长程静电学用于机器学习的原子间势能更简单
Long-range electrostatics for machine learning interatomic potentials is easier than we thought
- Department of Chemistry, UC Berkeley, California 94720, United States（加州大学伯克利分校化学系）
- Chemical Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, California, 94720, United States（伯克利国家实验室化学科学部）
- Bakar Institute of Digital Materials for the Planet, UC Berkeley, California 94720, United States（为地球数字化材料研究所）
- The Institute of Science and Technology Austria, Am Campus 1, 3400 Klosterneuburg, Austria（奥地利科学与技术研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出通过两个设计原则简化长程静电学在机器学习原子间势能中的应用，表明其比传统认知更简单且更具普遍性。
AI中文摘要：
缺乏长程静电学是现代机器学习原子间势能（MLIPs）的关键限制，阻碍了其在界面、电荷转移反应、极性和离子材料以及生物分子中的可靠应用。在本文综述中，我们提炼了Latent Ewald Summation（LES）框架背后的两个设计原则，该框架能够通过仅学习标准能量和力训练数据来捕捉长程相互作用、电荷和电响应：（i）使用具有环境依赖性的库仑功能形式来捕捉静电相互作用，（ii）避免对含糊的密度泛函理论（DFT）部分电荷进行显式训练。当这两个原则都得到满足时，仍然具有显著的灵活性：本质上任何短程MLIP都可以进行增强；在需要时可以添加电荷平衡方案；可以推断或微调偶极子和Born有效电荷；并且可以进一步结合电荷/自旋态嵌入或张量目标。我们还讨论了当前的局限性和开放性挑战。这些最小的、受物理指导的设计规则表明，将长程静电学纳入MLIPs中比人们通常认为的更简单且可能更具普遍性。
英文摘要：
The lack of long-range electrostatics is a key limitation of modern machine learning interatomic potentials (MLIPs), hindering reliable applications to interfaces, charge-transfer reactions, polar and ionic materials, and biomolecules. In this Perspective, we distill two design principles behind the Latent Ewald Summation (LES) framework, which can capture long-range interactions, charges, and electrical response just by learning from standard energy and force training data: (i) use a Coulomb functional form with environment-dependent charges to capture electrostatic interactions, and (ii) avoid explicit training on ambiguous density functional theory (DFT) partial charges. When both principles are satisfied, substantial flexibility remains: essentially any short-range MLIP can be augmented; charge equilibration schemes can be added when desired; dipoles and Born effective charges can be inferred or finetuned; and charge/spin-state embeddings or tensorial targets can be further incorporated. We also discuss current limitations and open challenges. Together, these minimal, physics-guided design rules suggest that incorporating long-range electrostatics into MLIPs is simpler and perhaps more broadly applicable than is commonly assumed.
