Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation

Abstract

An active learning procedure called Deep Potential Generator (DP-GEN) is proposed for the construction of accurate and transferable machine learning-based models of the potential energy surface (PES) for the molecular modeling of materials. This procedure consists of three main components: exploration, generation of accurate reference data, and training. Application to the sample systems of Al, Mg and Al-Mg alloys demonstrates that DP-GEN can produce uniformly accurate PES models with a minimal number of reference data.

References in corpus (7)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Machine Learning Unifies the Modelling of Materials and Molecules
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Silicon liquid structure and crystal nucleation from ab-initio deep Metadynamics
• Stratified construction of neural network based interatomic models for multicomponent materials
• Diffusion quantum Monte Carlo study of the equation of state and point defects in aluminum

Cited by in corpus (113)

• Machine learning and the physical sciences
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• DeePMD-kit v2: A software package for Deep Potential models
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Machine-learning interatomic potentials for materials science
• The Phase Diagram of a Deep Potential Water Model
• A deep potential model with long-range electrostatic interactions
• De novo exploration and self-guided learning of potential-energy surfaces
• Deep Potentials for Materials Science
• Committee neural network potentials control generalization errors and enable active learning
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Efficient global structure optimization with a machine learned surrogate model
• Deep neural network for the dielectric response of insulators
• Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
• Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
• DPA-2: a large atomic model as a multi-task learner
• How to validate machine-learned interatomic potentials
• Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
• Machine Learning on Neutron and X-Ray Scattering
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
• Phase equilibrium of water with hexagonal and cubic ice using the SCAN functional
• Automated discovery of a robust interatomic potential for aluminum
• Deep Learning of Accurate Force Field of Ferroelectric HfO${}_2$
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Gaussian approximation potentials for body-centered-cubic transition metals
• Deep learning inter-atomic potential model for accurate irradiation damage simulations
• Ground state energy functional with Hartree-Fock efficiency and chemical accuracy
• Tutorial: How to Train a Neural Network Potential
• Global optimization of atomistic structure enhanced by machine learning
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• Structural Phase Transitions in SrTiO3 from Deep Potential Molecular Dynamics
• Direct prediction of phonon density of states with Euclidean neural networks
• Accurate Deep Potential model for the Al-Cu-Mg alloy in the full concentration space
• Artificial Intelligence in Material Engineering: A review on applications of AI in Material Engineering
• Viscosity in water from first-principles and deep-neural-network simulations
• Universal QM/MM Approaches for General Nanoscale Applications
• Liquid-Liquid Critical Point in Phosphorus
• Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
• Deep Ensembles vs. Committees for Uncertainty Estimation in Neural-Network Force Fields: Comparison and Application to Active Learning
• An Experimentally Driven Automated Machine Learned lnter-Atomic Potential for a Refractory Oxide
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle
• Accurate machine learning force fields via experimental and simulation data fusion
• Optimization and Validation of a Deep Learning CuZr Atomistic Potential: Robust Applications for Crystalline and Amorphous Phases with near-DFT Accuracy
• Deep Coarse-grained Potentials via Relative Entropy Minimization
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
• A Tungsten Deep Neural-Network Potential for Simulating Mechanical Property Degradation Under Fusion Service Environment
• Universal interatomic potential for perovskite oxides
• Elinvar effect in $\beta -$Ti simulated by on-the-fly trained moment tensor potential
• A first-principles machine-learning force field for heterogeneous ice nucleation on microcline feldspar
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Active Learning A Neural Network Model For Gold Clusters \& Bulk From Sparse First Principles Training Data
• Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials
