Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.00867 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913131281776640 |
|---|---|
| author | You, Wen Zhou, Shaoqian Meng, Xuhui |
| author_facet | You, Wen Zhou, Shaoqian Meng, Xuhui |
| contents | Neural operators (NOs) provide a new paradigm for efficiently solving partial differential equations (PDEs), but their training depends on costly high-fidelity data from numerical solvers, limiting applications in complex systems. We propose a self-supervised neural operator (SNO) that generates accurate and diverse training data on the fly without numerical solvers. SNO consists of three parts: a physics-informed sampler (PI-sampler) based on Bayesian PINNs for efficient data generation, a function encoder (FE) for compact input-output representations, and an encoder-only Transformer for operator learning, mapping boundary/initial conditions, source terms, and geometries to PDE solutions. We validate SNO on 1D steady/unsteady nonlinear reaction-diffusion equations, a 2D nonlinear PDE with varying geometries, and vortex-induced vibration of a flexible cylinder in fluid dynamics. SNO achieves high accuracy in all cases, and lightweight finetuning (O(100) trainable variables) further improves predictions with only a few hundred steps. This work provides a new route toward pretrained foundation models as efficient PDE surrogates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00867 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-supervised neural operator for solving partial differential equations You, Wen Zhou, Shaoqian Meng, Xuhui Computational Physics Neural operators (NOs) provide a new paradigm for efficiently solving partial differential equations (PDEs), but their training depends on costly high-fidelity data from numerical solvers, limiting applications in complex systems. We propose a self-supervised neural operator (SNO) that generates accurate and diverse training data on the fly without numerical solvers. SNO consists of three parts: a physics-informed sampler (PI-sampler) based on Bayesian PINNs for efficient data generation, a function encoder (FE) for compact input-output representations, and an encoder-only Transformer for operator learning, mapping boundary/initial conditions, source terms, and geometries to PDE solutions. We validate SNO on 1D steady/unsteady nonlinear reaction-diffusion equations, a 2D nonlinear PDE with varying geometries, and vortex-induced vibration of a flexible cylinder in fluid dynamics. SNO achieves high accuracy in all cases, and lightweight finetuning (O(100) trainable variables) further improves predictions with only a few hundred steps. This work provides a new route toward pretrained foundation models as efficient PDE surrogates. |
| title | Self-supervised neural operator for solving partial differential equations |
| topic | Computational Physics |
| url | https://arxiv.org/abs/2509.00867 |