Improving physics-informed DeepONets with hard constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909229699301376 |
|---|---|
| author | Brecht, Rüdiger Popovych, Dmytro R. Bihlo, Alex Popovych, Roman O. |
| author_facet | Brecht, Rüdiger Popovych, Dmytro R. Bihlo, Alex Popovych, Roman O. |
| contents | Current physics-informed (standard or deep operator) neural networks still rely on accurately learning the initial and/or boundary conditions of the system of differential equations they are solving. In contrast, standard numerical methods involve such conditions in computations without needing to learn them. In this study, we propose to improve current physics-informed deep learning strategies such that initial and/or boundary conditions do not need to be learned and are represented exactly in the predicted solution. Moreover, this method guarantees that when a deep operator network is applied multiple times to time-step a solution of an initial value problem, the resulting function is at least continuous. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_07899 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Improving physics-informed DeepONets with hard constraints Brecht, Rüdiger Popovych, Dmytro R. Bihlo, Alex Popovych, Roman O. Machine Learning Numerical Analysis Computational Physics Current physics-informed (standard or deep operator) neural networks still rely on accurately learning the initial and/or boundary conditions of the system of differential equations they are solving. In contrast, standard numerical methods involve such conditions in computations without needing to learn them. In this study, we propose to improve current physics-informed deep learning strategies such that initial and/or boundary conditions do not need to be learned and are represented exactly in the predicted solution. Moreover, this method guarantees that when a deep operator network is applied multiple times to time-step a solution of an initial value problem, the resulting function is at least continuous. |
| title | Improving physics-informed DeepONets with hard constraints |
| topic | Machine Learning Numerical Analysis Computational Physics |
| url | https://arxiv.org/abs/2309.07899 |