On-the-fly machine learning force field generation: Application to melting points

Abstract

An efficient and robust on-the-fly machine learning force field method is developed and integrated into an electronic-structure code. This method realizes automatic generation of machine learning force fields on the basis of Bayesian inference during molecular dynamics simulations, where the first principles calculations are only executed, when new configurations out of already sampled datasets appear. The developed method is applied to the calculation of melting points of Al, Si, Ge, Sn and MgO. The applications indicate that more than 99 \% of the first principles calculations are bypassed during the force field generation. This allows the machine to quickly construct first principles datasets over wide phase spaces. Furthermore, with the help of the generated machine learning force fields, simulations are accelerated by a factor of thousand compared with first principles calculations. Accuracies of the melting points calculated by the force fields are examined by thermodynamic perturbation theory, and the examination indicates that the machine learning force fields can quantitatively reproduce the first principles melting points.

15 pages, 7 figures and 2 tables

References in corpus (18)

• Restoring the density-gradient expansion for exchange in solids and surfaces
• Generalized gradient approximation for solids and their surfaces
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Machine Learning Unifies the Modelling of Materials and Molecules
• Active learning of linearly parametrized interatomic potentials
• Machine-learning based interatomic potential for amorphous carbon
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• How van der Waals interactions determine the unique properties of water
• Machine learning a general purpose interatomic potential for silicon
• Machine learning of molecular properties: locality and active learning
• Silicon liquid structure and crystal nucleation from ab-initio deep Metadynamics
• Efficient nonparametric $n$-body force fields from machine learning
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Computing Gibbs free energy differences by interface pinning
• Melting Si: beyond density functional theory
• Electron correlation and the phase diagram of Si
• First-principle study of the melting temperature of MgO

Cited by in corpus (109)

