Articles | Volume 20, issue 3
https://doi.org/10.5194/tc-20-1543-2026
https://doi.org/10.5194/tc-20-1543-2026
Research article
 | 
11 Mar 2026
Research article |  | 11 Mar 2026

Mapping Antarctic geothermal heat flow with deep neural networks optimized by particle swarm optimization algorithm

Shaoxia Liu, Xueyuan Tang, Shuhu Yang, Lijuan Wang, and Jianjie Liu

Viewed

Total article views: 7,055 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
5,661 1,265 129 7,055 81 178 264
  • HTML: 5,661
  • PDF: 1,265
  • XML: 129
  • Total: 7,055
  • Supplement: 81
  • BibTeX: 178
  • EndNote: 264
Views and downloads (calculated since 31 Jul 2025)
Cumulative views and downloads (calculated since 31 Jul 2025)

Viewed (geographical distribution)

Total article views: 7,055 (including HTML, PDF, and XML) Thereof 7,032 with geography defined and 23 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 25 Jun 2026
Download
Short summary
Heat from inside the Earth beneath Antarctica affects how fast ice melts and how quickly the sea level rises, but direct measurements are very limited. We built a data-driven computer model that learns the complex links between geophysical features and geothermal heat flow and reports confidence. We find lower heat flow in East Antarctica and higher heat flow in West Antarctica, especially near coasts.
Share