通过可解释的机器学习预测金属玻璃中热激活$β$事件的倾向
Predicting the propensity for thermally activated $β$ events in metallic glasses via interpretable machine learning
摘要：
金属玻璃（MG）中的元激发，即，$β$过程涉及在附近的子盆地之间跳跃，是金属玻璃许多不寻常性质的基础。然而，仅从原子位置对这些激活过程的倾向进行高效率预测仍然是一个艰巨的挑战。最近，采用精心设计的现场环境描述符和机器学习（ML），在预测压力激活的$β$过程（即，剪切变换）从静态结构。然而，复杂的张量应力场和方向依赖性激活会在数据中引入非平凡噪声，限制了所学习的结构-性质映射的准确性。在这里，我们专注于热激活的元激发，并在几个Cu-Zr MG中生成高质量的数据，从而可以定量绘制势能图。在对具有短距离和中等距离电荷分布的原子环境进行指纹识别后，ML可以识别出对热激活具有强抵抗力或高顺应性的原子，其精度超过了应力驱动激活事件的ML模型。有趣的是，一个定量的“任务间”转移测试表明，我们的学习模型也可以概括预测剪切转换的倾向。我们的数据集可能有助于对MG中结构-性质关系的未来ML模型进行基准测试。
英文摘要：
The elementary excitations in metallic glasses (MGs), i.e., $β$ processes that involve hopping between nearby sub-basins, underlie many unusual properties of the amorphous alloys. A high-efficacy prediction of the propensity for those activated processes from solely the atomic positions, however, has remained a daunting challenge. Recently, employing well-designed site environment descriptors and machine learning (ML), notable progress has been made in predicting the propensity for stress-activated $β$ processes (i.e., shear transformations) from the static structure. However, the complex tensorial stress field and direction-dependent activation would induce non-trivial noises in the data, limiting the accuracy of the structure-property mapping learned. Here, we focus on the thermally activated elementary excitations and generate high-quality data in several Cu-Zr MGs, allowing quantitative mapping of the potential energy landscape. After fingerprinting the atomic environment with short- and medium-range interstice distribution, ML can identify the atoms with strong resistance or high compliance to thermal activation, at an unprecedented accuracy over ML models for stress-driven activation events. Interestingly, a quantitative "between-task" transferring test reveals that our learnt model can also generalize to predict the propensity of shear transformation. Our dataset is potentially useful for benchmarking future ML models on structure-property relationships in MGs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
