Accurate river water level estimation is critical for flood prevention, disaster mitigation, and water resource management, but conventional approaches struggle in complex plain river-network regions where water levels are influenced by precipitation, sluice regulation, human activities, and agricultural irrigation. These factors create strong nonlinearity, non-stationarity, and spatial heterogeneity that challenge traditional hydrological stations, which suffer from sparse coverage, high costs, and limited real-time capability.
To address these gaps, researchers from Nanjing University of Posts and Telecommunications, Henan Polytechnic University, Anhui University, and the Nanjing Institute of Geography and Limnology of the Chinese Academy of Sciences developed a physics-guided noise-enhanced adaptive fusion dual-stream network (PGNAF-DSNet). The model integrates observations from the Cyclone Global Navigation Satellite System (CYGNSS) and Sentinel-1 synthetic aperture radar (SAR) over the Jiangsu plain in China. Their findings were published in Satellite Navigation on October 12, 2026.
The study introduces several key innovations. First, researchers constructed physics-guided fused features: PFSWI (Polarization Fusion Surface Water Index), which multiplies Sentinel-1 backscatter differences by CYGNSS reflectivity, and Width_cv (river width coefficient of variation), embedding physical priors into the model. Second, they introduced a selective Gaussian noise enhancement strategy based on wavelet-denoised residual analysis, optimized using the Tree-structured Parzen Estimator algorithm, applied only to channels susceptible to observational errors. Third, the dual-stream architecture employs parallel Transformer and long short-term memory encoders to capture global and local temporal patterns, respectively, before fusion through an Adaptive Feature Fusion module that dynamically weights the two branches at the channel level.
On a strictly chronological dataset (training: January 2021–November 2022; testing: May–October 2023), PGNAF-DSNet outperformed Convolutional Neural Network, Transformer, LSTM, and Transformer-LSTM baselines. The model achieved a root mean square error of 0.2388 meters, a mean absolute error of 0.1624 meters, and a correlation coefficient of 0.9889. Notably, it maintained a correlation coefficient above 0.95 across all forecast horizons up to T+6. Ablation experiments confirmed each component's contribution, and SHAP analysis indicated that Width_cv and PFSWI both exhibit high feature importance.
The authors said the study's core contribution lies in moving beyond simple data-level fusion. Previous approaches mainly used CYGNSS to fill temporal gaps in SAR observations without fully exploiting cross-modal feature interactions. By constructing physics-guided fused features and adopting a dual-stream architecture, the model captures both global trends and local dynamics of water level changes in complex river networks. The selective noise enhancement strategy acts as a regularizer, improving robustness against observational uncertainty and human-induced disturbances.
PGNAF-DSNet offers a practical framework for water level monitoring in plain river-network regions, with potential applications in flood early warning, water resource management, and river-network regulation. The model reduced prediction errors by approximately 50% in areas significantly affected by human activities such as sluice regulation and agricultural irrigation, and maintained stable performance at T+6 forecasts, demonstrating promise for operational forecasting. The framework could also be extended to incorporate additional satellite observations, such as Surface Water and Ocean Topography water surface elevations, and adapted to other river systems through transfer learning. The full study is available via 10.1186/s43020-026-00219-7.