• Revealing the molecular structures of a-Al2O3(0001)-water interface by machine learning based computational vibrational spectroscopy
• Machine learning based non-Newtonian fluid model with molecular fidelity
• A deep machine learning potential for atomistic simulation of Fe-Si-O systems under Earth's outer core conditions
• Efficient Estimation of Material Property Curves and Surfaces via Active Learning
• Nucleating a Different Coordination in a Crystal under Pressure: A Study of the B1-B2 Transition in NaCl by Metadynamics
• Machine-learning potentials enable predictive $\text{and}$ tractable high-throughput screening of random alloys
• In operando active learning of interatomic interaction during large-scale simulations
• Full-scale ab initio simulations of laser-driven atomistic dynamics
• Twin Neural Network Regression
• Finite-temperature properties of antiferroelectric perovskite $\mathrm{PbZr}{\mathrm{O}}_3$ from deep learning interatomic potential
• Modeling the High-Pressure Solid and Liquid Phases of Tin from Deep Potentials with ab initio Accuracy
• Active Learning Algorithm for Computational Physics
• Machine Learned Interatomic Potentials for Ternary Carbides trained on the AFLOW Database
• Modeling Extensive Defects in Metals through Classical Potential-Guided Sampling and Automated Configuration Reconstruction
• Ring Polymer Molecular Dynamics and Active Learning of Moment Tensor Potential for Gas-Phase Barrierless Reactions: Application to S + H2
• DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
• Towards Large-Scale and Spatio-temporally Resolved Diagnosis of Electronic Density of States by Deep Learning
• Combining stochastic density functional theory with deep potential molecular dynamics to study warm dense matter
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Ab initio Canonical Sampling based on Variational Inference
• Active Learning Approach to Optimization of Experimental Control
• Picosecond-scale Heterogeneous Melting of Metals at Extreme Non-equilibrium States
• Physics-informed active learning for accelerating quantum chemical simulations
• Improved decision making with similarity based machine learning: Applications in chemistry
• Unraveling Antagonistic Collision-Controlled Reactivity in Energetic Molecular Perovskites with Deep Potential Molecular Dynamics
• Thermal conductivity of MgO in giant planetary interior conditions predicted by deep potential
• Thermal disorder and phonon softening in the ferroelectric phase transition of lead titanate
• Facilitating {\it ab initio} configurational sampling of multicomponent solids using an on-lattice neural network model and active learning
• High-Throughput Condensed-Phase Hybrid Density Functional Theory for Large-Scale Finite-Gap Systems: The SeA Approach
• Probing the state of hydrogen in $\delta$-AlOOH at mantle conditions with machine learning potential
• Machine learning potentials for complex aqueous systems made simple
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Size and Quality of Quantum Mechanical Data Sets for Training Neural Network Force Fields for Liquid Water
• Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
• Pre-training, fine-tuning, and distillation (PFD): Automatically generating machine learning force fields from universal models
• Isotope effects in x-ray absorption spectra of liquid water
• Automated atomistic simulations of dissociated dislocations with ab initio accuracy
• Stability and distortion of fcc-LaH${}_{10}$ with path-integral molecular dynamics
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• On the Quality of Uncertainty Estimates from Neural Network Potential Ensembles
• Active-learning-based efficient prediction of ab-initio atomic energy: a case study on a Fe random grain boundary model with millions of atoms
• Efficient dataset generation for machine learning perovskite alloys
• Slowly Quenched, High Pressure Glassy B${}_2$O${}_3$ at DFT Accuracy
• Free energy profiles for chemical reactions in solution from high-dimensional neural network potentials: The case of the Strecker synthesis
• Atomistic simulations of thermodynamic properties of liquid gallium from first principles
• Ab Initio bulk free energy surface of proper ferroelectrics
• Mitigating distribution shift in machine learning-augmented hybrid simulation
• Quantum Active Learning
• Active Learning in Physics: From 101, to Progress, and Perspective
• Active Δ-learning with universal potentials for global structure optimization
• Accurate force field of two-dimensional ferroelectrics from deep learning
• Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles
• The ground state of CuInP${}_2$S${}_6$ thin films: A study of the deep potential method
• Intrinsic structure of relaxor ferroelectrics from first principles