# Progressive Attention-Enhanced EfficientNet–UNet for Robust Water-Body Mapping from Satellite Imagery

## TL;DR

This paper introduces a deep learning model that improves water-body mapping from satellite images using attention mechanisms, achieving high accuracy and robustness.

## Contribution

The paper introduces a CBAM-integrated EfficientNet–UNet model for water-body mapping and validates its performance through rigorous testing.

## Key findings

- The model achieved a Dice score of 88.78% and IoU of 79.82% on the test set.
- Attention mechanisms significantly enhance the extraction of complex water-body patterns.
- The model is computationally efficient and suitable for large-scale deployment in water-resource monitoring.

## Abstract

The sustainable management of water resources and the development of climate-resilient infrastructure depend on the precise identification of water bodies in satellite imagery. This paper presents a novel deep learning architecture that integrates a convolutional block attention module (CBAM) into a modified EfficientNet–UNet backbone. This integration allows the model to prioritize informative features and spatial areas. The model robustness is ensured through a rigorous training regimen featuring five-fold cross-validation, dynamic test-time augmentation, and optimization with the Lovász loss function. The final model achieved the following values on the independent test set: precision = 90.67%, sensitivity = 86.96%, specificity = 96.18%, accuracy = 93.42%, Dice score = 88.78%, and IoU = 79.82%. These results demonstrate improvement over conventional segmentation pipelines, highlighting the effectiveness of attention mechanisms in extracting complex water-body patterns and boundaries. The key contributions of this paper include the following: (i) adaptation of CBAM within a UNet-style architecture tailored for remote sensing water-body extraction; (ii) a rigorous ablation study detailing the incremental impact of decoder complexity, attention integration, and loss function choice; and (iii) validation of a high-fidelity, computationally efficient model ready for deployment in large-scale water-resource and ecosystem-monitoring systems. Our findings show that attention-guided segmentation networks provide a robust pathway toward high-fidelity and sustainable water-body mapping.