A coarse-grained deep neural network model for liquid water

@article{Patra2019ACD,
  title={A coarse-grained deep neural network model for liquid water},
  author={Tarak K. Patra and Troy David Loeffler and Henry Chan and Mathew J. Cherukara and Badri Narayanan and Subramanian K.R.S. Sankaranarayanan},
  journal={Applied Physics Letters},
  year={2019}
}
We introduce a coarse-grained deep neural network model (CG-DNN) for liquid water that utilizes 50 rotational and translational invariant coordinates, and is trained exclusively against energies of ~30,000 bulk water configurations. Our CG-DNN potential accurately predicts both the energies and molecular forces of water; within 0.9 meV/molecule and 54 meV/angstrom of a reference (coarse-grained bond-order potential) model. The CG-DNN water model also provides good prediction of several… 

Figures and Tables from this paper

Active learning a coarse-grained neural network model for bulk water from sparse training data
TLDR
This work demonstrates that with ∼300 reference data, the AL-NN water model is able to accurately predict both the energies and the molecular forces of water, within 2 meV per molecule and 40 meV A−1 of the reference model.
Machine learning for reparameterization of four-site water models: TIP4P-BG and TIP4P-BGT.
TLDR
The potential of the proposed data-driven machine learning procedure has been demonstrated for parameterizing a MD-based material model that exhibits excellent performance with a reasonable balance among the four crucial physical properties of water.
BLAST: Bridging Length/time scales via Atomistic Simulation Toolkit
TLDR
Several important aspects in force field development are discussed and features in BLAST (Bridging Length/time scales via Atomistic Simulation Toolkit) that enable its functionalities and ease of use are highlighted.
Taking materials dynamics to new extremes using machine learning interatomic potentials
Understanding materials dynamics under extreme conditions of pressure, temperature, and strain rate is a scientific quest that spans nearly a century. Atomic simulations have had a considerable
Monte Carlo Simulations of Au38(SCH3)24 Nanocluster Using Distance-Based Machine Learning Methods.
We present an implementation of distance-based machine learning (ML) methods to create a realistic atomistic interaction potential to be used in Monte Carlo simulations of thermal dynamics of
Active Learning the Potential Energy Landscape for Water Clusters from Sparse Training Data
Molecular dynamics with predefined functional forms is a popular technique for understanding dynamical evolution of systems. The predefined functional forms impose limits on the physics that can be...
Computational Modeling of Battery Materials
  • B. Narayanan
  • Engineering
    Reference Module in Earth Systems and Environmental Sciences
  • 2021
Deep Learning Order Parameter for Polymer Phase Transition
TLDR
A deep autoencoder that autonomously discovers an appropriate order parameter from molecular dynamics simulation data to characterize the coil to globule phase transition of a polymer is reported.
...
1
2
...

References

SHOWING 1-10 OF 27 REFERENCES
Machine learning coarse grained models for water
TLDR
A machine-learned coarse-grained water model to elucidate the ice nucleation process much more efficiently than previous models is developed, in a significant departure from conventional force-field fitting.
DeePCG: Constructing coarse-grained models via deep neural networks.
TLDR
It is found that the two-body, three- body, and higher-order oxygen correlation functions produced by the coarse-grained and full atomistic models agree very well with each other, illustrating the effectiveness of the DeePCG model on a rather challenging task.
A density-functional theory-based neural network potential for water clusters including van der Waals corrections.
TLDR
This work presents a high-dimensional neural network (NN) potential for water clusters based on density-functional theory (DFT) calculations, which is constructed using clusters containing up to 10 monomers and is in principle able to meet all these requirements.
Physically informed artificial neural networks for atomistic modeling of materials
TLDR
An approach to improve the transferability of machine-learning potentials by including information on the physical nature of interatomic bonding, called the physically informed neural network (PINN) potential.
Construction of high-dimensional neural network potentials using environment-dependent atom pairs.
TLDR
This work presents an implementation of an NN method based on atom pairs, and its accuracy and performance are compared to the atom-based NN approach, with the pair-based method yielding a slightly higher accuracy making it a competitive alternative for addressing complex systems in MD simulations.
Generalized neural-network representation of high-dimensional potential-energy surfaces.
TLDR
A new kind of neural-network representation of DFT potential-energy surfaces is introduced, which provides the energy and forces as a function of all atomic positions in systems of arbitrary size and is several orders of magnitude faster than DFT.
Atom-centered symmetry functions for constructing high-dimensional neural network potentials.
  • J. Behler
  • Computer Science
    The Journal of chemical physics
  • 2011
TLDR
Neural networks offer an unbiased and numerically very accurate approach to represent high-dimensional ab initio potential-energy surfaces and a transformation to symmetry functions is required to enable molecular dynamics simulations of large systems.
Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data.
TLDR
A novel method is proposed for transferring physical insights from physical equations onto more generic descriptors, allowing us to screen billions of unknown compositions for Li-ion conductivity, a scale which was previously unfeasible.
...
1
2
3
...