High accuracy and transferability of a neural network potential through charge equilibration for calcium fluoride

Faraji, Somayeh; Ghasemi, S. Alireza; Rostami, Samare; Rasoulkhani, Robabe; Schaefer, Bastian; Goedecker, Stefan; Amsler, Maximilian

doi:10.1103/physrevb.95.104105

Cited by 94 publications

(81 citation statements)

References 85 publications

(73 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, prominent advances in machine learning techniques have led to the development of computationally very efficient, yet accurate potential energy surfaces [22][23][24][25][26] , where various different techniques have been introduced over the years [27][28][29][30][31][32][33][34][35][36][37][38][39][40][41] . These methods do not utilize physically motivated functional forms, but rather use highly flexible general functions being able to represent in principle arbitrary functional relations.…”

Section: Introductionmentioning

confidence: 99%

Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground

Schran

Behler

Marx

2019

J. Chem. Theory Comput.

122

137

View full text Add to dashboard Cite

Highly accurate potential energy surfaces are of key interest for the detailed understanding and predictive modeling of chemical systems. In recent years, several new types of force fields, which are based on machine learning algorithms and fitted to ab initio reference calculations, have been introduced to meet this requirement. Here we show how high-dimensional neural network potentials can be employed to automatically generate the potential energy surface of finite sized clusters at coupled cluster accuracy, namely CCSD(T*)-F12a/aug-cc-pVTZ. The developed automated procedure utilizes the established intrinsic properties of the model such that the configurations for the training set are selected in an unbiased and efficient way to minimize the computational effort of expensive reference calculations. These ideas are applied to protonated water clusters from the hydronium cation, H 3 O + , up to the tetramer, H 9 O + 4 , and lead to a common potential energy surface that describes all these systems at essentially converged coupled cluster accuracy with a fitting error of 0.06 kJ/mol per atom. The fit is validated in detail and separately for all clusters up to the tetramer and yields reliable results not only for stationary points, but also for reaction pathways, intermediate configurations, as well as different sampling techniques. Per design the NNPs constructed in this fashion can handle very different conditions including the quantum nature of the nuclei and enhanced sampling techniques covering very low as well as high temperatures. This enables fast and exhaustive exploration of the targeted protonated water clusters at essentially converged interactions. In addition, the automated process will allow one to tackle finite systems much beyond the present case.

show abstract

Section: Introductionmentioning

confidence: 99%

Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground

Schran

Behler

Marx

2019

J. Chem. Theory Comput.

122

137

View full text Add to dashboard Cite

show abstract

“…[5][6][7][8][9][12][13][14][15][16]23 Accuracy and transferability are not the only advantages of ML force fields. Their most appealing aspect is that they can be created and improved in a highly automatic manner with minimal human intervention within one unified framework.…”

Section: Discussionmentioning

confidence: 99%

A universal strategy for the creation of machine learning-based atomistic force fields

et al. 2017

View full text Add to dashboard Cite

Emerging machine learning (ML)-based approaches provide powerful and novel tools to study a variety of physical and chemical problems. In this contribution, we outline a universal strategy to create ML-based atomistic force fields, which can be used to perform high-fidelity molecular dynamics simulations. This scheme involves (1) preparing a big reference dataset of atomic environments and forces with sufficiently low noise, e.g., using density functional theory or higher-level methods, (2) utilizing a generalizable class of structural fingerprints for representing atomic environments, (3) optimally selecting diverse and non-redundant training datasets from the reference data, and (4) proposing various learning approaches to predict atomic forces directly (and rapidly) from atomic configurations. From the atomistic forces, accurate potential energies can then be obtained by appropriate integration along a reaction coordinate or along a molecular dynamics trajectory. Based on this strategy, we have created model ML force fields for six elemental bulk solids, including Al, Cu, Ti, W, Si, and C, and show that all of them can reach chemical accuracy. The proposed procedure is general and universal, in that it can potentially be used to generate ML force fields for any material using the same unified workflow with little human intervention. Moreover, the force fields can be systematically improved by adding new training data progressively to represent atomic environments not encountered previously.

show abstract

“…Behler and co-workers showed how the electrostatic energy in solids can be described by environment-dependent charges that are fitted through a separate NN, later summing up the short-and long-range terms, [169,171] similar in spirit to how an Ewald summation is done. More recently, Goedecker and co-workers proposed an environment-dependent charge equilibration scheme for ionic systems, initially introduced for NaCl clusters in the gas phase, [170] constructing a simple force field just from electrostatic terms. More recently, Goedecker and co-workers proposed an environment-dependent charge equilibration scheme for ionic systems, initially introduced for NaCl clusters in the gas phase, [170] constructing a simple force field just from electrostatic terms.…”

Section: Challenges and Future Directionsmentioning

confidence: 99%

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

2019

View full text Add to dashboard Cite

In pursuit of this goal, atomic-scale computer simulations have long been a central approach, and two major families of methods are routinely used today. On the one hand, there are quantum-mechanical simulations, in which we solve Schrödinger's equation for the electronic structure of molecular and periodic systems, most widely based on density-functional theory (DFT). [6][7][8] These methods provide (largely) reliable results for structural models of materials that normally contain a few tens or hundreds of atoms. State-of-the-art DFT methods can be applied to many material classes, and they are increasingly used for high-throughput screening and "in silico" (computer-based) design of materials: new compositions and previously unknown structures have been identified in DFT searches and subsequently experimentally realized. [5,[9][10][11] On the other hand, interatomic potential models ("force fields"), parameterizing interactions between atoms with (relatively) simple functional forms, are widely used in materials science to describe matter in molecular dynamics (MD) simulations. These simulations grant access to larger time and length scales, reaching system sizes of up to hundreds of thousands of atoms. [12] In parameterizing these potentials, a certain physical form of the atomic interactions is assumed, often in terms of bond distances, angles, and so on, and physical properties such as equilibrium lattice parameters or elastic constants enter the fitting of the potential. For this reason, such potentials are often called "empirical." They are several orders of magnitude faster than DFT, but necessarily less accurate and less easily transferable.In this Progress Report, we highlight recent developments in "machine-learned" interatomic potentials, which represent a rapidly growing field that promises to do away with the aforementioned trade-offs. Over the last year, there has been a surge of interest in machine learning (ML) methodology: part of it is due to the dramatic growth of ML throughout the scientific disciplines, and part of it is due to tangible success stories of ML-based interatomic potentials that are now beginning to emerge. We will argue that this is an exciting development with very practical implications, currently on the verge of moving from a somewhat specialized new technology to everyday applicability, poised to enhance and complement the communities' existing strengths in computational materials modeling. We will show selected applications of ML potentials to problems in materials science, discuss the current limitations (and possible pitfalls), and outline what we expect to be interesting directions for the development of the field in the coming years.Atomic-scale modeling and understanding of materials have made remarkable progress, but they are still fundamentally limited by the large computational cost of explicit electronic-structure methods such as density-functional theory. This Progress Report shows how machine learning (ML) is currently enabling a new degree of realism in materi...

show abstract

High accuracy and transferability of a neural network potential through charge equilibration for calcium fluoride

Cited by 94 publications

References 85 publications

Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground

Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground

A universal strategy for the creation of machine learning-based atomistic force fields

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

Contact Info

Product

Resources

About