High-precision Sea Surface Temperature (SST) prediction is critical for understanding ocean–atmosphere interactions and climate anomaly monitoring. We propose GRU_EKAN, a novel hybrid model where Gated Recurrent Units (GRUs) capture temporal dependencies and the Enhanced Kolmogorov–Arnold Network (EKAN) models complex feature interactions between SST and multivariate ocean predictors. This study integrates GRU with EKAN, using B-spline-parameterized activation functions to model high-dimensional nonlinear relationships between multiple ocean variables (including sea water potential temperature at the sea floor, ocean mixed layer thickness defined by sigma theta, sea water salinity, current velocities, and sea surface height) and SST. L2 regularization addresses multicollinearity among predictors. Experiments were conducted at 25 South China Sea sites using 2011–2021 CMEMS data. The results show that GRU_EKAN achieves a superior mean R2 of 0.85, outperforming LSTM_EKAN, GRU, and LSTM by 5%, 25%, and 23%, respectively. Its average RMSE (0.90 °C), MAE (0.76 °C), and MSE (0.80 °C2) represent reductions of 31.3%, 27.0%, and 53.2% compared to GRU. The model also exhibits exceptional stability and minimal Weighted Quality Evaluation Index (WQE) fluctuation. During the 2019–2020 temperature anomaly events, GRU_EKAN predictions aligned closest with observations and captured abrupt trend shifts earliest. This model provides a robust tool for high-precision SST forecasting in the South China Sea, supporting marine heatwave warnings.
Satellite altimetry has become an important tool for monitoring inland water dynamics and has been widely used for water-level retrieval, hydrological simulation, and flood–drought risk assessment. To review research progress and development trends over the past three decades, this study combines bibliometric analysis with a traditional review approach. A total of 4764 publications indexed in the Web of Science Core Collection from 1991 to 2025 were analyzed. Using VOSviewer_1.6.20 and CiteSpace_6.4, we constructed knowledge maps of publication trends, disciplinary intersections, author collaboration, keyword clustering, and burst evolution. Representative studies were further synthesized qualitatively. The results show that remote sensing, geology, and imaging science form the core disciplinary framework of this field. Research hotspots have shifted from single water-level observation to multi-parameter retrieval and integration with hydrological models. New missions, including Surface Water and Ocean Topography (SWOT) and Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), have improved spatial resolution and coverage, accelerating the development of this field. However, agricultural water management and the integration of artificial intelligence with hydrological models remain limited. Key challenges include monitoring small and complex water bodies, multi-source data fusion, uncertainty quantification, physics-informed artificial intelligence, and operational applications.