Moving sample method for solving time-dependent partial differential equations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917223782678528 |
|---|---|
| author | Xu, Beining Yu, Haijun Zhai, Jiayu Tang, Kejun Wan, Xiaoliang |
| author_facet | Xu, Beining Yu, Haijun Zhai, Jiayu Tang, Kejun Wan, Xiaoliang |
| contents | Solving time-dependent partial differential equations (PDEs) that exhibit sharp gradients or local singularities is computationally demanding, as traditional physics-informed neural networks (PINNs) often suffer from inefficient point allocation that wastes resources on regions already well-resolved. This paper presents an adaptive sampling framework for PINNs aimed at efficiently solving time-dependent partial differential equations with pronounced local singularities. The method employs a residual-driven strategy, where the spatial-temporal distribution of training points is iteratively updated according to the error field from the previous iteration. This targeted allocation enables the network to concentrate computational effort on regions with significant residuals, achieving higher accuracy with fewer sampling points compared to uniform sampling. Numerical experiments on representative PDE benchmarks demonstrate that the proposed approach improves solution quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18575 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Moving sample method for solving time-dependent partial differential equations Xu, Beining Yu, Haijun Zhai, Jiayu Tang, Kejun Wan, Xiaoliang Numerical Analysis Solving time-dependent partial differential equations (PDEs) that exhibit sharp gradients or local singularities is computationally demanding, as traditional physics-informed neural networks (PINNs) often suffer from inefficient point allocation that wastes resources on regions already well-resolved. This paper presents an adaptive sampling framework for PINNs aimed at efficiently solving time-dependent partial differential equations with pronounced local singularities. The method employs a residual-driven strategy, where the spatial-temporal distribution of training points is iteratively updated according to the error field from the previous iteration. This targeted allocation enables the network to concentrate computational effort on regions with significant residuals, achieving higher accuracy with fewer sampling points compared to uniform sampling. Numerical experiments on representative PDE benchmarks demonstrate that the proposed approach improves solution quality. |
| title | Moving sample method for solving time-dependent partial differential equations |
| topic | Numerical Analysis |
| url | https://arxiv.org/abs/2601.18575 |