Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning

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, howe...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Qi Wang, Jun Ding, Longfei Zhang, Evgeny Podryabinkin, Alexander Shapeev, Evan Ma
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Acceso en línea:https://doaj.org/article/607c7977330949b6958952bb11789513
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:607c7977330949b6958952bb11789513
record_format dspace
spelling oai:doaj.org-article:607c7977330949b6958952bb117895132021-12-02T13:33:28ZPredicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning10.1038/s41524-020-00467-42057-3960https://doaj.org/article/607c7977330949b6958952bb117895132020-12-01T00:00:00Zhttps://doi.org/10.1038/s41524-020-00467-4https://doaj.org/toc/2057-3960Abstract 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.Qi WangJun DingLongfei ZhangEvgeny PodryabinkinAlexander ShapeevEvan MaNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 6, Iss 1, Pp 1-12 (2020)
institution DOAJ
collection DOAJ
language EN
topic Materials of engineering and construction. Mechanics of materials
TA401-492
Computer software
QA76.75-76.765
spellingShingle Materials of engineering and construction. Mechanics of materials
TA401-492
Computer software
QA76.75-76.765
Qi Wang
Jun Ding
Longfei Zhang
Evgeny Podryabinkin
Alexander Shapeev
Evan Ma
Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning
description 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.
format article
author Qi Wang
Jun Ding
Longfei Zhang
Evgeny Podryabinkin
Alexander Shapeev
Evan Ma
author_facet Qi Wang
Jun Ding
Longfei Zhang
Evgeny Podryabinkin
Alexander Shapeev
Evan Ma
author_sort Qi Wang
title Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning
title_short Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning
title_full Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning
title_fullStr Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning
title_full_unstemmed Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning
title_sort predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/607c7977330949b6958952bb11789513
work_keys_str_mv AT qiwang predictingthepropensityforthermallyactivatedbeventsinmetallicglassesviainterpretablemachinelearning
AT junding predictingthepropensityforthermallyactivatedbeventsinmetallicglassesviainterpretablemachinelearning
AT longfeizhang predictingthepropensityforthermallyactivatedbeventsinmetallicglassesviainterpretablemachinelearning
AT evgenypodryabinkin predictingthepropensityforthermallyactivatedbeventsinmetallicglassesviainterpretablemachinelearning
AT alexandershapeev predictingthepropensityforthermallyactivatedbeventsinmetallicglassesviainterpretablemachinelearning
AT evanma predictingthepropensityforthermallyactivatedbeventsinmetallicglassesviainterpretablemachinelearning
_version_ 1718392854699573248