Spherical Physics-Informed Neural Operator with Multi-Scale Coupling for Meteorological Downscaling

Ye, Yiqiang; Wang, Yichi; Wen, Jiawei; Jiang, Jiahui; Zhong, Zhaoyu; Yu, Jiangjian; Xiao, Chunxia; Zhang, Haodi

doi:10.24963/ijcai.2026/734

Spherical Physics-Informed Neural Operator with Multi-Scale Coupling for Meteorological Downscaling

Yiqiang Ye, Yichi Wang, Jiawei Wen, Jiahui Jiang, Zhaoyu Zhong, Jiangjian Yu, Chunxia Xiao, Haodi Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI4Tech: AI Enabling Technologies. Pages 6600-6608.

https://doi.org/10.24963/ijcai.2026/734

Keywords

Domain-specific AI4Tech: Other AI4Tech applications

Abstract

Meteorological downscaling is crucial for high-resolution regional climate forecasting and disaster early warning. While neural operators have emerged as a promising paradigm for modeling complex spatiotemporal mappings, existing frameworks often struggle with spherical manifold geometric distortions, inherent atmospheric multi-scale coupling mismatches, and lack of explicit atmospheric laws. We propose the Spherical Physics-informed Neural Operator, which utilizes a Spherical Laplacian Decomposition to partition atmospheric fields into hierarchical frequency components, maintaining exact point-wise correspondence across scales. To evaluate these representations at arbitrary locations, we introduce a localized spherical integral operator that approximates continuous kernel transforms via geometry-aware attention. Dynamical consistency is further enforced by embedding differentiable constraints into the learning process. Extensive experiments demonstrate that our framework attains superior accuracy and zero-shot generalization across various meteorological variables and unseen queries, representing a robust and interpretable solution for global-to-regional meteorological downscaling.

Yiqiang Ye, Yichi Wang, Jiawei Wen, Jiahui Jiang, Zhaoyu Zhong, Jiangjian Yu, Chunxia Xiao, and Haodi Zhang. 2026. Spherical Physics-Informed Neural Operator with Multi-Scale Coupling for Meteorological Downscaling. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 6600–6608. https://doi.org/10.24963/ijcai.2026/734

@inproceedings{ijcai2026p734,
  title     = {Spherical Physics-Informed Neural Operator with Multi-Scale Coupling for Meteorological Downscaling},
  author    = {Ye, Yiqiang and Wang, Yichi and Wen, Jiawei and Jiang, Jiahui and Zhong, Zhaoyu and Yu, Jiangjian and Xiao, Chunxia and Zhang, Haodi},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {6600--6608},
  year      = {2026},
  month     = {8},
  note      = {AI4Tech: AI Enabling Technologies},
  doi       = {10.24963/ijcai.2026/734},
  url       = {https://doi.org/10.24963/ijcai.2026/734},
}

TY  - CPAPER
TI  - Spherical Physics-Informed Neural Operator with Multi-Scale Coupling for Meteorological Downscaling
AU  - Ye, Yiqiang
AU  - Wang, Yichi
AU  - Wen, Jiawei
AU  - Jiang, Jiahui
AU  - Zhong, Zhaoyu
AU  - Yu, Jiangjian
AU  - Xiao, Chunxia
AU  - Zhang, Haodi
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 6600
EP  - 6608
DO  - 10.24963/ijcai.2026/734
UR  - https://doi.org/10.24963/ijcai.2026/734
ER  -