Stratified construction of neural network based interatomic models for multicomponent materials

Abstract

Recent application of neural networks (NNs) to modeling interatomic interactions has shown the learning machines' encouragingly accurate performance for select elemental and multicomponent systems. In this study, we explore the possibility of building a library of NN-based models by introducing a hierarchical NN training. In such a stratified procedure NNs for multicomponent systems are obtained by sequential training from the bottom up: first unaries, then binaries, and so on. Advantages of constructing NN sets with shared parameters include acceleration of the training process and intact description of the constituent systems. We use an automated generation of diverse structure sets for NN training on density functional theory-level reference energies. In the test case of Cu, Pd, Ag, Cu-Pd, Cu-Ag, Pd-Ag, and Cu-Pd-Ag systems, NNs trained in the traditional and stratified fashions are found to have essentially identical accuracy for defect energies, phonon dispersions, formation energies, etc. The models' robustness is further illustrated via unconstrained evolutionary structure searches in which the NN is used for the local optimization of crystal unit cells.

References in corpus (13)

• On representing chemical environments
• High-throughput electronic band structure calculations: challenges and tools
• Perspective on density functional theory
• Perspective: Advances and challenges in treating van der Waals dispersion forces in density functional theory
• Van der Waals Density Functional for Layered Structures
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• New Superconducting and Semiconducting Fe-B Compounds Predicted with an Ab Initio Evolutionary Search
• A learning scheme to predict atomic forces and accelerate materials simulations
• Ab initio quality neural-network potential for sodium
• Stability of 41 metal - boron systems at 0 GPa and 30 GPa from first principles
• Van der Waals interactions in the ground state of Mg(BH4)2 from density functional theory

Cited by in corpus (29)

• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Machine learning a general purpose interatomic potential for silicon
• Machine-learning interatomic potentials for materials science
• De novo exploration and self-guided learning of potential-energy surfaces
• Towards high-throughput superconductor discovery via machine learning
• Data-driven learning of total and local energies in elemental boron
• Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
• Gaussian approximation potential modeling of lithium intercalation in carbon nanostructures
• Ephemeral data derived potentials for random structure search
• Hybrid neural network potential for multilayer graphene
• Simple machine-learned interatomic potentials for complex alloys
• MAISE: Construction of neural network interatomic models and evolutionary structure optimization
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Atomic energy mapping of neural network potential
• Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
• PyXtal FF: a Python Library for Automated Force Field Generation
• Unusual pressure-induced periodic lattice distortion in SnSe${}_2$
• Genarris: Random Generation of Molecular Crystal Structures and Fast Screening with a Harris Approximation
• KLIFF: A framework to develop physics-based and machine learning interatomic potentials
• Electronic structure based descriptor for characterizing local atomic environments
• Phase stability of Au-Li binary systems studied using neural network potential
• Prediction of stable Li-Sn compounds: boosting ab initio searches with neural network potentials
• Machine Learned Interatomic Potentials for Ternary Carbides trained on the AFLOW Database
• Generator of Neural Network Potential for Molecular Dynamics: Constructing Robust and Accurate Potentials with Active Learning for Nanosecond-scale Simulations
• A transferable artificial neural network model for atomic forces in nanoparticles
• Neural Networks Potential from the Bispectrum Component: A Case Study on Crystalline Silicon
• Machine learning search for stable binary Sn alloys with Na, Ca, Cu, Pd, and Ag
• Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary Alloys
• The Homunculus Brain and Categorical Logic