Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys

Abstract

Combining the efficiency of semi-empirical potentials with the accuracy of quantum mechanical methods, machine-learning interatomic potentials (MLIPs) have significantly advanced atomistic modeling in computational materials science and chemistry. This necessitates the continual development of MLIP models with improved accuracy and efficiency, which enable long-time scale molecular dynamics simulations to unveil the intricate underlying mechanisms that would otherwise remain elusive. Among various existing MLIP models, the moment tensor potential (MTP) model employs a highly descriptive rotationally-covariant moment tensor to describe the local atomic environment, enabling the use of even linear regression for model fitting. Although the current MTP model has achieved state-of-the-art efficiency for similar accuracy, there is still room for optimizing the contraction process of moment tensors. In this work, we propose an effective genetic algorithm based optimization scheme that can significantly reduce the number of independent moment tensor components and intermediate tensor components. This leads to a speedup of nearly one order of magnitude in efficiency and also improved accuracy compared to the traditional MTP model for intricate basis sets. We have applied our improved MTP model to predicting the energetic and dynamical properties of various point and planar defects in Ni-Al alloys, showing overall good performances and in general outperforming the semi-empirical potentials. This work paves the way for fast and accurate atomistic modeling of complex systems and provides a useful tool for modeling defects in Ni-Al alloys.

52 pages, 13 figures

References in corpus (36)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Implementation strategies in phonopy and phono3py
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Active learning of linearly parametrized interatomic potentials
• On-the-fly machine learning force field generation: Application to melting points
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Physics-inspired structural representations for molecules and materials
• Machine learning a general purpose interatomic potential for silicon
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• Deep Potential: a general representation of a many-body potential energy surface
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Impact of lattice relaxations on phase transitions in a high-entropy alloy studied by machine-learning potentials
• Deep Potentials for Materials Science
• Efficient global structure optimization with a machine learned surrogate model
• Machine learning of molecular properties: locality and active learning
• Machine-learning interatomic potential for radiation damage and defects in tungsten
• DPA-2: a large atomic model as a multi-task learner
• Gaussian approximation potentials for body-centered-cubic transition metals
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Progress in Computational Understanding of Ferroelectric Mechanisms in HfO${}_2$
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• Efficacy of surface error corrections to density functional theory calculations of vacancy formation energy in transition metals
• GPTFF: A high-accuracy out-of-the-box universal AI force field for arbitrary inorganic materials
• $\alpha$-$\beta$ phase transition of zirconium predicted by on-the-fly machine-learned force field
• E(n)-Equivariant Cartesian Tensor Passing Potential
• Phase stability of Au-Li binary systems studied using neural network potential
• Comprehensive ab initio study of effects of alloying elements on generalized stacking fault energies of Ni and Ni${}_3$Al
• General time-reversal equivariant neural network potential for magnetic materials
• Effects of applied mechanical strain on vacancy clustering in FCC Ni