What question did this study set out to answer?

To develop an effective model for accurately delineating water bodies from high-resolution remote sensing images under complex conditions.

April 19, 2026Open Access

An Uncertainty-Aware Hybrid CNN–Transformer Network for Accurate Water Body Extraction from High-Resolution Remote Sensing Images in Complex Scenarios

Key Points

To develop an effective model for accurately delineating water bodies from high-resolution remote sensing images under complex conditions.
Designed a hybrid CNN–Transformer model combining a multi-scale transformer module and an uncertainty-guided information fusion module.
Model optimized using a comprehensive loss function for precise water body mapping.
Introduced the HBD_Water dataset containing 44 multispectral images at 2 m resolution for model training and evaluation.
Conducted water mapping experiments across three datasets to verify model effectiveness.
The hybrid model demonstrates improved accuracy in water body extraction compared to advanced models like TransUNet and DeeplabV3+.
Quantification and suppression of mapping uncertainty contribute to enhanced precision in delineation.
Extensive experiments show effective performance across different scales and conditions.

Abstract

Timely and accurate monitoring of surface water dynamics via remote sensing is critical, given water resources’ importance. However, accurate water body delineation based on high-resolution remotely sensed imagery is still challenging due to the complexity of water bodies’ boundaries and the diversity of their shapes and sizes, which can lead to boundary ambiguity and varying degrees of confusion with near-water vegetation in water body maps. To address this challenge, we introduce an uncertainty-aware hybrid CNN–Transformer model for delineating water bodies using remotely sensed imagery. In our designed network, a multi-scale transformer (MST) module is first designed to effectively model and refine the multi-scale global semantic dependencies of water bodies. Subsequently, an uncertainty-guided multi-scale information fusion (MSIF) module is constructed to extract water body mapping information from these multi-scale features output from the MST module and fuse them adaptively. Across different scales, the extracted features differ in their ability to distinguish water bodies from non-water bodies and in their levels of uncertainty. Consequently, during the adaptive fusion of multi-scale water body information in the MSIF module, the mapping uncertainty is quantified and suppressed to minimize its impact, thus yielding enhanced precision in water body delineation. Ultimately, a comprehensive loss function is designed for model optimization to generate the final water body map. Furthermore, to promote water body segmentation models’ development, this study also presents the HBDWater water body sample dataset, which contains 44 multispectral, 5000 × 5000-pixel images at 2 m spatial resolution, and will be released on the LuojiaSET platform soon. Finally, to verify the proposed model and its constituent MST and MSIF modules, extensive water mapping experiments were performed on three datasets. The experimental results substantiate their effectiveness. Furthermore, comparative experiment results demonstrate that the proposed model performs better at water body extraction than advanced networks including TransUNet, DeeplabV3+, and ADCNN.

An Uncertainty-Aware Hybrid CNN–Transformer Network for Accurate Water Body Extraction from High-Resolution Remote Sensing Images in Complex Scenarios

Key Points

Abstract

Cite This Study