EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An AESRGAN Remote Sensing Super-Resolution Model for Accurate Water Extraction

Hongjie Liu, Wenlong Song, Juan Lv, Yizhu Lu, Long Chen, Yutong Zhao, Shaobo Linghu, Yifan Duan, Pengyu Chen, Tianshi Feng, Rongjie Gui

Remote Sensing · 08.04.2026 · 18 (8) · 1108

DOI: 10.3390/rs18081108 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 08.04.2026. Verfasst von Hongjie Liu und 10 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Water Conservancy Technology Project of Hunan Province, Three Gorges Follow-up Work, Special Project on Basic Scientific Research Funds of China Institute of Water Resources and Hydropower Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate monitoring of water spatiotemporal dynamics is critical for hydrological process analysis and climate impact assessment. While remote sensing enables effective water monitoring, public satellite imagery is limited by mixed-pixel effects that hinder small river detection, and high-resolution commercial data suffers from low temporal frequency and restricted coverage. To address these limitations, this study proposes a deep learning-based super-resolution (SR) framework for multispectral remote sensing imagery. This paper constructs a matched dataset for GF2 and Sentinel-2 imagery and develops an Attention Enhanced Super Resolution Generative Adversarial Network (AESRGAN). By integrating attention mechanisms and a spectral-structural loss design, the network is optimized to adapt to the characteristics of multispectral remote sensing imagery. Experimental results demonstrate that AESRGAN achieves strong reconstruction performance, with a Peak Signal-to-Noise Ratio (PSNR) of 33.83 dB and a Structural Similarity Index Measure (SSIM) of 0.882. Water extraction based on the reconstructed imagery using the U-Net++ model achieved an overall accuracy of 0.97 and a Kappa coefficient of 0.92. In addition, the reconstructed imagery improved the estimation accuracy of river length, width, and area by 0.34%, 3.28%, and 8.51%, respectively. The proposed framework provides an effective solution for multi-source remote sensing data fusion and high-precision surface water monitoring, offering new potential for long-term hydrological observation using medium-resolution satellite imagery.

Förderung

  • Water Conservancy Technology Project of Hunan Province
  • Three Gorges Follow-up Work
  • Special Project on Basic Scientific Research Funds of China Institute of Water Resources and Hydropower Research
  • Special Fund for Scientific and Technological Achievements Transformation of China Institute of Water Resources and Hydropower Research

Zitieren

APA

Liu, H., Song, W., Lv, J., Lu, Y., Chen, L., Zhao, Y., Linghu, S., Duan, Y., Chen, P., Feng, T., & Gui, R. (2026). An AESRGAN Remote Sensing Super-Resolution Model for Accurate Water Extraction. Remote Sensing, 18(8), 1108. https://doi.org/10.3390/rs18081108

Vancouver

Liu H, Song W, Lv J, Lu Y, Chen L, Zhao Y, et al. An AESRGAN Remote Sensing Super-Resolution Model for Accurate Water Extraction. Remote Sensing. 2026;18(8):1108. doi:10.3390/rs18081108

BibTeX
@article{Liu2026,
  author = {Liu, Hongjie and Song, Wenlong and Lv, Juan and Lu, Yizhu and Chen, Long and Zhao, Yutong and Linghu, Shaobo and Duan, Yifan and Chen, Pengyu and Feng, Tianshi and Gui, Rongjie},
  title = {An AESRGAN Remote Sensing Super-Resolution Model for Accurate Water Extraction},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {1108},
  doi = {10.3390/rs18081108}
}
Kostenlos starten →