Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron

Abstract

We show that the Gaussian Approximation Potential machine learning framework can describe complex magnetic potential energy surfaces, taking ferromagnetic iron as a paradigmatic challenging case. The training database includes total energies, forces, and stresses obtained from density-functional theory in the generalized-gradient approximation, and comprises approximately 150,000 local atomic environments, ranging from pristine and defected bulk configurations to surfaces and generalized stacking faults with different crystallographic orientations. We find the structural, vibrational and thermodynamic properties of the GAP model to be in excellent agreement with those obtained directly from first-principles electronic-structure calculations. There is good transferability to quantities, such as Peierls energy barriers, which are determined to a large extent by atomic configurations that were not part of the training set. We observe the benefit and the need of using highly converged electronic-structure calculations to sample a target potential energy surface. The end result is a systematically improvable potential that can achieve the same accuracy of density-functional theory calculations, but at a fraction of the computational cost.

References in corpus (6)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Machine-learning based interatomic potential for amorphous carbon
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Thermoelastic properties of $\alpha$-iron from first-principles
• Quasi-particle bands and structural phase transition of iron from Gutzwiller Density-Functional Theory

Cited by in corpus (63)

• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Physics-inspired structural representations for molecules and materials
• Machine learning a general purpose interatomic potential for silicon
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• An Accurate and Transferable Machine Learning Potential for Carbon
• De novo exploration and self-guided learning of potential-energy surfaces
• Deep Potentials for Materials Science
• Machine-learning interatomic potential for radiation damage and defects in tungsten
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Quantum-Accurate Spectral Neighbor Analysis Potential Models for Ni-Mo Binary Alloys and FCC Metals
• Ab initio vibrational free energies including anharmonicity for multicomponent alloys
• Predicting Young's Modulus of Glasses with Sparse Datasets using Machine Learning
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Machine learned Force-Fields for an ab-initio Quality Description of Metal-Organic Frameworks
• Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
• Equation of state of fluid methane from first principles with machine learning potentials
• Quantum-accurate magneto-elastic predictions with classical spin-lattice dynamics
• Temperature Effect on Phonon Dispersion Stability of Zirconium by Machine Learning-driven Atomistic Simulations
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• Quantifying Chemical Structure and Atomic Energies in Amorphous Silicon Networks
• A Novel Approach to Describe Chemical Environments in High Dimensional Neural Network Potentials
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Optimization and Validation of a Deep Learning CuZr Atomistic Potential: Robust Applications for Crystalline and Amorphous Phases with near-DFT Accuracy
• Machine learning for molecular dynamics with strongly correlated electrons
• A New Kind of Atlas of Zeolite Building Blocks
• Efficiency, Accuracy, and Transferability of Machine Learning Potentials: Application to Dislocations and Cracks in Iron
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Multiscale machine-learning interatomic potentials for ferromagnetic and liquid iron
• A deep machine learning potential for atomistic simulation of Fe-Si-O systems under Earth's outer core conditions
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Searching for iron nanoparticles with a general-purpose Gaussian approximation potential
• In operando active learning of interatomic interaction during large-scale simulations
• Modeling the Ga/As binary system across temperaturesand compositions from first principles
• Lattice dynamics and elastic properties of alpha-U at high-temperature and high-pressure by machine learning potential simulations
• Geometries of edge and mixed dislocations in bcc Fe from first principles calculations
• A "Magnetic" Machine Learning Interatomic Potential for Nickel
• Classical and Machine Learning Interatomic Potentials for BCC Vanadium
• A collinear-spin machine learned interatomic potential for Fe${}_7$Cr${}_2$Ni alloy
• Machine-learning of atomic-scale properties based on physical principles
• Ab initio Canonical Sampling based on Variational Inference
• Proper Orthogonal Descriptors for Efficient and Accurate Interatomic Potentials
• Imeall: A Computational Framework for the Calculation of the Atomistic Properties of Grain Boundaries
• Robust data-driven approach for predicting the configurational energy of high entropy alloys
• Fast proper orthogonal descriptors for many-body interatomic potentials
• Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys
• Automated atomistic simulations of dissociated dislocations with ab initio accuracy
• Benchmarking Structural Evolution Methods for Training of Machine Learned Interatomic Potentials
• Machine learning interatomic potential for the low-modulus Ti-Nb-Zr alloys in the vicinity of dynamical instability
• Machine-Learning Potentials Predict Orientation- and Mode-Dependent Fracture in Refractory Diborides
• Atomistic Graph Neural Networks for metals: Application to bcc iron
• MC3D: The Materials Cloud computational database of experimentally known stoichiometric inorganics
• Ab initio machine learning in chemical compound space
• Open-Science Platform for Computational Materials Science: AiiDA and the Materials Cloud
• DeFecT-FF: a machine learning force field framework for high throughput defect modeling in CdTe-based solar cells
• Radiation damage and phase stability of Al${}_x$CrCuFeNi${}_y$ alloys using a machine-learned interatomic potential
• Teaching Solid Mechanics to Artificial Intelligence: a fast solver for heterogeneous solids
• Core structure of dislocations in ordered ferromagnetic FeCo
• Development of data-driven spd tight-binding models of Fe -- parameterisation based on QSGW and DFT calculations including information about higher-order elastic constants
• Combining DFT with ML to study size specific interactions between metal clusters and adsorbates
• Analysis of Atomistic Representations Using Weighted Skip-Connections