A physics-informed neural network framework for modeling obstacle-related equations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929550517075968 |
|---|---|
| author | Bahja, Hamid El Hauffen, Jan Christian Jung, Peter Bah, Bubacarr Karambal, Issa |
| author_facet | Bahja, Hamid El Hauffen, Jan Christian Jung, Peter Bah, Bubacarr Karambal, Issa |
| contents | Deep learning has been highly successful in some applications. Nevertheless, its use for solving partial differential equations (PDEs) has only been of recent interest with current state-of-the-art machine learning libraries, e.g., TensorFlow or PyTorch. Physics-informed neural networks (PINNs) are an attractive tool for solving partial differential equations based on sparse and noisy data. Here extend PINNs to solve obstacle-related PDEs which present a great computational challenge because they necessitate numerical methods that can yield an accurate approximation of the solution that lies above a given obstacle. The performance of the proposed PINNs is demonstrated in multiple scenarios for linear and nonlinear PDEs subject to regular and irregular obstacles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_03552 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A physics-informed neural network framework for modeling obstacle-related equations Bahja, Hamid El Hauffen, Jan Christian Jung, Peter Bah, Bubacarr Karambal, Issa Machine Learning Information Theory Numerical Analysis Analysis of PDEs Deep learning has been highly successful in some applications. Nevertheless, its use for solving partial differential equations (PDEs) has only been of recent interest with current state-of-the-art machine learning libraries, e.g., TensorFlow or PyTorch. Physics-informed neural networks (PINNs) are an attractive tool for solving partial differential equations based on sparse and noisy data. Here extend PINNs to solve obstacle-related PDEs which present a great computational challenge because they necessitate numerical methods that can yield an accurate approximation of the solution that lies above a given obstacle. The performance of the proposed PINNs is demonstrated in multiple scenarios for linear and nonlinear PDEs subject to regular and irregular obstacles. |
| title | A physics-informed neural network framework for modeling obstacle-related equations |
| topic | Machine Learning Information Theory Numerical Analysis Analysis of PDEs |
| url | https://arxiv.org/abs/2304.03552 |