Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 19, issue 10
Articles | Volume 19, issue 10
https://doi.org/10.5194/amt-19-3407-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-19-3407-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 10
Research article
 | 
26 May 2026
Research article |  | 26 May 2026

DTL-IceNet: a dual-task learning architecture with multi-scale fusion mechanisms for enhanced ice detection on transmission lines

Yufei Fu, Yang Cheng, Song Yuan Cao, Ling Tan, Jiaxin He, Mengya Wang, and Wenjie Zhang

Viewed

Total article views: 3,229 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,980 1,063 186 3,229 138 132
  • HTML: 1,980
  • PDF: 1,063
  • XML: 186
  • Total: 3,229
  • BibTeX: 138
  • EndNote: 132
Views and downloads (calculated since 13 Nov 2025)
Cumulative views and downloads (calculated since 13 Nov 2025)

Viewed (geographical distribution)

Total article views: 3,229 (including HTML, PDF, and XML) Thereof 3,194 with geography defined and 35 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 13 Jun 2026
Download
Short summary
This paper integrates image recognition and semantic segmentation techniques into a dual-task deep learning model. A key innovation is the incorporation of physical characteristics of ice-covered transmission lines to physically constrain and refine the deep learning outputs. This framework not only achieves accurate identification of ice types on transmission lines but also significantly improves the computational accuracy of ice thickness estimation.
Read more
Share