EUVIMEDEUVIMED entdecken
Crossref

Ad-SACNet: Spatial Attention Compression Network for Atmospheric Duct Inversion With Radar Sea Clutter Data

Jiajing Wu, Ziliang Wei, Che Liu, Qian Ma, Zhiqiang Wei, Tiejun Cui, Qingliang Li, Xiaoyu Wu, Junyu Ye, Shuqin Wu, Jianye Wang

IEEE Transactions on Antennas and Propagation · 2026-08 · 74 (8) · 7967-7981

DOI: 10.1109/tap.2025.3645358 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Antennas and Propagation, 2026-08. Verfasst von Jiajing Wu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Key Laboratory of Electromagnetic Wave Propagation, National Natural Science Foundation of China, Henan Provincial Joint Fund for Science and Technology Research and Development Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As an abnormal atmospheric phenomenon, an atmospheric duct makes electromagnetic waves deviate from the original orbital direction and causes radar detection blind spots. Therefore, accurate atmospheric duct prediction can take corresponding measures to correct and compensate the duct structure in time and provide radar air traffic control warning. However, when accounting for the inhomogeneous variations of atmospheric ducts, high-dimensional atmospheric duct profile modeling is required, and such high-dimensional inversion involves enormous computational complexity and consequently impairs the practical inversion speed. Additionally, deep learning-based atmospheric duct inversion models, such as long short-term memory (LSTM) and convolutional neural network (CNN), fail to fully leverage information regarding the spatial inhomogeneous variations of atmospheric ducts. Thus, this study proposes a framework named Ad-SACNet, which inverts the variations of the atmospheric duct modified refractive index profile (M-profile) from the perspective of accounting for the high-dimensional and complex variations of atmospheric ducts. Specifically, in our method, the high-dimensional atmospheric duct M profile is first spatially compressed to reduce the computational complexity of the inversion model. Then, three multiscale modules are operated to mine spatial inhomogeneous features. Finally, the output of the three modules is integrated by the fusion module to fully exploit the spatial inhomogeneity of the atmospheric duct, which is exploited to attain the final atmospheric duct inversion results. Based on radar simulation and measured data, this article comprehensively evaluates and compares the proposed Ad-SACNet. The accuracy of the inversion obtained for simulated and measured radar sea clutter by Ad-SACNet is better than the most advanced baseline.

Förderung

  • National Key Laboratory of Electromagnetic Wave Propagation
  • National Natural Science Foundation of China
  • Henan Provincial Joint Fund for Science and Technology Research and Development Province

Zitieren

APA

Wu, J., Wei, Z., Liu, C., Ma, Q., Wei, Z., Cui, T., Li, Q., Wu, X., Ye, J., Wu, S., & Wang, J. (2026). Ad-SACNet: Spatial Attention Compression Network for Atmospheric Duct Inversion With Radar Sea Clutter Data. IEEE Transactions on Antennas and Propagation, 74(8), 7967-7981. https://doi.org/10.1109/tap.2025.3645358

Vancouver

Wu J, Wei Z, Liu C, Ma Q, Wei Z, Cui T, et al. Ad-SACNet: Spatial Attention Compression Network for Atmospheric Duct Inversion With Radar Sea Clutter Data. IEEE Transactions on Antennas and Propagation. 2026;74(8):7967-7981. doi:10.1109/tap.2025.3645358

BibTeX
@article{Wu2026,
  author = {Wu, Jiajing and Wei, Ziliang and Liu, Che and Ma, Qian and Wei, Zhiqiang and Cui, Tiejun and Li, Qingliang and Wu, Xiaoyu and Ye, Junyu and Wu, Shuqin and Wang, Jianye},
  title = {Ad-SACNet: Spatial Attention Compression Network for Atmospheric Duct Inversion With Radar Sea Clutter Data},
  journal = {IEEE Transactions on Antennas and Propagation},
  year = {2026},
  volume = {74},
  number = {8},
  pages = {7967--7981},
  doi = {10.1109/tap.2025.3645358}
}
Kostenlos starten →