Saved in:
Bibliographic Details
Main Authors: Jones, Michael S., Kunimune, Justin, Casey, Daniel, Kustowski, Bogdan, Kur, Eugene, Humbird, Kelli
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.21006
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911420398960640
author Jones, Michael S.
Kunimune, Justin
Casey, Daniel
Kustowski, Bogdan
Kur, Eugene
Humbird, Kelli
author_facet Jones, Michael S.
Kunimune, Justin
Casey, Daniel
Kustowski, Bogdan
Kur, Eugene
Humbird, Kelli
contents A combination of physics-based simulation and experiments has been critical to achieving ignition in inertial confinement fusion (ICF). Simulation and experiment both produce a mixture of scalar and images outputs, however only a subset of simulated data are available experimentally. We introduce a generative framework, called JointDiff, which enables predictions of conditional simulation input and output distributions from partial, multi-modal observations. The model leverages joint diffusion to unify forward surrogate modeling, inverse inference, and output imputation into one architecture. We train our model on a large ensemble of three-dimensional Multi-Rocket Piston simulations and demonstrate high accuracy, statistical robustness, and transferability to experiments performed at the National Ignition Facility (NIF). This work establishes JointDiff as a flexible generative surrogate for multi-modal scientific tasks, with implications for understanding diagnostic constraints, aligning simulation to experiment, and accelerating ICF design.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21006
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A joint diffusion approach to multi-modal inference in inertial confinement fusion
Jones, Michael S.
Kunimune, Justin
Casey, Daniel
Kustowski, Bogdan
Kur, Eugene
Humbird, Kelli
Plasma Physics
A combination of physics-based simulation and experiments has been critical to achieving ignition in inertial confinement fusion (ICF). Simulation and experiment both produce a mixture of scalar and images outputs, however only a subset of simulated data are available experimentally. We introduce a generative framework, called JointDiff, which enables predictions of conditional simulation input and output distributions from partial, multi-modal observations. The model leverages joint diffusion to unify forward surrogate modeling, inverse inference, and output imputation into one architecture. We train our model on a large ensemble of three-dimensional Multi-Rocket Piston simulations and demonstrate high accuracy, statistical robustness, and transferability to experiments performed at the National Ignition Facility (NIF). This work establishes JointDiff as a flexible generative surrogate for multi-modal scientific tasks, with implications for understanding diagnostic constraints, aligning simulation to experiment, and accelerating ICF design.
title A joint diffusion approach to multi-modal inference in inertial confinement fusion
topic Plasma Physics
url https://arxiv.org/abs/2601.21006