MAISE: Construction of neural network interatomic models and evolutionary structure optimization

Abstract

Module for ab initio structure evolution (MAISE) is an open-source package for materials modeling and prediction. The code's main feature is an automated generation of neural network (NN) interatomic potentials for use in global structure searches. The systematic construction of Behler-Parrinello-type NN models approximating ab initio energy and forces relies on two approaches introduced in our recent studies. An evolutionary sampling scheme for generating reference structures improves the NNs' mapping of regions visited in unconstrained searches, while a stratified training approach enables the creation of standardized NN models for multiple elements. A more flexible NN architecture proposed here expands the applicability of the stratified scheme for an arbitrary number of elements. The full workflow in the NN development is managed with a customizable 'MAISE-NET' wrapper written in Python. The global structure optimization capability in MAISE is based on an evolutionary algorithm applicable for nanoparticles, films, and bulk crystals. A multitribe extension of the algorithm allows for an efficient simultaneous optimization of nanoparticles in a given size range. Implemented structure analysis functions include fingerprinting with radial distribution functions and finding space groups with the SPGLIB tool. This work overviews MAISE's available features, constructed models, and confirmed predictions.

References in corpus (35)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms
• CALYPSO: a method for crystal structure prediction
• On representing chemical environments
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Ab initio Random Structure Searching
• Molecular geometry optimization with a genetic algorithm
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Active learning of linearly parametrized interatomic potentials
• Van der Waals Density Functional for Layered Structures
• Machine-learning based interatomic potential for amorphous carbon
• Spin waves and revised crystal structure of honeycomb iridate Na2IrO3
• Machine learning a general purpose interatomic potential for silicon
• Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
• Discovery of a superhard iron tetraboride superconductor
• De novo exploration and self-guided learning of potential-energy surfaces
• Data-driven learning of total and local energies in elemental boron
• New Superconducting and Semiconducting Fe-B Compounds Predicted with an Ab Initio Evolutionary Search
• How to quantify energy landscapes of solids
• On the Completeness of Atomic Structure Representations
• Silicon liquid structure and crystal nucleation from ab-initio deep Metadynamics
• Ab initio quality neural-network potential for sodium
• The performance of Minima Hopping and Evolutionary Algorithms for cluster structure prediction
• Stability of 41 metal - boron systems at 0 GPa and 30 GPa from first principles
• Theoretical study of metal borides stability
• Stratified construction of neural network based interatomic models for multicomponent materials
• Prediction of new crystal structure phases in metal borides: a lithium monoboride analog to MgB2
• Au40: A Large Tetrahedral Magic Cluster
• Evolutionary Metadynamics: a Novel Method to Predict Crystal Structures
• Possible routes for synthesis of new boron-rich Fe-B and Fe(1-x)Cr(x)B4 compounds
• Predicting Polymeric Crystal Structures by Evolutionary Algorithms
• Stability and superconductivity of Ca-B phases at ambient and high pressure
• Advanced first-principles theory of superconductivity including both lattice vibrations and spin fluctuations: The case of FeB${}_4$
• MUSE: Multi-algorithm collaborative crystal structure prediction
• FLAME: a library of atomistic modeling environments

Cited by in corpus (18)

• Machine-learning interatomic potentials for materials science
• Towards high-throughput superconductor discovery via machine learning
• Ephemeral data derived potentials for random structure search
• Developments and Further Applications of Ephemeral Data Derived Potentials
• KLIFF: A framework to develop physics-based and machine learning interatomic potentials
• Prediction of stable Li-Sn compounds: boosting ab initio searches with neural network potentials
• Electronic, vibrational, and electron-phonon coupling properties in SnSe${}_2$ and SnS${}_2$ under pressure
• XtalOpt Version 13: Multi-Objective Evolutionary Search for Novel Functional Materials
• Prospect of high-temperature superconductivity in layered metal borocarbides
• Thermodynamic stability of Li-B-C compounds from first principles
• Stability-superconductivity map for compressed Na-intercalated graphite
• Machine learning search for stable binary Sn alloys with Na, Ca, Cu, Pd, and Ag
• Structurally Constrained Evolutionary Algorithm for the Discovery and Design of Metastable Phases
• First-principles design of ambient-pressure Mg${}_x$B${}_2$C${}_2$ and Na${}_x$BC superconductors
• Superconductor discovery in the emerging paradigm of Materials Informatics
• XtalOpt Version 14: Variable-Composition Crystal Structure Search for Functional Materials Through Pareto Optimization
• Optimal boron-doped graphene substrate for glucose Raman signal enhancement
• High-$T_{\mathrm{c}}$ Ag${}_x$BC and Cu${}_x$BC superconductors accessible via topochemical reactions