AI 中文总结
本文开发了电场响应图神经网络（EFR-GNN），将其应用于MgO、GaAs、α-AgI的电场驱动动力学有限温度模拟，实现了对相关现象的准确描述，为该领域模拟提供了新途径。
AI 中文摘要
电场驱动动力学的有限温度模拟需要统一描述原子间相互作用、局域电子态以及构型依赖的电响应。第一性原理模拟的尺度受限于算力，而传统机器学习势缺乏电场效应。近期机器学习框架已纳入电响应或原子分辨的电子态信息，但很少在单一框架中同时包含两者。本文开发了电场响应图神经网络（EFR-GNN），可预测能量、力、Born有效电荷张量、原子分辨电荷与磁矩，并支持带原子分辨局域电子态追踪的长时间电场驱动分子动力学。在空穴掺杂MgO中，静态电场通过由近邻模型量化的前后不对称性校正热激活空穴极化子的跳跃；在GaAs中，共振太赫兹激发产生相干Γ点横光学声子，其退相与实验一致，且相反螺旋度可反转其旋转；在超离子α-AgI中，该模型重现了温度依赖的Ag⁺迁移率与集体电场驱动离子漂移。综上，EFR-GNN为电场驱动原子与局域载流子动力学的有限温度模拟提供了一种方法。
英文摘要
Finite-temperature simulations of electric-field-driven dynamics need a unified description of interatomic interactions, local electronic states, and configuration-dependent electric responses. First-principles simulations remain scale-limited, whereas conventional machine-learning potentials lack electric-field effects. Recent machine-learning frameworks have incorporated electric-field response or atom-resolved electronic-state information, but rarely both within a single framework. Here, we develop an electric-field-response graph neural network (EFR-GNN) that predicts energies, forces, Born effective charge tensors, atom-resolved charges and magnetic moments, and supports long-time field-driven molecular dynamics with atom-resolved tracking of localized electronic states. In hole-doped MgO, static fields rectify thermally activated hole-polaron hopping through a forward--backward asymmetry quantified by a nearest-neighbor model. In GaAs, resonant terahertz excitation generates a coherent $Γ$-point transverse-optical phonon with dephasing consistent with experiment, while opposite helicities reverse its rotation. In superionic $α$-AgI, it reproduces temperature-dependent Ag$^+$ mobility and collective field-driven ionic drift. Together, EFR-GNN offers an approach to finite-temperature simulations of field-driven atomic and localized-carrier dynamics.
