从基础机器学习势能中提取隐含的静电信息，让模型更高效且可预测红外光谱。
Distilling latent electrostatics from foundation machine learning interatomic potentials
- 用DFT能量和力训练轻量级模型，从基础势能中学习原子电荷与长程静电。
- 在液态水、浓盐酸和TiO2-水界面测试中，模型成功预测红外光谱与有效电荷。
- 微调少量高精度DFT数据即可显著提升界面系统的结构与光谱预测能力。
基础机器学习势能（MLIPs）已实现跨化学与材料空间的原子模拟，但多数仍计算成本高且缺乏显式静电，限制了对长程相互作用和电响应系统的应用。此前我们提出隐式埃瓦尔德求和（LES），仅基于密度泛函理论（DFT）的能量和力标签，学习隐含原子电荷与长程静电。本文利用LES从基础模型中提取静电：以教师模型预测的能量和力为标签，训练轻量级的LES增强学生模型，并可选地在额外DFT数据上微调。所得模型显著降低计算成本，同时提供玻恩有效电荷张量和红外光谱预测能力。我们在广泛的基础MLIPs（包括UMA、MACE、Orb、eSEN、GemNet-OC、PET和EquiformerV2）上进行基准测试，对比其在液态水、浓盐酸及锐钛矿TiO2(101)-水界面的实验红外光谱表现。结果显示，大多数基础模型均能提取静电响应。进一步表明，教师模型的DFT级别与训练数据比模型架构对静电与光谱精度影响更大。对于TiO2-水界面，使用少量更高水平的DFT数据微调后，结构与红外预测均得到改善。因此，基于LES的蒸馏为将基础MLIP转化为高效、电响应模型提供了实用路径，同时检验了基础模型中编码的物理保真度。
原文摘要 · Abstract (English)
Foundation machine learning interatomic potentials (MLIPs) have enabled atomistic simulations across broad regions of chemical and materials space, but many remain computationally expensive and lack explicit electrostatics, limiting their use for systems governed by long-range interactions and electrical response. Previously, we introduced Latent Ewald Summation (LES), which learns latent atomic charges and long-range electrostatics from density functional theory (DFT) energy and force labels alone. Here, we use LES to extract electrostatics that are latent in foundation models: energies and forces predicted by a teacher model are used to train a lightweight LES-augmented student MLIP, with optional fine-tuning on additional DFT data. The resulting models reduce computational cost while providing access to Born effective charge tensors, and infrared spectra. We benchmark student models distilled from a broad set of foundation MLIPs, including UMA, MACE, Orb, eSEN, GemNet-OC, PET, and EquiformerV2-based models, against experimental infrared spectra for liquid water, concentrated hydrochloric acid, and the anatase TiO2(101)-water interface. Across these systems, electrostatic response can be extracted from most foundation MLIPs. The benchmark further shows that the underlying DFT level and dataset used to train the teacher model play a larger role than architecture in determining electrostatic and spectroscopic accuracy. For the TiO2-water interface, fine-tuning with a modest amount of higher-level DFT data improves structural and infrared predictions. LES-based distillation therefore provides a practical route for converting foundation MLIPs into efficient, electrically responsive models, while also testing the physical fidelity encoded in foundation models.
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。