• Machine-learning interatomic potentials for materials science
• Unified Representation of Molecules and Crystals for Machine Learning
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• De novo exploration and self-guided learning of potential-energy surfaces
• A practical guide to machine learning interatomic potentials -- Status and future
• Efficient global structure optimization with a machine learned surrogate model
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
• Gaussian approximation potentials for body-centered-cubic transition metals
• Sparse Gaussian Process Potentials: Application to Lithium Diffusivity in Superionic Conducting Solid Electrolytes
• Tutorial: How to Train a Neural Network Potential
• Machine learned Force-Fields for an ab-initio Quality Description of Metal-Organic Frameworks
• Global optimization of atomistic structure enhanced by machine learning
• Roadmap on Electronic Structure Codes in the Exascale Era
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of Stanene
• High-Dimensional Potential Energy Surfaces for Molecular Simulations
• An Experimentally Driven Automated Machine Learned lnter-Atomic Potential for a Refractory Oxide
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• Stable solid molecular hydrogen above 900K from a machine-learned potential trained with diffusion Quantum Monte Carlo
• Anharmonic lattice dynamics in large thermodynamic ensembles with machine-learning force fields: CsPbBr${}_3$ a phonon-liquid with Cs rattlers
• Extending the limit of molecular dynamics with ab initio accuracy to 10 billion atoms
• $\alpha$-$\beta$ phase transition of zirconium predicted by on-the-fly machine-learned force field
• Elinvar effect in $\beta -$Ti simulated by on-the-fly trained moment tensor potential
• Layer-by-layer phase transformation in Ti${}_3$O${}_5$ revealed by machine learning molecular dynamics simulations
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation
• Ab initio structural optimization at finite temperatures based on anharmonic phonon theory: Application to the structural phase transitions of BaTiO${}_3$
• Controlled defect production in monolayer MoS2 via electron irradiation at ultralow accelerating voltages
• Exploring librational pathways with on-the-fly machine-learning force fields: Methylammonium molecules in MAPbX${}_3$ (X=I, Br, Cl) perovskites
• Progress, challenges and perspectives of computational studies on glassy superionic conductors for solid-state batteries
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Hydrogen Diffusion in Magnesium Using Machine Learning Potentials: a comparative study
• Machine-learning potentials enable predictive $\text{and}$ tractable high-throughput screening of random alloys
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Atomistic structure search using local surrogate mode
• Temperature-Dependent Chirality in Halide Perovskites
• Measuring transferability issues in machine-learning force fields: The example of Gold-Iron interactions with linearized potentials
• Machine learning density functionals from the random-phase approximation
• Tracing Ion Migration in Halide Perovskites with Machine Learned Force Fields
• In operando active learning of interatomic interaction during large-scale simulations
• Machine Learning for Exploring Small Polaron Configurational Space
• Ab-initio calculation of point defect equilibria during heat treatment: Nitrogen, hydrogen, and silicon doped diamond
• Active learning of effective Hamiltonian for super-large-scale atomic structures
• Machine Learned Interatomic Potentials for Ternary Carbides trained on the AFLOW Database
• Lattice thermal conductivity of ZrSe2 based on the anharmonic phonon approach and on-the-fly machine learning force fields
• Ab initio machine learning of phase space averages
• Hydrogen-induced degradation dynamics in silicon heterojunction solar cells via machine learning
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Mean-Field Density Matrix Decompositions
• Mixed-anion mixed-cation perovskite (FAPbI${}_3$)${}_{0.875}$(MAPbBr${}_3$)${}_{0.125}$: an ab-initio molecular dynamics study
• Machine learning phases and criticalities without using real data for training
• Electronic Structure and Vibrational Stability of Copper-substituted Lead Apatite (LK-99)
• Phase transitions of LaMnO${}_3$ and SrRuO${}_3$ from DFT + U based machine learning force fields simulations
• Physics-informed active learning for accelerating quantum chemical simulations
• Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations
• Designing Bimetallic Nanoparticle Catalysts via Tailored Surface Segregation
• Engineering Topological Phases Guided by Statistical and Machine Learning Methods
• Cascading symmetry constraint during machine learning-enabled structural search for sulfur induced Cu(111)-$(\sqrt{43}\times \sqrt{43})$ surface reconstruction
• Melting Temperature of Iron Under the Earth's Inner Core Condition from Deep Machine Learning
• Deep-learning-based prediction of the tetragonal$\to$cubic transition in davemaoite
• DPmoire: A tool for constructing accurate machine learning force fields in moiré systems
• Ab initio calculation of the magnetic Gibbs free energy of materials using magnetically constrained supercells
• A smooth basis for atomistic machine learning
• Gaussian Process Regression Adaptive Density-Guided Approach: Towards Calculations of Potential Energy Surfaces for Larger Molecules
• Machine learning at the atomic-scale
• Local structure, thermodynamics, and melting curve of boron phosphide at high pressures by deep learning-driven ab initio simulations
• Automated atomistic simulations of dissociated dislocations with ab initio accuracy
• 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
• AI-accelerated Materials Informatics Method for the Discovery of Ductile Alloys
• Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
• Quantum Delocalization Enables Water Dissociation on Ru(0001)
• Coexistence of Superconductivity and Superionicity in Li${}_2$MgH${}_{16}$
• Locally Spontaneous Dynamic Oxygen Migration on Biphenylene: A DFT Study
• Active-learning-based efficient prediction of ab-initio atomic energy: a case study on a Fe random grain boundary model with millions of atoms
• On-the-fly machine learning-augmented constrained AIMD to design new routes from glassy carbon to quenchable amorphous diamond with low pressure and temperature
• Molecular dynamics-driven global tetra-atomic potential energy surfaces: Application to the AlF dimer
• Why Superconducting Ta Qubits Have Fewer Tunneling Two-Level Systems at the Air-Oxide Interface Than Nb Qubits
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Combining Brillouin spectroscopy and machine learned interatomic potentials to probe mechanical properties of metal organic frameworks
• Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
• GPR_calculator: An On-the-Fly Surrogate Model to Accelerate Massive Nudged Elastic Band Calculations
• Large-scale cooperative sulfur vacancy dynamics in two-dimensional MoS2 from machine learning interatomic potentials
• Novel algorithms and high-performance cloud computing enable efficient fully quantum mechanical protein-ligand scoring
• Structure and thermodynamics of defects in Na-feldspar from a neural network potential
• Accurate Machine Learning Interatomic Potentials for Polyacene Molecular Crystals: Application to Single Molecule Host-Guest Systems
• Water structuring at stacked graphene interfaces unveiled by machine-learning molecular dynamics
• Evidence of Molecular Hydrogen in the N-doped LuH3 System: a Possible Path to Superconductivity?
• Temperature-transferable tight-binding model using a hybrid-orbital basis
• Surface Reconstructions in Thin-Films of Magnetic Topological Insulator MnBi${}_2$Te${}_4$
• Revisiting thermal transport in CuCl: First-principles calculations and machine learning force fields
• Machine-Learned Potentials for Solvation Modeling
• Towards Improved Quantum Machine Learning for Molecular Force Fields
• Interfacial Behavior from the Atomic Blueprint: Machine Learning-Guided Design of Spatially Functionalized a-SiO2 Surfaces
• High-pressure melting and elastic behavior of vanadium and niobium based on ab initio and machine learning molecular dynamics
• Anharmonicity and Coulomb pseudopotential effects on superconductivity in YH${}_6$ and YH${}_9$
• Impact of Metal Cation on Chiral Properties of 2D Halide Perovskites
• Oxygen-deficiency-driven phase segregation enables enhanced hole transport in amorphous tellurium oxides
• A Simple and Scalable Kernel Density Approach for Reliable Uncertainty Quantification in Atomistic Machine Learning
• Active Δ-learning with universal potentials for global structure optimization
• A molecular rotor driven by an electric field on graphene
• Smooth Overlap of Spin Orientations: Machine Learning Exchange Fields for Ab-initio Spin Dynamics
• Elastic properties of amorphous LiTaCl${}_6$ solid-state electrolyte
• Machine Learning Study of Surface Reconstructions of the Cu${}_2$O(111) Surface
• Thermal transport and phase transitions of zirconia by on-the-fly machine-learned interatomic potentials
• Deep machine learning potentials for multicomponent metallic melts: development, predictability and compositional transferability
• Atomistic mechanisms of phase transitions in all-temperature barocaloric material KPF${}_6$
• Validation of moment tensor potentials for fcc and bcc metals using EXAFS spectra