Deep Potential: A General Representation of a Many-Body Potential Energy Surface
From MaRDI portal
Publication:5159341
Abstract: We present a simple, yet general, end-to-end deep neural network representation of the potential energy surface for atomic and molecular systems. This methodology, which we call Deep Potential, is "first-principle" based, in the sense that no ad hoc approximations or empirical fitting functions are required. The neural network structure naturally respects the underlying symmetries of the systems. When tested on a wide variety of examples, Deep Potential is able to reproduce the original model, whether empirical or quantum mechanics based, within chemical accuracy. The computational cost of this new model is not substantially larger than that of empirical force fields. In addition, the method has promising scalability properties. This brings us one step closer to being able to carry out molecular simulations with accuracy comparable to that of quantum mechanics models and computational cost comparable to that of empirical potentials.
Recommendations
- The role of depth and flatness of a potential energy surface in chemical reaction dynamics
- Potential energy surface exploration with equilibrial paths. I: Theory
- Potential energy surface exploration with equilibrial paths. II: Application
- Exploring the potential energy landscape over a large parameter-space
- The many-body problem with an energy-dependent confining potential
- scientific article; zbMATH DE number 2010155
- Born-Oppenheimer potential energy surfaces for Kohn-Sham models in the local density approximation
- scientific article; zbMATH DE number 17115
Cites work
Cited in
(32)- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- Machine learning materials physics: integrable deep neural networks enable scale bridging by learning free energy functions
- Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
- Unified regression model in fitting potential energy surfaces for quantum dynamics
- Using neural networks to accelerate the solution of the Boltzmann equation
- Deep Density: circumventing the Kohn-Sham equations via symmetry preserving neural networks
- Solving many-electron Schrödinger equation using deep neural networks
- Proper orthogonal descriptors for efficient and accurate interatomic potentials
- Solving traveltime tomography with deep learning
- Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks
- Physics-constrained, data-driven discovery of coarse-grained dynamics
- Better approximations of high dimensional smooth functions by deep neural networks with rectified power units
- Machine learning and computational mathematics
- Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
- Multi-scale deep neural network (MscaleDNN) for solving Poisson-Boltzmann equation in complex domains
- Neural networks-based variationally enhanced sampling
- SwitchNet: a neural Network Model for forward and inverse scattering problems
- Molecular modeling by machine learning
- FLAME: a library of atomistic modeling environments
- A general code for fitting global potential energy surfaces via CHIPR method: direct-fit diatomic and tetratomic molecules
- DP-GEN: a concurrent learning platform for the generation of reliable deep learning based potential energy models
- A Framework for a Generalization Analysis of Machine-Learned Interatomic Potentials
- Deep Learning Unravels a Dynamic Hierarchy While Empowering Molecular Dynamics Simulations
- A mathematical perspective of machine learning
- Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs
- An equivariant neural operator for developing nonlocal tensorial constitutive models
- Solving inverse problems with deep learning
- Proper orthogonal descriptors for multi-element chemical systems
- Overview frequency principle/spectral bias in deep learning
- On understanding and overcoming spectral biases of deep neural network learning methods for solving PDEs
- The neural networks with tensor weights and emergent fermionic Wick rules in the large-width limit
- Deep learning for the semi-classical limit of the Schrödinger equation
This page was built for publication: Deep Potential: A General Representation of a Many-Body Potential Energy Surface
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5159341)
