Li et al. (2026) TA-TransUNet: An Improved Deep Learning Network Model for Water Body Extraction From Remote Sensing Images

Identification

• Journal: IEEE Transactions on Geoscience and Remote Sensing
• Year: 2026
• Date: 2026-01-01
• Authors: Zhenxuan Li, Miner Huang, Hao Wu, Zhiyong Lv, Tingye Tao, Zhaofu Wu, Yongchao Zhu, Shuiping Li, Xiaochuan Qu
• DOI: 10.1109/tgrs.2026.3654523

Research Groups

[Not specified in the provided text]

Short Summary

This paper introduces TA-TransUNet, an improved deep learning network model specifically designed for the accurate and efficient extraction of water bodies from remote sensing images.

Objective

• To develop and evaluate an improved deep learning network model, TA-TransUNet, for enhanced water body extraction from remote sensing images.

Study Configuration

• Spatial Scale: [Not specified in the provided text, but implied to be relevant to remote sensing image resolution, e.g., pixel level to regional coverage.]
• Temporal Scale: [Not specified in the provided text, but implied to be based on individual remote sensing image acquisitions.]

Methodology and Data

• Models used: TA-TransUNet (an improved deep learning network model, likely a variant of TransUNet).
• Data sources: Remote sensing images.

Main Results

• [Not specified in the provided text, but the title implies improved performance in water body extraction compared to existing methods.]

Contributions

• [Not specified in the provided text, but likely includes the novel architecture or improvements of TA-TransUNet and its demonstrated effectiveness for water body extraction.]

Funding

[Not specified in the provided text]

Citation

@article{Li2026TATransUNet,
  author = {Li, Zhenxuan and Huang, Miner and Wu, Hao and Lv, Zhiyong and Shi, Wenzhong and Tao, Tingye and Wu, Zhaofu and Zhu, Yongchao and Li, Shuiping and Qu, Xiaochuan},
  title = {TA-TransUNet: An Improved Deep Learning Network Model for Water Body Extraction From Remote Sensing Images},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2026},
  doi = {10.1109/tgrs.2026.3654523},
  url = {https://doi.org/10.1109/tgrs.2026.3654523}
}