Stress and heat flux via automatic differentiation

Abstract

Machine-learning potentials provide computationally efficient and accurate approximations of the Born-Oppenheimer potential energy surface. This potential determines many materials properties and simulation techniques usually require its gradients, in particular forces and stress for molecular dynamics, and heat flux for thermal transport properties. Recently developed potentials feature high body order and can include equivariant semi-local interactions through message-passing mechanisms. Due to their complex functional forms, they rely on automatic differentiation (AD), overcoming the need for manual implementations or finite-difference schemes to evaluate gradients. This study demonstrates a unified AD approach to obtain forces, stress, and heat flux for such potentials, and provides a model-independent implementation. The method is tested on the Lennard-Jones potential, and then applied to predict cohesive properties and thermal conductivity of tin selenide using an equivariant message-passing neural network potential.

9 pages, 2 figures, 6 tables, excluding supplement (3 pages, 3 figures, 2 tables). Additional information at https://marcel.science/glp

References in corpus (14)

• Restoring the density-gradient expansion for exchange in solids and surfaces
• Generalized gradient approximation for solids and their surfaces
• Machine learning for molecular simulation
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
• The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Anharmonicity in Thermal Insulators: An Analysis from First Principles
• Multilayer atomic cluster expansion for semi-local interactions
• Ab initio Green-Kubo simulations of heat transport in solids: Method and implementation
• Heat flux for semi-local machine-learning potentials
• Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations
• So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systems
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields

Cited by in corpus (5)

• Molecular dynamics simulations of heat transport using machine-learned potentials: A mini review and tutorial on GPUMD with neuroevolution potentials
• Thermal conductivity of Li${}_3$PS${}_4$ solid electrolytes with ab initio accuracy
• Guest Editorial: Special Topic on Software for Atomistic Machine Learning
• Algorithmic differentiation for plane-wave DFT: materials design, error control and learning model parameters
• Accelerated Machine Learning Force Field for Predicting Thermal Conductivity of Organic Liquids