arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.13774cond-mat.mtrl-scicond-mat.dis-nn
收藏

$ab$分子动力学电子结构的神经网络表示

Neural network representation of electronic structure from $ab$ $initio$ molecular dynamics

Qiangqiang Gu, Linfeng Zhang, Ji Feng

摘要:

尽管其丰富的信息内容,在$ab$ $initio$分子动力学模拟中大量积累的电子结构数据通常未得到充分利用。我们引入了一个可转移的高保真度神经网络表示这样的数据的形式紧束缚哈密顿晶体材料。$ab$ $initio$电子结构的这种预测表示与机器学习增强的分子动力学相结合,能够实现高效准确的电子演化和采样。当应用于一维电荷密度波材料碳炔时,我们能够计算正则系综的光谱函数和电导率。在孤子-反孤子对湮灭过程中的谱函数的评估揭示了显着的重整化的低能边缘模式,由于延迟的电子晶格耦合超过Born-Oppenheimer限制。电子结构动力学系统的有效和可重复使用的代理模型的可用性将使计算许多有趣的物理性质,铺平道路,以前无法进入或具有挑战性的途径,在材料建模。

英文摘要:

Despite their rich information content, electronic structure data amassed at high volumes in $ab$ $initio$ molecular dynamics simulations are generally under-utilized. We introduce a transferable high-fidelity neural network representation of such data in the form of tight-binding Hamiltonians for crystalline materials. This predictive representation of $ab$ $initio$ electronic structure, combined with machine-learning boosted molecular dynamics, enables efficient and accurate electronic evolution and sampling. When applied to a one-dimension charge-density wave material, carbyne, we are able to compute the spectral function and optical conductivity in the canonical ensemble. The spectral functions evaluated during soliton-antisoliton pair annihilation process reveal significant renormalization of low-energy edge modes due to retarded electron-lattice coupling beyond the Born-Oppenheimer limit. The availability of an efficient and reusable surrogate model for the electronic structure dynamical system will enable calculating many interesting physical properties, paving way to previously inaccessible or challenging avenues in materials modeling.

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。

↑