Chi et al. (2026) PCEED-Net: A Physics-Constrained Enhanced Encoder–Decoder Network for Precipitation Nowcasting

Identification

• Journal: IEEE Transactions on Geoscience and Remote Sensing
• Year: 2026
• Date: 2026-01-01
• Authors: Haotian Chi, Lingjia Gu, Jianfu Yuan, Yan-An Liu, Yuheng Zhao, Keyu Wu
• DOI: 10.1109/tgrs.2026.3660822

Research Groups

[Not specified in the provided text.]

Short Summary

This paper introduces PCEED-Net, a physics-constrained enhanced encoder-decoder network, for the task of precipitation nowcasting.

Objective

• To develop and evaluate PCEED-Net, a novel physics-constrained enhanced encoder-decoder network, for improved precipitation nowcasting.

Study Configuration

• Spatial Scale: Not specified, but typically regional to local for precipitation nowcasting.
• Temporal Scale: Not specified, but typically short-term (minutes to a few hours ahead) for nowcasting.

Methodology and Data

• Models used: PCEED-Net (Physics-Constrained Enhanced Encoder–Decoder Network), a deep learning model.
• Data sources: Not specified, but typically involves radar reflectivity, satellite imagery, or ground-based precipitation observations for nowcasting.

Main Results

[Not specified in the provided text.]

Contributions

[Not specified in the provided text, but the novelty likely lies in the "Physics-Constrained" aspect and the "Enhanced Encoder-Decoder Network" architecture for precipitation nowcasting.]

Funding

[Not specified in the provided text.]

Citation

@article{Chi2026PCEEDNet,
  author = {Chi, Haotian and Gu, Lingjia and Yuan, Jianfu and Liu, Yan-An and Zhao, Yuheng and Wu, Keyu},
  title = {PCEED-Net: A Physics-Constrained Enhanced Encoder–Decoder Network for Precipitation Nowcasting},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2026},
  doi = {10.1109/tgrs.2026.3660822},
  url = {https://doi.org/10.1109/tgrs.2026.3660822}
}