We have developed a machine learning model for critical cooling rates for metallic glasses based on computational properties, supporting in-silico screening for desired R_c values and significantly reducing reliance on time-consuming laboratory work. We compare results for features derived from easy-to-compute functions of elemental properties to more complex physically motivated properties using ab initio, machine-learning potentials, and empirical potential molecular dynamics methods. The established approach enables property acquisition across a diverse range of alloys. Analysis of various features for 34 alloys from 20 chemical systems shows that the best model for critical cooling rates was learned from one elemental property-based feature and three simulated features. The elemental property based feature is an ideal entropy value based on alloy stoichiometry. The simulated features were acquired from estimates of energies above the convex hull, changes in heat capacity, and the fraction of icosahedra-like Voronoi polyhedra. Models were assessed through a demanding cross validation test based on repeatedly leaving out full chemical systems as test sets and had an R² of 0.78 and a mean average error of 0.76 in units of log₁₀(K/s). We demonstrate with Shapley additive explanation analysis that the most impactful features have physically reasonable influence on model predictions. The established methodology can be applied to other high-throughput studies of material properties of diverse compositions.

中文翻译：

---

通过基于元素和分子模拟的特征化来机器学习金属玻璃临界冷却速率


我们开发了一个基于计算特性的机器学习模型，用于金属玻璃的临界冷却速率，支持对所需 R_c 值进行计算机筛选，并显着减少对耗时实验室工作的依赖。我们使用 ab initio、机器学习电位和经验电位分子动力学方法，将从易于计算的元素特性函数得出的特征结果与更复杂的物理动机特性进行比较。既定的方法使各种合金的性能获得成为可能。对来自 20 个化学体系的 34 种合金的各种特征的分析表明，临界冷却速率的最佳模型是从 1 个基于元素性质的特征和 3 个模拟特征中学习的。基于元素性质的特征是基于合金化学计量的理想熵值。模拟特征是通过对凸包上方能量、热容变化以及二十面体状 Voronoi 多面体的分数的估计获得的。模型通过苛刻的交叉验证测试进行评估，该测试基于反复遗漏完整的化学系统作为测试集，R² 为 0.78，平均误差为 0.76，单位为 log₁₀（K/s）。我们通过 Shapley 加法解释分析证明，最具影响力的特征对模型预测具有物理上合理的影响。已建立的方法可应用于不同成分的材料特性的其他高通量研究。