Skip to main content
QUICK REVIEW

[论文解读] Performance of universal machine learning potentials in global optimization

Edan T. Marcial, L. N. Chaudhary|arXiv (Cornell University)|Feb 26, 2026
Machine Learning in Materials Science被引用 0
一句话总结

本研究在不同无机体系的全局无约束结构搜索中基准九种通用机器学习势(uMLPs),以评估它们定位DFT基态结构的能力。

ABSTRACT

Rapid development of universal machine learning potentials (uMLPs) and expansion of training data sets are reshaping the state of the art in atomistic simulation, highlighting the need for concurrent systematic benchmarking of their capabilities. Global optimization is among the most demanding uMLP applications because unconstrained exploration includes probing motifs not present in reference sets. We examined the latest generation of uMLPs in unconstrained evolutionary searches to assess whether these models can consistently predict complex crystal structure ground states across diverse inorganic systems. Our findings demonstrate that the considered M3GNet, MACE, SevenNet, EquiformerV2, MatterSim, GRACE, eSEN, Orb-v3, and PET-MAD models span a wide performance range, from near ab initio to essentially non-predictive, in their ability to resolve competing phases within low-energy basins. Additional tests on hcp-Zn, MB$_4$ (M = Cr, Mn, and Fe), and LiB$_{y}$ ($y\approx 0.9$) ground states reveal that several uMLPs capture fine energy differences arising from subtle electronic structure features.

研究动机与目标

  • 评估当前uMLPs在多种化学体系的无约束全局搜索中定位晶体基态结构的能力。
  • 评估uMLPs在超出训练数据的低能盆地探索中的鲁棒性。
  • 在多种泛函下,将代理势驱动的结果与参考DFT进行比较。
  • 识别不同uMLP架构在结构预测任务中的优点与失败模式。

提出的方法

  • 在不进行微调的情况下使用开箱即用的预训练uMLPs(M3GNet、MACE、SevenNet、EquiformerV2、MatterSim、GRACE、eSEN、Orb-v3、PET-MAD)。
  • 使用MAISE进行零温度进化搜索,以生成候选结构族。
  • 对候选体进行每个uMLP的放松,并使用DFT(PBE/PBEsol/r2SCAN)重新优化以进行基准比较。
  • 通过合并来自各uMLP的极小值池并使用DFT重新放松,计算结构和能量接近度量。
  • 使用将uMLP与DFT池之间的平均能量偏移量相减的排名RMSE来评估排序保真度。
  • 分析uMLPs在再现已知相以及识别任何伪极小值方面的表现。
Figure 1: Stability of the tI10-Na 2 CN 2 , mS28-MgB 3 C 3 , and oI28-MgB 3 C 3 phases identified in this work relative to reported mS10-Na 2 CN 2 and hP14-MgB 3 C 3 evaluated with common DFT functionals.
Figure 1: Stability of the tI10-Na 2 CN 2 , mS28-MgB 3 C 3 , and oI28-MgB 3 C 3 phases identified in this work relative to reported mS10-Na 2 CN 2 and hP14-MgB 3 C 3 evaluated with common DFT functionals.

实验结果

研究问题

  • RQ1当前的uMLPs是否能够在多样化无机化学体系的无约束全局搜索中可靠地分辨竞争的低能晶体结构?
  • RQ2不同uMLPs产生的代理PES景观在能量排序和极小值结构接近度方面与DFT相比如何?
  • RQ3哪些uMLPs在具有挑战性的案例(如Zn c/a异常、MB4衍生物、LiBx偏化学计量相)中最能再现基态结构模式?
  • RQ4在全局优化中uMLPs的常见失效模式(如伪极小值、排序错误、vdW或堆叠问题等)是什么,如何缓解?

主要发现

  • uMLPs的性能范围广,从接近从头计算到在低能盆地内几乎不可预测。
  • 若干uMLPs(特别是eSEN和一些中到大型架构)能够捕捉由微妙电子结构特征引起的细微能量差异,从而在基态预测中表现良好。
  • 一些化合物(如Zn c/a异常、MB4衍生物、LiBx非化学计量相)揭示了特定弱点,如排序错误、层间距过高估计或伪低能极小值。
  • 代理放松能量景观在完全放松后对DFT有适度但系统性的偏离,催生潜在的混合工作流(NN放松结合单次DFT能量)。
  • 将九种uMLP合并的池进行对比,可以一致评估到DFT极小值的接近度和排序保真度,在相关案例中,排名RMSE通常在几meV/原子到数十meV/原子范围内。
  • 总体上,uMLPs在排名准确性方面通常优于先前针对研究的M-Sn二元系统的特定Behler–Parrinello NN势。
Figure 2: Performance metrics on merged pools assessed relative to the reference DFT method, PBEsol for PT and PBE for the rest, and averaged over 11 compounds, excluding AgClO 4 . The schematics at the top clarify the definitions of the proximity and ranking metrics introduced in the text. The repr
Figure 2: Performance metrics on merged pools assessed relative to the reference DFT method, PBEsol for PT and PBE for the rest, and averaged over 11 compounds, excluding AgClO 4 . The schematics at the top clarify the definitions of the proximity and ranking metrics introduced in the text. The repr

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。