Specialising neural network potentials for accurate properties and application to the mechanical response of titanium

Tongqi Wen,David J Srolovitz,Lingyu Zhu,Rui Wang,Zhaoxuan Wu,Linfeng Zhang,Han Wang

doi:10.1038/s41524-021-00661-y

Abstract

Large scale atomistic simulations provide direct access to important materials phenomena not easily accessible to experiments or quantum mechanics-based calculation approaches. Accurate and efficient interatomic potentials are the key enabler, but their development remains a challenge for complex materials and/or complex phenomena. Machine learning potentials, such as the Deep Potential (DP) approach, provide robust means to produce general purpose interatomic potentials. Here, we provide a methodology for specialising machine learning potentials for high fidelity simulations of complex phenomena, where general potentials do not suffice. As an example, we specialise a general purpose DP method to describe the mechanical response of two allotropes of titanium (in addition to other defect, thermodynamic and structural properties). The resulting DP correctly captures the structures, energies, elastic constants and γ-lines of Ti in both the HCP and BCC structures, as well as properties such as dislocation core structures, vacancy formation energies, phase transition temperatures, and thermal expansion. The DP thus enables direct atomistic modelling of plastic and fracture behaviour of Ti. The approach to specialising DP interatomic potential, DPspecX, for accurate reproduction of properties of interest “X”, is general and extensible to other systems and properties.

Highlights

Most mechanical responses of structural metals and alloys are governed by defect interactions at the atomistic scale and their evolution at the meso- to macro-scales
We introduce a general procedure for training accurate, neuralnetwork interatomic potentials fit-for-purpose and demonstrate this approach by training an interatomic potential for accurate simulations of the mechanical response of Ti
To overcome the systematic inadequacy of these empirical/semi-empirical interatomic potentials, we focus on machine learning neural network-based interatomic potentials[12]

Summary

Introduction

Most mechanical responses of structural metals and alloys are governed by defect interactions at the atomistic scale and their evolution at the meso- to macro-scales. While many different machine learning approaches to training interatomic potentials[18,19,20,21,22,23,24,25] are emerging (some for Ti26,27), we explicitly focus on developing machine learning potentials for the prediction of mechanical properties of α − β Ti. Here, we propose a specialising step, an extension to the current DP-GEN scheme, to systematically train machine learning interatomic potentials to reproduce crystal structures, elastic constant tensors, surface and stacking fault energies of Ti. The training datasets include experimental data from the literature and DFT data calculated in this work.

Results

Conclusion