Development and optimization of physics-informed neural networks for solving partial differential equations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915138082177024 |
|---|---|
| author | Sharimbayev, Batyr Kadyrov, Shirali Kavokin, Aleksei |
| author_facet | Sharimbayev, Batyr Kadyrov, Shirali Kavokin, Aleksei |
| contents | This work compares the advantages and limitations of the Finite Difference Method with Physics-Informed Neural Networks, showing where each can best be applied for different problem scenarios. Analysis on the L2 relative error based on one-dimensional and two-dimensional Poisson equations suggests that FDM gives far more accurate results with a relative error of 7.26 x 10-8 and 2.21 x 10-4, respectively, in comparison with PINNs, with an error of 5.63 x 10-6 and 6.01 x 10-3 accordingly. Besides forward problems, PINN is realized also for forward-inverse problems which reflect its ability to predict source term after its sufficient training. Visualization of the solution underlines different methodologies adopted by FDM and PINNs, yielding useful insights into their performance and applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02599 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Development and optimization of physics-informed neural networks for solving partial differential equations Sharimbayev, Batyr Kadyrov, Shirali Kavokin, Aleksei General Mathematics This work compares the advantages and limitations of the Finite Difference Method with Physics-Informed Neural Networks, showing where each can best be applied for different problem scenarios. Analysis on the L2 relative error based on one-dimensional and two-dimensional Poisson equations suggests that FDM gives far more accurate results with a relative error of 7.26 x 10-8 and 2.21 x 10-4, respectively, in comparison with PINNs, with an error of 5.63 x 10-6 and 6.01 x 10-3 accordingly. Besides forward problems, PINN is realized also for forward-inverse problems which reflect its ability to predict source term after its sufficient training. Visualization of the solution underlines different methodologies adopted by FDM and PINNs, yielding useful insights into their performance and applicability. |
| title | Development and optimization of physics-informed neural networks for solving partial differential equations |
| topic | General Mathematics |
| url | https://arxiv.org/abs/2502.02599 |