Abstract
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 could 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 a high 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.
Highlights
Metallic glasses (MGs), as a unique class of amorphous materials, exhibit a high atomic packing density with pronounced topological and chemical short-to-medium range order[1,2,3,4]
Many properties of MGs can be depicted in terms of excursions in the potential energy landscape (PEL)[6,7,8], which is a multidimensional configurational space with local energy minima separated by barriers
We develop machine learning (ML) models to predict the propensity of thermally activated elementary excitation, from the atomic environment of the static MG structure
Summary
Metallic glasses (MGs), as a unique class of amorphous materials, exhibit a high atomic packing density with pronounced topological and chemical short-to-medium range order[1,2,3,4]. By fingerprinting the atomic site environment with a recently proposed interstice distribution representation[19], we find that ML can reliably identify atoms with the highest 5% and lowest 5% activation energy, reaching an area under the receiver operating characteristic curve (AUC-ROC) of 0.942 and 0.888, respectively Such accuracies are considerably better than that in previous ML predictions of the propensity for stress-driven shear transformations[18,19]. We conduct quantitative “between-task” transferring tests and show that our learnt model can be used to predict the propensity for shear transformation as well This ML work highlights the predictive power of local static structure to quantitatively connect with β processes in MGs. here we use activation-relaxation technique (ART)[27,28] to probe the propensity for thermal activation of each atom in MGs (see schematic description, which will be discussed later). This avoids the problem associated with common stress activation indicators (e.g., non-affine displacement or von Mises strain), which often exhibit a skewed “long-tail” distribution[29] and the resolution at the
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
