Saved in:
Bibliographic Details
Main Authors: Wang, Zixu, Wang, Yuhan, Ma, Junfei, Wu, Fuyuan, Yan, Junchi, Yuan, Xiaohui, Zhang, Zhe, Zhang, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.16227
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918101350612992
author Wang, Zixu
Wang, Yuhan
Ma, Junfei
Wu, Fuyuan
Yan, Junchi
Yuan, Xiaohui
Zhang, Zhe
Zhang, Jie
author_facet Wang, Zixu
Wang, Yuhan
Ma, Junfei
Wu, Fuyuan
Yan, Junchi
Yuan, Xiaohui
Zhang, Zhe
Zhang, Jie
contents This work presents predictive hydrodynamic simulations empowered by artificial intelligence (AI) for laser driven implosion experiments, taking the double-cone ignition (DCI) scheme as an example. A Transformer-based deep learning model MULTI-Net is established to predict implosion features according to laser waveforms and target radius. A Physics-Informed Decoder (PID) is proposed for high-dimensional sampling, significantly reducing the prediction errors compared to Latin hypercube sampling. Applied to DCI experiments conducted on the SG-II Upgrade facility, the MULTI-Net model is able to predict the implosion dynamics measured by the x-ray streak camera. It is found that an effective laser absorption factor about 65\% is suitable for the one-dimensional simulations of the DCI-R10 experiments. For shot 33, the mean implosion velocity and collided plasma density reached 195 km/s and 117 g/cc, respectively. This study demonstrates a data-driven AI framework that enhances the prediction ability of simulations for complicated laser fusion experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16227
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Predictive Hydrodynamic Simulations for Laser Direct-drive Implosion Experiments via Artificial Intelligence
Wang, Zixu
Wang, Yuhan
Ma, Junfei
Wu, Fuyuan
Yan, Junchi
Yuan, Xiaohui
Zhang, Zhe
Zhang, Jie
Plasma Physics
Artificial Intelligence
This work presents predictive hydrodynamic simulations empowered by artificial intelligence (AI) for laser driven implosion experiments, taking the double-cone ignition (DCI) scheme as an example. A Transformer-based deep learning model MULTI-Net is established to predict implosion features according to laser waveforms and target radius. A Physics-Informed Decoder (PID) is proposed for high-dimensional sampling, significantly reducing the prediction errors compared to Latin hypercube sampling. Applied to DCI experiments conducted on the SG-II Upgrade facility, the MULTI-Net model is able to predict the implosion dynamics measured by the x-ray streak camera. It is found that an effective laser absorption factor about 65\% is suitable for the one-dimensional simulations of the DCI-R10 experiments. For shot 33, the mean implosion velocity and collided plasma density reached 195 km/s and 117 g/cc, respectively. This study demonstrates a data-driven AI framework that enhances the prediction ability of simulations for complicated laser fusion experiments.
title Predictive Hydrodynamic Simulations for Laser Direct-drive Implosion Experiments via Artificial Intelligence
topic Plasma Physics
Artificial Intelligence
url https://arxiv.org/abs/2507.16227