| Abstract Scope |
Predicting glasses’ properties from their structures is challenging because of the inherently disordered atomic configurations. Here we tackle the problem using a machine learning algorithm. First, local environments are encoded by the SOAP descriptors, which are then fed into extreme gradient boosting tree algorithm to train/predict given samples’ configurational energy. After ranking the relative importance of the extracted local environments using their SHAP values during the ML training, 40 important unique local environments (ULEs) most responsible for the global energy of ZrCu-based glasses are identified. Markedly, we discover that the same short-range orders of Voronoi cells, when embedded in various ULEs, could impact the sample’s global stability in qualitatively different manners. These findings thus reveal a profound connection between short-range orders and medium-range orders. By varying the cut-off radius in the SOAP encoding process, we discover an optimal training/prediction performance, which may indicate an effective length scale for medium-range orders. |