用深度学习加速半导体光谱模拟，实现高温下高精度计算。
Deep Neural Network for Phonon-Assisted Optical Spectra in Semiconductors
- 结合深度学习紧束缚模型与分子动力学，快速生成哈密顿量。
- 在100-400K温度范围准确模拟硅和砷化镓的声子诱导带隙变化。
- 适合研究复杂材料中电子-声子耦合现象的高通量计算。
基于第一性原理的有限温度下半导体声子辅助光学谱的精确模拟仍面临巨大挑战，因其需大超胞进行声子采样，并依赖计算成本高昂的高精度交换关联（XC）泛函。本文提出一种高效方法，结合深度学习紧束缚与势能模型，以第一性原理精度解决该问题。通过分子动力学采样原子构型，并利用深度学习实现哈密顿量快速评估，该方法可大规模模拟温度依赖的光学性质，使用先进XC泛函（HSE、SCAN）。在硅和砷化镓上验证，温度范围为100–400 K，结果准确捕捉了声子引起的带隙重整化及间接/直接吸收过程，与实验数据在五数量级范围内高度一致。本工作为复杂材料中电子-声子耦合现象的高通量研究开辟新路径，突破传统方法因大超胞与昂贵泛函带来的计算瓶颈。
原文摘要 · Abstract (English)
Ab initio based accurate simulation of phonon-assisted optical spectra of semiconductors at finite temperatures remains a formidable challenge, as it requires large supercells for phonon sampling and computationally expensive high-accuracy exchange-correlation (XC) functionals. In this work, we present an efficient approach that combines deep learning tight-binding and potential models to address this challenge with ab initio fidelity. By leveraging molecular dynamics for atomic configuration sampling and deep learning-enabled rapid Hamiltonian evaluation, our approach enables large-scale simulations of temperature-dependent optical properties using advanced XC functionals (HSE, SCAN). Demonstrated on silicon and gallium arsenide across temperature 100-400 K, the method accurately captures phonon-induced bandgap renormalization and indirect/direct absorption processes which are in excellent agreement with experimental findings over five orders of magnitude. This work establishes a pathway for high-throughput investigation of electron-phonon coupled phenomena in complex materials, overcoming traditional computational limitations arising from large supercell used with computationally expensive XC-functionals.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。