发表机构
University of North Carolina at Charlotte; Los Alamos National Laboratory; North Carolina Battery Complexity, Autonomous Vehicle and Electrification (BATT CAVE) Research Center（北卡罗来纳大学夏洛特分校; 洛斯阿拉莫斯国家实验室; 北卡罗来纳电池复杂性、自动驾驶与电气化（BATT CAVE）研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究基准测试了通用机器学习力场在高能分子晶体结构预测中的可靠性，发现GAFF预弛豫可减少失败，其中MACE-OFF在平滑性、结构保真度和应力收敛间取得最佳平衡。
AI 中文摘要
通用机器学习原子间势（UMLIPs）的最新发展为基于几何弛豫和能量排序筛选分子晶体提供了一条快速途径，但它们在化学多样性含能材料上的可靠性仍不明确。特别是，尚不清楚这些UMLIPs是否过于敏感，在弛豫周期性晶体时破坏所需的分子连通性。在此，我们检验了以下假设：经典力场预弛豫可以为后续UMLIP弛豫提供更合适的起始几何结构，并在一个大型高能分子晶体数据库上进行了验证。我们将三个模型（MACE、MACE-OFF和UMA）与通用安培力场（GAFF）结合使用来检验这一假设。其中，直接使用MACE-OFF和UMA表现出非常高的弛豫成功率，并最接近地保持了参考几何结构，但它们仍会在某些罕见情况下失败。使用GAFF预弛豫可以系统地减少弛豫失败的数量，且计算成本更低。我们的对比性失败与鲁棒性分析揭示了所评估模型之间的不同权衡。其中，MACE-OFF在势能面平滑性、结构保真度和应力收敛之间取得了更好的折中，可作为自动化结构优化的可靠基础的良好选择。
英文摘要
Recent developments of universal machine learning interatomic potentials (UMLIPs) offer a fast route for screening molecular crystals based on geometry relaxation and energy ranking, but their reliability across chemically diverse energetic materials remains elusive. In particular, it is unclear whether or not these UMLIPs are over-sensitive to break the desired molecular connectivity for relaxing the periodic crystals. Herein we tested the hypothesis that classical force-field pre-relaxation can provide a more suitable starting geometry for subsequent UMLIP relaxation on a large database of high energy molecular crystals. Three models (MACE, MACE-OFF and UMA) in conjunction with the General Amber Force Field (GAFF) were applied to test this hypothesis. Among them, direct MACE-OFF and UMA showed very high relaxation success and preserved the reference geometries most closely, but they still exhibit failures for some rare cases. Using GAFF pre-relaxation can systematically reduce the number of failed relaxations with lower computational costs. Our comparative failure and robustness analyses revealed distinct trade-offs among the evaluated models. Among them, MACE-OFF achieves a better compromise between potential energy surface smoothness, structural fidelity, and stress convergence, serving as a good choice to provide a reliable foundation for automated structural optimization.
Comments10 pages, 9 figures
