MAPUNet: Multi-scale attention for InSAR phase unwrapping in mining areas
Baojing Zhang, Wenfu Yang, Xiaowei Zhang, Li Wang, Yan Cui, Xiaoyu Wang, Yufei Zhang · 2026
Read MAPUNet: Multi-scale attention for InSAR phase unwrapping in mining areas by Baojing Zhang, Wenfu Yang, Xiaowei Zhang, Li Wang, Yan Cui, Xiaoyu Wang, Yufei Zhang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13210142.txt.
Description
Radar maps of sinking mining land are hard to unwrap, and a 2026 study by Baojing Zhang teaches a neural network to do it more faithfully. The research article presents MAPUNet, a multi-scale attention network for interferometric phase unwrapping where large ground deformation and noise defeat traditional algorithms.
The design adds pyramid pooling for wide context, a dual attention block, and a channel-attention residual module to suppress noise while keeping important features. On simulated scenes with heavy noise it beat rival methods on image similarity scores in the authors' tests. Applied to a real Shanxi mining district, it measured subsidence reaching roughly nine centimeters within one month.
Catalog record
| CREATOR | Baojing Zhang, Wenfu Yang, Xiaowei Zhang, Li Wang, Yan Cui, Xiaoyu Wang, Yufei Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |