对支持纳米颗粒的通用机器学习互原子势的基准测试：将能量精度与结构探索解耦
Benchmarking Universal Machine Learning Interatomic Potentials for Supported Nanoparticles: Decoupling Energy Accuracy from Structural Exploration
AI总结：
本文通过对比通用机器学习互原子势（uMLIPs）与特定领域模型，在支持纳米颗粒的Al₂O₃表面评估能量精度与结构探索能力，发现MACE-OMAT在能量精度上与DP-UniAlCu相当，而MatterSim-v1.0.0-1M在某些尺寸下能发现更稳定的结构。
AI中文摘要：
支持纳米颗粒催化剂在化工行业中被广泛应用。基于密度泛函理论（DFT）的计算建模通常涉及稳定局部最低能量构型的结构搜索和有限温度下的分子动力学（MD）模拟。这些任务在DFT中对大系统计算需求高且难以处理。在过去的二十年中，机器学习互原子势（MLIPs）已被成功用于显著增加可模拟系统的大小和时间尺度，以逼近DFT的精度。然而，训练可靠的MLIPs并不容易，因为它需要许多昂贵的DFT计算。最近，几种通用MLIPs（uMLIPs）已被开发，这些模型在涵盖广泛分子和材料的大型数据集上进行训练。本文通过将uMLIPs的准确性和效率与我们特定领域的DP-UniAlCu模型进行基准测试，发现MACE-OMAT能够合理地重现全局优化中发现的低能结构，其能量精度与DP-UniAlCu相当。有趣的是，MatterSim-v1.0.0-1M模型在结合能方面存在较大的偏差，但可以在某些支持纳米颗粒尺寸下发现比其他两个模型更稳定的结构，显示出其在结构探索方面的能力。对于MD模拟，MACE-OMAT和MatterSim-v1.0.0-1M能够定性地重现DP-UniAlCu预测的Cu原子均方位移（MSD_Cu），尽管成本大约高两个数量级。我们证明，即使没有任何微调，uMLIPs在模拟支持纳米颗粒方面也非常有用，尽管其减少的效率仍然是大规模模拟的限制因素。
英文摘要：
Supported nanoparticle catalysts are widely used in the chemical industry. Computational modeling of supported nanoparticles based on density functional theory (DFT) often involves structural searches of stable local minimum energy configurations and molecular dynamics simulations at finite temperature. These are computationally demanding tasks that are intractable within DFT for large systems. In the last two decades, machine learning interatomic potentials (MLIPs) have been successfully used to substantially increase the size and time scales accessible to simulations approximating DFT accuracy. However, training reliable MLIPs is non-trivial as it requires many costly DFT calculations. Recently, several universal MLIPs (uMLIPs) have been developed, which are trained on large datasets that cover a wide range of molecules and materials. Here, we benchmark the accuracy and the efficiency of these uMLIPs in describing Cu nanoparticles supported on Al$_2$O$_3$ surfaces against our domain-specific DP-UniAlCu model. We find that the MACE-OMAT can reproduce reasonably well the low-energy structures found in global optimization at an energy accuracy comparable to DP-UniAlCu. Interestingly, the MatterSim-v1.0.0-1M model, which exhibits larger deviations in the binding energies, can find even more stable configurations than the other two models in some supported nanoparticle sizes, showing its capability in structure exploration. For MD simulations, MACE-OMAT and MatterSim-v1.0.0-1M can qualitatively reproduce the mean-squared displacements of Cu atoms (MSD$_\mathrm{Cu}$) predicted by DP-UniAlCu, albeit at roughly two orders of magnitude higher cost. We demonstrate that the uMLIPs can be very useful in simulating supported nanoparticles even without any fine-tuning, though their reduced efficiency remains a limiting factor for large-scale simulations.
