发表机构
Center for Computational Science and Engineering, Massachusetts Institute of Technology; Department of Materials Science and Engineering, Massachusetts Institute of Technology; John A. Paulson School of Engineering and Applied Sciences, Harvard University; Robert Bosch LLC Research and Technology Center, Watertown; Initiative for Computational Catalysis, Flatiron Institute（麻省理工学院计算科学与工程中心; 麻省理工学院材料科学与工程系; 哈佛大学约翰·A·保尔森工程与应用科学学院; 罗伯特博世有限责任公司研究和技术中心; 平顿研究所计算催化倡议）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RS-CIDER是一种机器学习非局域交换泛函，通过拟合能量和能级近似HSE06的短程Hartree-Fock交换项，在分子和固态性质上高度一致，且计算速度提升一个数量级以上。
AI 中文摘要
与半局域近似相比，屏蔽杂化泛函（如HSE06）改善了带隙、电荷局域化和氧化还原能量学的描述，但其显式的Hartree-Fock交换项对于大型周期性系统（尤其是在平面波基组计算中）计算成本高昂。在此，我们提出RS-CIDER，一种机器学习非局域交换泛函，通过显式拟合基态能量和单粒子能级来近似HSE06中的短程Hartree-Fock交换项。RS-CIDER结合了尺度不变的半局域和非局域密度描述符，并且可以在不显式应用短程Hartree-Fock交换算符的情况下自洽地评估。RS-CIDER在分子反应能量和固态带隙方面与HSE06表现出高度一致性。跨不同材料的进一步测试显示，RS-CIDER与HSE06在局部磁性、Cu-O相竞争、极化子局域化和中性缺陷能量学方面具有一致性。对于Fe橄榄石，化学特异性微调恢复了HSE06的Li插层电压。计时基准显示，相对于HSE06，RS-CIDER将每个自洽场步骤的实测墙钟时间减少了一个数量级以上。综合这些分子和固态结果，RS-CIDER被确立为一种高效的HSE06自洽机器学习替代模型。
英文摘要
Screened hybrid functionals such as HSE06 improve the description of band gaps, charge localization, and redox energetics relative to semilocal approximations, but their explicit Hartree-Fock exchange term is computationally costly for large, periodic systems, especially in plane-wave basis set calculations. Here we present RS-CIDER, a machine-learned non-local exchange functional that approximates the short-range Hartree-Fock exchange term in HSE06 by explicitly fitting both ground-state energies and single-particle energy levels. RS-CIDER combines scale-invariant semilocal and non-local density descriptors and can be evaluated self-consistently without explicitly applying the short-range Hartree-Fock exchange operator. RS-CIDER shows close agreement with HSE06 for molecular reaction energies and solid-state band gaps. Further tests across distinct materials show agreement between RS-CIDER and HSE06 for local magnetism, Cu-O phase competition, polaron localization, and neutral-defect energetics. For an Fe olivine, chemistry-specific fine-tuning recovers the HSE06 Li intercalation voltage. A timing benchmark shows that RS-CIDER reduces the measured per-SCF-step wall time by more than an order of magnitude relative to HSE06. Together, these molecular and solid-state results establish RS-CIDER as an efficient self-consistent machine-learned surrogate for HSE06.
