Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions

Abstract 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 ini...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniel A. Serino, Evan Bell, Marc Klasky, Ben S. Southworth, Balasubramanya Nadiga, Trevor Wilcox, Oleg Korobkin
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-10869-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766635856986112
author Daniel A. Serino
Evan Bell
Marc Klasky
Ben S. Southworth
Balasubramanya Nadiga
Trevor Wilcox
Oleg Korobkin
author_facet Daniel A. Serino
Evan Bell
Marc Klasky
Ben S. Southworth
Balasubramanya Nadiga
Trevor Wilcox
Oleg Korobkin
author_sort Daniel A. Serino
collection DOAJ
description Abstract 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 machine learning architectures are able to accurately infer initial conditions and EOS parameters, and that the estimated parameters can be used in a hydrodynamics code to obtain density fields, shocks, and material interfaces that satisfy thermodynamic and hydrodynamic consistency. 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. To the best of our knowledge, our framework is the first demonstration of recovering both thermodynamic and hydrodynamic consistent density fields from noisy radiographs.
format Article
id doaj-art-eab5777ca83d4212bf71f0f444dec534
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-eab5777ca83d4212bf71f0f444dec5342025-08-20T03:04:30ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-10869-3Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosionsDaniel A. Serino0Evan Bell1Marc Klasky2Ben S. Southworth3Balasubramanya Nadiga4Trevor Wilcox5Oleg Korobkin6Theoretical Division, Los Alamos National LaboratoryTheoretical Division, Los Alamos National LaboratoryTheoretical Division, Los Alamos National LaboratoryTheoretical Division, Los Alamos National LaboratoryComputer, Computational, and Statistical Sciences Division, Los Alamos National LaboratoryTheoretical Design Division, Los Alamos National LaboratoryTheoretical Division, Los Alamos National LaboratoryAbstract 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 machine learning architectures are able to accurately infer initial conditions and EOS parameters, and that the estimated parameters can be used in a hydrodynamics code to obtain density fields, shocks, and material interfaces that satisfy thermodynamic and hydrodynamic consistency. 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. To the best of our knowledge, our framework is the first demonstration of recovering both thermodynamic and hydrodynamic consistent density fields from noisy radiographs.https://doi.org/10.1038/s41598-025-10869-3
spellingShingle Daniel A. Serino
Evan Bell
Marc Klasky
Ben S. Southworth
Balasubramanya Nadiga
Trevor Wilcox
Oleg Korobkin
Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
Scientific Reports
title Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
title_full Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
title_fullStr Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
title_full_unstemmed Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
title_short Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
title_sort physics consistent machine learning framework for inverse modeling with applications to icf capsule implosions
url https://doi.org/10.1038/s41598-025-10869-3
work_keys_str_mv AT danielaserino physicsconsistentmachinelearningframeworkforinversemodelingwithapplicationstoicfcapsuleimplosions
AT evanbell physicsconsistentmachinelearningframeworkforinversemodelingwithapplicationstoicfcapsuleimplosions
AT marcklasky physicsconsistentmachinelearningframeworkforinversemodelingwithapplicationstoicfcapsuleimplosions
AT benssouthworth physicsconsistentmachinelearningframeworkforinversemodelingwithapplicationstoicfcapsuleimplosions
AT balasubramanyanadiga physicsconsistentmachinelearningframeworkforinversemodelingwithapplicationstoicfcapsuleimplosions
AT trevorwilcox physicsconsistentmachinelearningframeworkforinversemodelingwithapplicationstoicfcapsuleimplosions
AT olegkorobkin physicsconsistentmachinelearningframeworkforinversemodelingwithapplicationstoicfcapsuleimplosions