Saved in:
Bibliographic Details
Main Authors: Zhang, Zhuo, Yang, Xi, Miao, Ying, Hu, Xiaobin, Gao, Yifu, Zhao, Yuan, Yang, Yong, Yang, Canqun, Khoo, Boocheong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.23192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914517397536768
author Zhang, Zhuo
Yang, Xi
Miao, Ying
Hu, Xiaobin
Gao, Yifu
Zhao, Yuan
Yang, Yong
Yang, Canqun
Khoo, Boocheong
author_facet Zhang, Zhuo
Yang, Xi
Miao, Ying
Hu, Xiaobin
Gao, Yifu
Zhao, Yuan
Yang, Yong
Yang, Canqun
Khoo, Boocheong
contents While Transformers have demonstrated remarkable potential in modeling Partial Differential Equations (PDEs), modeling large-scale unstructured meshes with complex geometries remains a significant challenge. Existing efficient architectures often employ feature dimensionality reduction strategies, which inadvertently induces Geometric Aliasing, resulting in the loss of critical physical boundary information. To address this, we propose the Physics-Geometry Operator Transformer (PGOT), designed to reconstruct physical feature learning through explicit geometry awareness. Specifically, we propose Spectrum-Preserving Geometric Attention (SpecGeo-Attention). Utilizing a ``physics slicing-geometry injection" mechanism, this module incorporates multi-scale geometric encodings to explicitly preserve multi-scale geometric features while maintaining linear computational complexity $O(N)$. Furthermore, PGOT dynamically routes computations to low-order linear paths for smooth regions and high-order non-linear paths for shock waves and discontinuities based on spatial coordinates, enabling spatially adaptive and high-precision physical field modeling. PGOT achieves consistent state-of-the-art performance across four standard benchmarks and excels in large-scale industrial tasks including airfoil and car designs.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23192
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
Zhang, Zhuo
Yang, Xi
Miao, Ying
Hu, Xiaobin
Gao, Yifu
Zhao, Yuan
Yang, Yong
Yang, Canqun
Khoo, Boocheong
Machine Learning
While Transformers have demonstrated remarkable potential in modeling Partial Differential Equations (PDEs), modeling large-scale unstructured meshes with complex geometries remains a significant challenge. Existing efficient architectures often employ feature dimensionality reduction strategies, which inadvertently induces Geometric Aliasing, resulting in the loss of critical physical boundary information. To address this, we propose the Physics-Geometry Operator Transformer (PGOT), designed to reconstruct physical feature learning through explicit geometry awareness. Specifically, we propose Spectrum-Preserving Geometric Attention (SpecGeo-Attention). Utilizing a ``physics slicing-geometry injection" mechanism, this module incorporates multi-scale geometric encodings to explicitly preserve multi-scale geometric features while maintaining linear computational complexity $O(N)$. Furthermore, PGOT dynamically routes computations to low-order linear paths for smooth regions and high-order non-linear paths for shock waves and discontinuities based on spatial coordinates, enabling spatially adaptive and high-precision physical field modeling. PGOT achieves consistent state-of-the-art performance across four standard benchmarks and excels in large-scale industrial tasks including airfoil and car designs.
title PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
topic Machine Learning
url https://arxiv.org/abs/2512.23192