Neuro-Spectral Architectures for Causal Physics-Informed Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911265491779584 |
|---|---|
| author | Bizzi, Arthur Moreira, Leonardo M. Marques, Márcio Mendonça, Leonardo de Oliveira, Christian Júnior Balestro, Vitor Fernandez, Lucas dos Santos Yukimura, Daniel Petrov, Pavel Pereira, João M. Novello, Tiago Nissenbaum, Lucas |
| author_facet | Bizzi, Arthur Moreira, Leonardo M. Marques, Márcio Mendonça, Leonardo de Oliveira, Christian Júnior Balestro, Vitor Fernandez, Lucas dos Santos Yukimura, Daniel Petrov, Pavel Pereira, João M. Novello, Tiago Nissenbaum, Lucas |
| contents | Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs). However, standard MLP-based PINNs often fail to converge when dealing with complex initial value problems, leading to solutions that violate causality and suffer from a spectral bias towards low-frequency components. To address these issues, we introduce NeuSA (Neuro-Spectral Architectures), a novel class of PINNs inspired by classical spectral methods, designed to solve linear and nonlinear PDEs with variable coefficients. NeuSA learns a projection of the underlying PDE onto a spectral basis, leading to a finite-dimensional representation of the dynamics which is then integrated with an adapted Neural ODE (NODE). This allows us to overcome spectral bias, by leveraging the high-frequency components enabled by the spectral representation; to enforce causality, by inheriting the causal structure of NODEs, and to start training near the target solution, by means of an initialization scheme based on classical methods. We validate NeuSA on canonical benchmarks for linear and nonlinear wave equations, demonstrating strong performance as compared to other architectures, with faster convergence, improved temporal consistency and superior predictive accuracy. Code and pretrained models are available in https://github.com/arthur-bizzi/neusa. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04966 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neuro-Spectral Architectures for Causal Physics-Informed Networks Bizzi, Arthur Moreira, Leonardo M. Marques, Márcio Mendonça, Leonardo de Oliveira, Christian Júnior Balestro, Vitor Fernandez, Lucas dos Santos Yukimura, Daniel Petrov, Pavel Pereira, João M. Novello, Tiago Nissenbaum, Lucas Machine Learning 68T07 I.2.1 Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs). However, standard MLP-based PINNs often fail to converge when dealing with complex initial value problems, leading to solutions that violate causality and suffer from a spectral bias towards low-frequency components. To address these issues, we introduce NeuSA (Neuro-Spectral Architectures), a novel class of PINNs inspired by classical spectral methods, designed to solve linear and nonlinear PDEs with variable coefficients. NeuSA learns a projection of the underlying PDE onto a spectral basis, leading to a finite-dimensional representation of the dynamics which is then integrated with an adapted Neural ODE (NODE). This allows us to overcome spectral bias, by leveraging the high-frequency components enabled by the spectral representation; to enforce causality, by inheriting the causal structure of NODEs, and to start training near the target solution, by means of an initialization scheme based on classical methods. We validate NeuSA on canonical benchmarks for linear and nonlinear wave equations, demonstrating strong performance as compared to other architectures, with faster convergence, improved temporal consistency and superior predictive accuracy. Code and pretrained models are available in https://github.com/arthur-bizzi/neusa. |
| title | Neuro-Spectral Architectures for Causal Physics-Informed Networks |
| topic | Machine Learning 68T07 I.2.1 |
| url | https://arxiv.org/abs/2509.04966 |