Deep learning inter-atomic potential model for accurate irradiation damage simulations

  title={Deep learning inter-atomic potential model for accurate irradiation damage simulations},
  author={Hao Wang and Xun Guo and Linfeng Zhang and Han Wang and Jianming Xue},
  journal={Applied Physics Letters},
We propose a hybrid scheme that interpolates smoothly the Ziegler-Biersack-Littmark (ZBL) screened nuclear repulsion potential with a newly developed deep learning potential energy model. The resulting DP-ZBL model can not only provide overall good performance on the predictions of near-equilibrium material properties but also capture the right physics when atoms are extremely close to each other, an event that frequently happens in computational simulations of irradiation damage events. We… 

Figures and Tables from this paper

Deep-learning interatomic potential for irradiation damage simulations in MoS2 with ab initial accuracy
Potentials that could accurately describe the irradiation damage processes are highly desired to figure out the atomic-level response of various newly-discovered materials under irradiation
A Tungsten Deep Neural-Network Potential for Simulating Mechanical Property Degradation Under Fusion Service Environment
Tungsten is a promising candidate material in fusion energy facilities. Molecular dynamics (MD) simulations reveal the atomistic scale mechanisms, so they are crucial for the understanding of the
A Tungsten Deep Potential with High Accuracy and Generalization Ability based on a Newly Designed Three-body Embedding Formalism
Tungsten is a promising candidate material in fusion energy facilities. Molecular dynamics (MD) simulations reveal the atomistic scale mechanisms, so they are crucial for the understanding of the
Machine-learning interatomic potential for radiation damage and defects in tungsten
We introduce a machine-learning interatomic potential for tungsten using the Gaussian Approximation Potential framework. We specifically focus on properties relevant for simulations of
Pushing the Limit of Molecular Dynamics with Ab Initio Accuracy to 100 Million Atoms with Machine Learning
  • Weile Jia, Han Wang, Linfeng Zhang
  • Computer Science
    SC20: International Conference for High Performance Computing, Networking, Storage and Analysis
  • 2020
A machine learningbased simulation protocol (Deep Potential Molecular Dynamics), while retaining ab initio accuracy, can simulate more than 1 nanosecond-long trajectory of over 100 million atoms per day, using a highly optimized code (GPU DeePMD-kit) on the Summit supercomputer.
Deep Learning Inter-atomic Potential for Thermal and Phonon Behaviour of Silicon Carbide with Quantum Accuracy
Silicon carbide (SiC) is an essential material for next generation semiconductors and components for nuclear plants. It’s applications are strongly dependent on its thermal conductivity, which is
Deep Neural Network for Accurate and Efficient Atomistic Modeling of Phase Change Memory
This letter presents a general-purpose fully-atomistic method to simulate phase change memory (PCM), by combining density functional theory (DFT) and deep neural network (DNN) and its efficiency and accuracy may be useful to develop next-generation atomistic modeling tools to enable in-depth optimization of PCM.
nap: A molecular dynamics package with parameter-optimization programs for classical and machine-learning potentials
The nap is a package for molecular dynamics (MD) simulation consisting of an MD program (pmd) that can perform large-scale simulation using a spatial-decomposition technique and two


Improving atomic displacement and replacement calculations with physically realistic damage models
Two new complementary displacement production estimators and atomic mixing functions are proposed that extend the NRT-dpa by providing more physically realistic descriptions of primary defect creation in materials and may become additional standard measures for radiation damage quantification.
Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
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.
Reinforced dynamics for enhanced sampling in large atomic and molecular systems. I. Basic Methodology
A new approach for efficiently exploring the configuration space and computing the free energy of large atomic and molecular systems is proposed, motivated by an analogy with reinforcement learning, which allows for an efficient exploration of the configurationspace by adding an adaptively computed biasing potential to the original dynamics.
Learning scheme to predict atomic forces and accelerate materials simulations
It is argued that pathways are available to systematically and continuously improve the predictive capability of such a learned force field in an adaptive manner, and that this concept can be generalized to include multiple elements.
Machine Learning Force Fields: Construction, Validation, and Outlook
The multistep workflow required for force fields construction is discussed, which begins with generating diverse reference atomic environments and force data, choosing a numerical representation for the atomic environments, selecting a representative training set, and lastly the learning method itself, for the case of Al.
Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
We introduce a scheme for molecular simulations, the deep potential molecular dynamics (DPMD) method, based on a many-body potential and interatomic forces generated by a carefully crafted deep
Coherent displacement of atoms during ion irradiation
Ion irradiation is a common technique of materials processing, as well as being relevant to the radiation damage incurred in nuclear reactors. Early models of the effects of ion irradiation typically
Adaptive coupling of a deep neural network potential to a classical force field.
This work makes the DeePMD region embedded in the AMM simulated system as if it were embedded in a system that is fully described by the accurate potential, by using a force interpolation scheme and imposing a thermodynamics force in the transition region.
Deep Potential: a general representation of a many-body potential energy surface
Deep Potential is able to reproduce the original model, whether empirical or quantum mechanics based, within chemical accuracy, and the computational cost of this new model is not substantially larger than that of empirical force fields.