Reinforcing materials modelling by encoding the structures of defects in crystalline solids into distortion scores

Abstract

This work revises the concept of defects in crystalline solids and proposes a universal strategy for their characterization at the atomic scale using outlier detection based on statistical distances. The proposed strategy provides a generic measure that describes the distortion score of local atomic environments. This score facilitates automatic defect localization and enables a stratified description of defects, which allows to distinguish the zones with different levels of distortion within the structure. This work proposes applications for advanced materials modelling ranging from the surrogate concept for the energy per atom to the relevant information selection for evaluation of energy barriers from the mean force. Moreover, this concept can serve for design of robust interatomic machine learning potentials and high-throughput analysis of their databases. The proposed definition of defects opens up many perspectives for materials design and characterization, promoting thereby the development of novel techniques in materials science.

Efficient and transferable machine learning potentials for the simulation of crystal defects in bcc Fe and W

“…However, the fitting databases of both potentials contained the Gao di-interstitial configuration I Gao 2 [72]. A detailed analysis based on outlier detection and distortion score shows that the components related to C15 clusters are missing in the ML GAP database [14]. As a possible solution to improve the performance of the GAP potential for C15 clusters, one may consider including 3D cluster structures into the training databases in order to enrich the variety of atomic environments known by the model.…”

“…The gray dotted lines labeled with V 1−3 refer to the energy barriers for migration of mono-, di-and tri-vacancies from DFT calculations in Fe [81] and W [79]. The saddle point structure in the inset plot of (a) is detected using the distortion score of local atomic environments [14]. The atoms are colored according to the magnitude of the distortion score (yellow -high, green -medium, blue -low).…”

“…The missing configurations can be revealed at the stage of the database design using the distortion scores based on outlier analysis of the database. This method was recently demonstrated to be very efficient for a similar problem with GAP potential for Fe [14].…”

“…ML potentials require an extensive training database because its content has a strong impact on the accuracy and transferability of the potential. The design of the database, which includes the choice of relevant information, as well as the selection of pertinent instances [12][13][14], called sparsification, is a crucial step for obtaining a relevant ML potential.…”

“…One can partially overcome this inconvenience with the help of well-chosen regularization, constant augmentation of the database or by using on-the-fly active learning techniques [53,57,59] in order to constantly increase the boundaries of interpolation regime. Alternatively to ML force fields, many other ML approaches and surrogate models are designed to characterize defects in crystalline materials [14,[60][61][62][63][64].…”