面向DFT+U能量学的DPA-4力场的数据高效适配：以NiO为例
Data-Efficient Adaptation of DPA-4 Force Fields to DFT+U Energetics: A Case Study in NiO
浏览论文内容
中文总结 AI 辅助
本研究以NiO为案例，通过微调预训练的DPA-4力场，高效修正了源层面的错误相能量学，提出了一种预训练与目标微调结合的多保真度策略。
中文摘要 AI 辅助
基于机器学习的力场（MLFF）这类基础模型，常以涵盖广泛材料的数据集进行预训练，而这类数据集的电子结构惯例可能无法复现特定关联材料所需的相能量学。本文以NiO为案例，探究能否通过目标层面的微调高效修正源层面的错误相能量学。在常见的结构插值中，非自旋极化的PBE泛函与铁磁PBE+U泛函对八面体Oct相和平面正方形Sqr相的能量排序预测结果相反。预训练的DPA-4模型可快速适配NiO的PBE+U表面，仅需约170个PBE+U标签，即可达到约0.5 meV/原子的能量均方根误差（RMSE）和约30 meV/Å的力均方根误差。关键的是，此前针对相反的无U表面完成微调的模型，其恢复定性PBE+U相排序所需的目标数据效率，与直接从各自预训练初始化参数进行微调的模型几乎相同。本研究结果表明，错误的源层面相能量学可通过目标层面的微调得到逆转，同时提出了一种实用的多保真度策略：预训练阶段优先选择广泛、一致且成本低廉的数据，而规模较小的目标层面数据集则通过特定应用的微调来实现所需的能量学。
英文摘要
Foundation machine-learned force fields (MLFFs) are often pretrained on broad materials datasets whose electronic-structure conventions may not reproduce the phase energetics required for a specific correlated material. Using NiO as a case study, we examine whether incorrect source-level phase energetics can be corrected efficiently through target-level fine-tuning. Along a common structural interpolation, non-spin-polarized PBE and ferromagnetic PBE+U predict opposite energetic orderings of the octahedral Oct and square-planar Sqr phases. Pretrained DPA-4 models adapt rapidly to the NiO PBE+U surface, reaching energy and force root-mean-square errors (RMSEs) of approximately 0.5 meV/atom and 30 meV/Å, respectively, with approximately 170 PBE+U labels. Crucially, models previously fine-tuned to the opposing no-U surface recover the qualitative PBE+U phase ordering with nearly the same target-data efficiency as models fine-tuned directly from their respective pretrained initializations. Our results show that incorrect source-level phase energetics can be reversed through target-level fine-tuning, and suggest a practical multi-fidelity strategy in which pretraining prioritizes broad, consistent, and affordable data, while compact target-level datasets impose energetics through application-specific fine-tuning.
