Stress and heat flux via automatic differentiation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 95 references that are in the map. First posted on arXiv 2 May 2023.
Builds on
19 of 95 references.
References · 19
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2015Automatic differentiation in machine learning: a surveycited by 846
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
- 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
- 2020Directional Message Passing for Molecular Graphscited by 556
- 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
- 2020Machine Learning Force Fieldscited by 204
- 2019Machine learning for molecular simulationcited by 109
- 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103
- 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 100
7 more
- 2022So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systemscited by 39
- 2022SchNetPack 2.0: A neural network toolbox for atomistic machine learningcited by 29
- 2022Hyperactive Learning (HAL) for Data-Driven Interatomic Potentialscited by 17
- 2020Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learningcited by 11
- 2022Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulationscited by 9
- 2022Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fieldscited by 7
- 2023Heat flux for semi-local machine-learning potentialscited by 3
Built on by
Citing papers per year: 2023: 1.
1 paper.