The elementary excitations in metallic glasses (MGs), i.e., β processes that involve hopping between nearby sub-basins, underlie many unusual properties of these 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 representations 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 local structure. However, the complex stress field in the solid and direction-dependent activation inevitably induce non-trivial noises in the data and limit the quality of the structure-property relation learned. Here, we focus on 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 convey to predict the propensity of shear transformation. Our dataset is potentially useful for benchmarking future ML models on structure-property relationships in MGs. 

One could refer to npj Computational Materials (2020) 6:194 ; https://doi.org/10.1038/s41524-020-00467-4