Scholarlink

Abstract <p>Atomistic simulations offer insights into material behavior at the atomic level. However, they can be computationally intensive. In this paper, two deep learning models, deep symbolic optimization (DSO) and deep neural networks (DNN), and one generative large language model, GPT-4o, are employed to construct surrogates for atomistic simulations. Specifically, atomistic simulations are first&#xa0;performed to investigate the collapse of a nanovoid under hydrostatic pressure. We focus on the role of initial void radius and material characteristics, such as intrinsic and unstable stacking fault energies and surface energy (SE). We find that the critical pressure required for void collapse spans from 17.05 to 19.62&#xa0;GPa, with the highest values corresponding to the maximum USFE. Additionally, an intermediate SE value (1068.13&#xa0;<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\hbox {mJ/m}^2\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mtext>mJ/m</mtext> <mn>2</mn> </msup> </math></EquationSource> </InlineEquation>) minimizes the critical pressure. Based on the simulation results, surrogate models based on DSO, DNN, and GPT-4o are constructed, concluding that the SE affects the critical pressure the most.</p> Graphical abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Constructing surrogates for atomistic simulations via deep learning and generative large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月7日

查看全文
  • Mahshad Fani,
  • William Chadwell,
  • Nishad Tasnim,
  • Xin Wang,
  • Mohammad Younes Araghi,
  • Kun Lu,
  • Zejian Zhou,
  • Tang Gu,
  • Shuozhi Xu

摘要

Abstract

Atomistic simulations offer insights into material behavior at the atomic level. However, they can be computationally intensive. In this paper, two deep learning models, deep symbolic optimization (DSO) and deep neural networks (DNN), and one generative large language model, GPT-4o, are employed to construct surrogates for atomistic simulations. Specifically, atomistic simulations are first performed to investigate the collapse of a nanovoid under hydrostatic pressure. We focus on the role of initial void radius and material characteristics, such as intrinsic and unstable stacking fault energies and surface energy (SE). We find that the critical pressure required for void collapse spans from 17.05 to 19.62 GPa, with the highest values corresponding to the maximum USFE. Additionally, an intermediate SE value (1068.13  \(\hbox {mJ/m}^2\) mJ/m 2 ) minimizes the critical pressure. Based on the simulation results, surrogate models based on DSO, DNN, and GPT-4o are constructed, concluding that the SE affects the critical pressure the most.

Graphical abstract