无需训练电荷数据，机器学习势能即可预测材料电响应
Machine learning interatomic potential can infer electrical response
- 在潜空间埃瓦尔德求和框架下，仅用能量力数据提取极化与有效电荷张量
- 成功预测水的红外光谱、高温超离子冰离子电导率及钛酸铅相变滞回
- 适用于电场驱动过程模拟，尤其适合大规模复杂体系
材料与化学系统在电场下的响应建模仍是长期挑战。机器学习原子间势（MLIPs）提供了高效可扩展的替代方案，但传统方法不包含电响应。本文展示，在潜空间埃瓦尔德求和（LES）框架下，仅通过学习能量与力数据，即可直接从长程MLIP中提取极化与玻恩有效电荷（BEC）张量。利用该方法，我们预测了无外场或外加电场下体相水的红外光谱、高压超离子冰的离子电导率，以及铁电钛酸铅钙钛矿的相变与滞回行为。本工作将MLIP的预测能力拓展至电响应领域，无需训练电荷或极化数据，实现了对多种体系中电场驱动过程的高精度规模化建模。
原文摘要 · Abstract (English)
Modeling the response of material and chemical systems to electric fields remains a longstanding challenge. Machine learning interatomic potentials (MLIPs) offer an efficient and scalable alternative to quantum mechanical methods but do not by themselves incorporate electrical response. Here, we show that polarization and Born effective charge (BEC) tensors can be directly extracted from long-range MLIPs within the Latent Ewald Summation (LES) framework, solely by learning from energy and force data. Using this approach, we predict the infrared spectra of bulk water under zero or finite external electric fields, ionic conductivities of high-pressure superionic ice, and the phase transition and hysteresis in ferroelectric PbTiO$_3$ perovskite. This work thus extends the capability of MLIPs to predict electrical response--without training on charges or polarization or BECs--and enables accurate modeling of electric-field-driven processes in diverse systems at scale.
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。