Deep Learning for Koopman Operator Estimation in Idealized Atmospheric Dynamics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929494614343680 |
|---|---|
| author | Millard, David Carr, Arielle Gaudreault, Stéphane |
| author_facet | Millard, David Carr, Arielle Gaudreault, Stéphane |
| contents | Deep learning is revolutionizing weather forecasting, with new data-driven models achieving accuracy on par with operational physical models for medium-term predictions. However, these models often lack interpretability, making their underlying dynamics difficult to understand and explain. This paper proposes methodologies to estimate the Koopman operator, providing a linear representation of complex nonlinear dynamics to enhance the transparency of data-driven models. Despite its potential, applying the Koopman operator to large-scale problems, such as atmospheric modeling, remains challenging. This study aims to identify the limitations of existing methods, refine these models to overcome various bottlenecks, and introduce novel convolutional neural network architectures that capture simplified dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06522 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Learning for Koopman Operator Estimation in Idealized Atmospheric Dynamics Millard, David Carr, Arielle Gaudreault, Stéphane Machine Learning Dynamical Systems Atmospheric and Oceanic Physics Deep learning is revolutionizing weather forecasting, with new data-driven models achieving accuracy on par with operational physical models for medium-term predictions. However, these models often lack interpretability, making their underlying dynamics difficult to understand and explain. This paper proposes methodologies to estimate the Koopman operator, providing a linear representation of complex nonlinear dynamics to enhance the transparency of data-driven models. Despite its potential, applying the Koopman operator to large-scale problems, such as atmospheric modeling, remains challenging. This study aims to identify the limitations of existing methods, refine these models to overcome various bottlenecks, and introduce novel convolutional neural network architectures that capture simplified dynamics. |
| title | Deep Learning for Koopman Operator Estimation in Idealized Atmospheric Dynamics |
| topic | Machine Learning Dynamical Systems Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2409.06522 |