Accurate river water level estimation is critical for flood prevention, disaster mitigation, and water resource management. However, complex plain river-network regions pose significant challenges due to strong non-stationarity and nonlinearity in water level variations, which are influenced by precipitation, sluice regulation, human activities, and agricultural irrigation. Traditional hydrological stations offer sparse spatial coverage and high operational costs, while satellite remote sensing alternatives each have limitations: conventional altimeters have sparse cross-track spacing, Synthetic Aperture Radar (SAR) has limited temporal resolution, and the Cyclone Global Navigation Satellite System (CYGNSS) suffers from coarse spatial resolution and observational noise.
To address these challenges, 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 the Physics-Guided Noise-Enhanced Adaptive Fusion Dual-Stream Network (PGNAF-DSNet). Published in Satellite Navigation on October 12, 2026, the model integrates Sentinel-1 SAR and CYGNSS observations through physics-guided feature construction, dual-stream temporal encoding, and adaptive feature fusion.
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 (TPE) algorithm (σ = 0.04157), applied only to channels susceptible to observational errors such as VV, VH, river width, and precipitation. Third, the dual-stream architecture employs parallel Transformer and long short-term memory (LSTM) encoders to capture global and local temporal patterns, respectively, before fusion through an Adaptive Feature Fusion (AFF) 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 (CNN), Transformer, LSTM, and Transformer-LSTM baselines. The model achieved a root mean square error (SRMSE) of 0.2388 meters, mean absolute error (SMAE) of 0.1624 meters, and a correlation coefficient (R) of 0.9889. Notably, the model maintained R ≥ 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 model reduced prediction errors by approximately 50% in regions significantly affected by human activities such as sluice regulation and agricultural irrigation.
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 framework could also be extended to incorporate additional satellite observations, such as Surface Water and Ocean Topography (SWOT) water surface elevations, and adapted to other river systems through transfer learning. The full study is available at 10.1186/s43020-026-00219-7.
