EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HyMambaNet: Efficient Remote Sensing Water Extraction Method Combining State Space Modeling and Multi-Scale Features

Handan Liu iD, Guangyi Mu, Kai Li, Haowei Zhang, Yibo Sun, Hongqing Sun, Sijia Li iD

Sensors · 05.12.2025 · 25 (24) · 7414

DOI: 10.3390/s25247414 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.12.2025. Verfasst von Handan Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Applied Disaster Prevention in Water Conservation Engineering of Jilin Province, Changchun Institute of Technology, Changchun 130103, C…. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Young Development Technology Project awarded to Dr. Mu from the Science and Technology Department of Jilin Province, Young Development Technology Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate segmentation of water bodies from high-resolution remote sensing imagery is crucial for water resource management and ecological monitoring. However, small and morphologically complex water bodies remain difficult to detect due to scale variations, blurred boundaries, and heterogeneous backgrounds. This study aims to develop a robust and scalable deep learning framework for high-precision water body extraction across diverse hydrological and ecological scenarios. To address these challenges, we propose HyMambaNet, a hybrid deep learning model that integrates convolutional local feature extraction with the Mamba state space model for efficient global context modeling. The network further incorporates multi-scale and frequency-domain enhancement as well as optimized skip connections to improve boundary precision and segmentation robustness. Experimental results demonstrate that HyMambaNet significantly outperforms existing CNN and Transformer-based methods. On the LoveHY dataset, it achieves 74.82% IoU and 88.87% F1-score, exceeding UNet by 7.49% IoU and 7.12% F1. On the LoveDA dataset, it attains 81.30% IoU and 89.99% F1-score, surpassing advanced models such as Deeplabv3+, AttenUNet, and TransUNet. These findings confirm that HyMambaNet provides an efficient and generalizable solution for large-scale water resource monitoring and ecological applications based on remote sensing imagery.

Schlagwörter

Stichwörter der Autor:innen

HyMambaNetMambaremote sensingsemantic segmentationstate space modelwater body extraction

Autor:innen und Institutionen

  • Laboratory of Applied Disaster Prevention in Water Conservation Engineering of Jilin Province, Changchun Institute of Technology, Changchun 130103, China.
  • Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, China.
  • Department of Civil Engineering, The University of Hong Kong, Hong Kong 999077, China.

ORCID-Profile: Handan Liu, Sijia Li

Förderung

  • Young Development Technology Project awarded to Dr. Mu from the Science and Technology Department of Jilin Province
  • Young Development Technology Project

Zitieren

APA

Liu, H., Mu, G., Li, K., Zhang, H., Sun, Y., Sun, H., & Li, S. (2025). HyMambaNet: Efficient Remote Sensing Water Extraction Method Combining State Space Modeling and Multi-Scale Features. Sensors, 25(24), 7414. https://doi.org/10.3390/s25247414

Vancouver

Liu H, Mu G, Li K, Zhang H, Sun Y, Sun H, et al. HyMambaNet: Efficient Remote Sensing Water Extraction Method Combining State Space Modeling and Multi-Scale Features. Sensors. 2025;25(24):7414. doi:10.3390/s25247414

BibTeX
@article{Liu2025,
  author = {Liu, Handan and Mu, Guangyi and Li, Kai and Zhang, Haowei and Sun, Yibo and Sun, Hongqing and Li, Sijia},
  title = {HyMambaNet: Efficient Remote Sensing Water Extraction Method Combining State Space Modeling and Multi-Scale Features},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {24},
  pages = {7414},
  doi = {10.3390/s25247414}
}
Kostenlos starten →