arXiv 2106.025282021-06physics.plasm-phcs.LG

多元素吸收光谱和发射光谱的神经网络替代模型

Neural Network Surrogate Models for Absorptivity and Emissivity Spectra of Multiple Elements

University of Notre Dame（圣母大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）

Michael D. Vander Wal, Ryan G. McClarren, Kelli D. Humbird

备注：: Elsevier Review Format, Double Spaced, 26 pages, 10 figures, 5 tables Michael D. Vander Wal: conceptualization, investigation, writing - original draft, writing - editing and review. Ryan G. McClarren - conceptualization, writing - editing and review. Kelli D. Humbird: conceptualization, writing - editing and review

摘要：

高能量密度物理的模拟在计算资源方面是昂贵的。特别是在高能量密度物理应用中，非局域热平衡（NLTE）区域等离子体不透明度的计算可能消耗高达辐射流体力学模拟总计算时间的90%。以前的工作已经证明，完全连接的自动编码器和深度联合信息神经网络（DJINN）的组合可以成功地取代氪的不透明度的标准NLTE计算。这项工作扩展了这个想法，将多个元素组合成一个单一的代理模型，重点放在自动编码器上。

英文摘要：

Simulations of high energy density physics are expensive in terms of computational resources. In particular, the computation of opacities of plasmas in the non-local thermal equilibrium (NLTE) regime can consume as much as 90\% of the total computational time of radiation hydrodynamics simulations for high energy density physics applications. Previous work has demonstrated that a combination of fully-connected autoencoders and a deep jointly-informed neural network (DJINN) can successfully replace the standard NLTE calculations for the opacity of krypton. This work expands this idea to combining multiple elements into a single surrogate model with the focus here being on the autoencoder.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。