Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
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_ | 1866912582385795072 |
|---|---|
| author | Serino, Daniel A. Bell, Evan Klasky, Marc Southworth, Ben S. Nadiga, Balasubramanya Wilcox, Trevor Korobkin, Oleg |
| author_facet | Serino, Daniel A. Bell, Evan Klasky, Marc Southworth, Ben S. Nadiga, Balasubramanya Wilcox, Trevor Korobkin, Oleg |
| contents | In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive modeling is complicated by uncertainty in parameters that characterize various aspects of the modeled system, such as those characterizing material properties, equation of state (EOS), opacities, and initial conditions. Typically, however, these parameters are not directly observable. What is observed instead is a time sequence of radiographic projections using X-rays. In this work, we define a set of sparse hydrodynamic features derived from the outgoing shock profile and outer material edge, which can be obtained from radiographic measurements, to directly infer such parameters. Our machine learning (ML)-based methodology involves a pipeline of two architectures, a radiograph-to-features network (R2FNet) and a features-to-parameters network (F2PNet), that are trained independently and later combined to approximate a posterior distribution for the parameters from radiographs. We show that the estimated parameters can be used in a hydrodynamics code to obtain density fields and hydrodynamic shock and outer edge features that are consistent with the data. Finally, we demonstrate that features resulting from an unknown EOS model can be successfully mapped onto parameters of a chosen analytical EOS model, implying that network predictions are learning physics, with a degree of invariance to the underlying choice of EOS model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20192 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions Serino, Daniel A. Bell, Evan Klasky, Marc Southworth, Ben S. Nadiga, Balasubramanya Wilcox, Trevor Korobkin, Oleg Computational Physics Machine Learning High Energy Physics - Phenomenology In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive modeling is complicated by uncertainty in parameters that characterize various aspects of the modeled system, such as those characterizing material properties, equation of state (EOS), opacities, and initial conditions. Typically, however, these parameters are not directly observable. What is observed instead is a time sequence of radiographic projections using X-rays. In this work, we define a set of sparse hydrodynamic features derived from the outgoing shock profile and outer material edge, which can be obtained from radiographic measurements, to directly infer such parameters. Our machine learning (ML)-based methodology involves a pipeline of two architectures, a radiograph-to-features network (R2FNet) and a features-to-parameters network (F2PNet), that are trained independently and later combined to approximate a posterior distribution for the parameters from radiographs. We show that the estimated parameters can be used in a hydrodynamics code to obtain density fields and hydrodynamic shock and outer edge features that are consistent with the data. Finally, we demonstrate that features resulting from an unknown EOS model can be successfully mapped onto parameters of a chosen analytical EOS model, implying that network predictions are learning physics, with a degree of invariance to the underlying choice of EOS model. |
| title | Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions |
| topic | Computational Physics Machine Learning High Energy Physics - Phenomenology |
| url | https://arxiv.org/abs/2412.20192 |