-precision SSH retrieval of GNSS-R altimetry satellites in the future.