Predictive Hydrodynamic Simulations for Laser Direct-drive Implosion Experiments via Artificial Intelligence

TL;DR

This paper introduces an AI-powered predictive framework using Transformer-based models and physics-informed decoding to accurately simulate laser-driven implosion experiments, improving efficiency and precision in complex fusion research.

Contribution

The study develops a novel AI framework with a Transformer model and physics-informed decoder to enhance hydrodynamic simulation accuracy for laser fusion experiments.

Findings

The MULTI-Net model accurately predicts implosion dynamics in experiments.

A 65% laser absorption factor is optimal for 1D simulations.

Predicted implosion velocity and plasma density closely match experimental data.

Abstract

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.