Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics

By Linfeng Zhang, Jiequn Han, Han Wang, Roberto Car, E. Weinan. 2017

1,554 citations recorded by the source corpus.

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 neural network trained with ab initio data. The neural network model preserves all the natural symmetries in the problem. It is first-principles based in the sense that there are no ad hoc components aside from the network model. We show that the proposed scheme provides an efficient and accurate protocol in a variety of systems, including bulk materials and molecules. In all these cases, DPMD gives results that are essentially indistinguishable from the original data, at a cost that scales linearly with system size.

Subfields: Atomic and Molecular Physics, and Optics, Materials Chemistry, Radiation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Materials Chemistry

In Radiation

Citations in the corpus

Cormorant: Covariant Molecular Neural Networks (2019, methodology): “To the best of our knowledge, the current state-of-the art algorithms on this dataset are DeepMD [Zhang et al., 2018], DTNN [Schütt et al., 2017], SchNet [Schütt et al., 2017], GDML [Chmiela et al., 2016], and sGDML [Chmiela et al., 2018].”
N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials (2018, positive): “…amount of activity in machine learned atomic potentials (MLAP), and molecular dynamics simulations based on this approach are starting to yield results that outperform other methods (Bart´ok et al., 2010; Behler, 2015; Shapeev, 2015; Chmiela et al., 2016; Zhang et al., 2017; Sch¨utt et al., 2017).”
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (2022, background): “This is analogous to the physical force ﬁelds (Schütt et al., 2017; Zhang et al., 2018; Hu et al., 2021; Shuaibi et al., 2021), which also gradually push particles towards convergence around the equilibrium states.”
Learning Gradient Fields for Molecular Conformation Generation (2021, methodology): “Neural Force Fields Neural networks have also been employed to estimate molecular potential energies and force fields (Schütt et al., 2017; Zhang et al., 2018; Hu et al., 2021).”
A universal graph deep learning interatomic potential for the periodic table (2022, background): “More recently, machine learning of the PES has emerged as a particularly promising approach to IAP development 4–8 .”
The MLIP package: moment tensor potentials with MPI and active learning (2020, background): “Neural network has been the first and are probably the most popular form of regressor for machine-learning potentials [1,4,17,20,60,69,79].”
Integrating Physics-Based Modeling with Machine Learning: A Survey (2020, background): “Inthecontext of molecular dynamics applications, a number of researchers [21, 292] have used a NN per individual atom to calculate each atom’s contribution to the total energy.”
Machine Learning for High-entropy Alloys: Progress, Challenges and Opportunities (2022, background): “Since the neural networks are applied to every atom, NNP is also referred to as high-dimensional NNP (HDNNP) [146].”
EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations (2023, critical): “We find that naively incorporating eSCN convolutions does not result in better performance than the original eSCN model.”
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials (2021, methodology): “Liquid Water and Ice: The data set of liquid waters and ice structures [15, 38] was generated from classical AIMD and path-integral AIMD simulations at different temperatures and pressures, computed with a PBE0-TS functional [15].”
Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games (2019, background): “…(MARL) (see Busoniu et al. (2008) for an earlier review), which recently has gained increasing research attention (see e.g. Foerster et al. (2016); Zhang et al. (2018a)), given the remarkable success of reinforcement learning in many applications, especially accompanied with the powerful function…”