Water Body Identification from Satellite Images Using a Hybrid Evolutionary Algorithm-Optimized U-Net Framework

TL;DR

This paper introduces an automated framework for identifying water bodies in satellite images using a U-Net model optimized by a hybrid evolutionary algorithm.

Contribution

The novel hybrid evolutionary optimization strategy enables fully automated segmentation without manual hyperparameter tuning.

Findings

The framework achieves a Pixel Accuracy of 96.79% and an F1-Score of 94.75 on satellite image datasets.

It outperforms mainstream models by over 10% in key metrics while addressing class imbalance automatically.

Abstract

Accurate and automated identification of water bodies from satellite imagery is critical for environmental monitoring, water resource management, and disaster response. Current deep learning approaches, however, suffer from a strong dependence on manual hyperparameter tuning, which limits their automation capability and robustness in complex, multi-scale scenarios. To overcome this limitation, this study proposes a fully automated segmentation framework that synergistically integrates an enhanced U-Net model with a novel hybrid evolutionary optimization strategy. Extensive experiments on public Kaggle and Sentinel-2 datasets demonstrate the superior performance of our method, which achieves a Pixel Accuracy of 96.79% and an F1-Score of 94.75, outperforming various mainstream baseline models by over 10% in key metrics. The framework effectively addresses the class imbalance problem and enhances feature representation without human intervention. This work provides a viable and efficient path toward fully automated remote sensing image analysis, with significant potential for application in large-scale water resource monitoring, dynamic environmental assessment, and emergency disaster management.

Figures