AI 中文总结
该研究评估通用机器学习原子间势的跨几何可迁移性，构建ZrO₂多构型数据集，测试26个预训练模型，发现零样本预测存在几何依赖型误差，对比不同训练策略，指出适配低配位离子纳米结构需多样目标数据与物理验证。
AI 中文摘要
基于机器学习的原子间势（MLIPs）相比第一性原理方法，能以低得多的计算成本实现原子级模拟，但人们对其在不同结构几何下的可靠性仍了解不足。受实验观察到的ZrO₂烧结过程（涉及颈部变薄和原子线形成）启发，我们构建了涵盖块体、 slab、颗粒、颈部及原子级细线环境的ZrO₂构型密度泛函理论数据集。我们首先对26个预训练MLIPs进行基准测试，发现零样本预测存在明显的几何依赖型性能下降；无需任何训练，仅经参考能量对齐后，最优零样本模型ORB-V3的能量和力均方根误差分别达到6 meV/原子和197.3 meV/Å，其中颈部和线构型的力误差最大。随后我们比较了零样本推理、微调及从头训练策略：微调的能量和力误差低于从头训练，且两者所需的 wall-clock 时间相当；几何特异性微调提升了域内精度，但常对其他结构类别产生负迁移，而混合几何微调则降低了跨几何误差。对弹性和振动性质、表面能及颈部动力学的评估进一步表明，基于平均能量和力误差的排序无法普遍预测性质层面的行为。这些结果说明，将基础MLIPs适配到低配位（离子）纳米结构时，需要几何多样化的目标数据和独立的物理验证。
英文摘要
Foundation machine-learning interatomic potentials (MLIPs) enable atomistic simulations at substantially lower computational cost than first-principles methods, but their reliability across structural geometries remains insufficiently understood. Here, we construct a density-functional-theory dataset of ZrO2 configurations spanning bulk, slab, particle, neck, and atomically thin wire environments motivated by an experimentally observed ZrO2 desintering process involving neck thinning and atomic wire formation. We first benchmark 26 pretrained MLIPs and observe pronounced geometry-dependent degradation in zero-shot predictions. Without any training, after only reference-energy alignment, the best zero-shot model (ORB-V3) reaches energy and force root-mean-square errors of 6 meV/atom and 197.3 meV/Å, respectively, with the largest force errors in neck and wire configurations. We then compare zero-shot inference, fine-tuning, and training from scratch strategies. Fine-tuning yields lower energy and force errors than training from scratch, while both require comparable wall-clock time. Geometry-specific fine-tuning improves in-domain accuracy but frequently produces negative transfer to other structural classes, whereas mixed-geometry fine-tuning reduces cross-geometry errors. Evaluations of elastic and vibrational properties, surface energies, and neck dynamics further show that rankings based on average energy and force errors do not universally predict property-level behavior. These results demonstrate that geometry-diverse target data and independent physical validations are necessary when adapting foundation MLIPs to low-coordination (ionic) nanostructures.
