A general-purpose machine-learning force field for bulk and nanostructured phosphorus

Deringer, Volker L.; Miguel, A.; Csänyi, Gábor

doi:10.1038/s41467-020-19168-z

Cited by 108 publications

(132 citation statements)

References 97 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…The structural map, visualizing the (dis-) similarity between different configurations, illustrates the connection between random structure search (gray), exploration with the potential using MD (orange), and manual database building (blue, green). Adapted from ref ( 163 ). Original figure published under the CC BY 4.0 license ( ).…”

Section: Gaussian Approximation Potential (Gap) Frameworkmentioning

confidence: 99%

Gaussian Process Regression for Materials and Molecules

et al. 2021

Self Cite

View full text Add to dashboard Cite

We provide an introduction to Gaussian process regression (GPR) machine-learning methods in computational materials science and chemistry. The focus of the present review is on the regression of atomistic properties: in particular, on the construction of interatomic potentials, or force fields, in the Gaussian Approximation Potential (GAP) framework; beyond this, we also discuss the fitting of arbitrary scalar, vectorial, and tensorial quantities. Methodological aspects of reference data generation, representation, and regression, as well as the question of how a data-driven model may be validated, are reviewed and critically discussed. A survey of applications to a variety of research questions in chemistry and materials science illustrates the rapid growth in the field. A vision is outlined for the development of the methodology in the years to come.

show abstract

Section: Gaussian Approximation Potential (Gap) Frameworkmentioning

confidence: 99%

Gaussian Process Regression for Materials and Molecules

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…[96][97][98][99] Interest in the use of phosphorus in battery electrodes and other advanced materials is also growing. [100][101][102][103][104][105] Overall, we believe P Kβ XES could find broad use and impact in fields relevant to chemical energy conversion.…”

Section: Discussionmentioning

confidence: 99%

Phosphorus Kβ X-ray emission spectroscopy detects non-covalent interactions of phosphate biomolecules in situ

et al. 2021

View full text Add to dashboard Cite

show abstract

“…1, where we use a new method to embed high-dimensional data in two dimensions, based on a hierarchical combination of cluster-based data classification and multidimensional scaling [34,35]. This is a popular tool for visualizing structural databases in the context of ML applied to the study of atomic systems [36][37][38][39].…”

Section: A C60 Gap Force Fieldmentioning

confidence: 99%

Machine learning force fields based on local parametrization of dispersion interactions: Application to the phase diagram of C60

et al. 2021

Self Cite

View full text Add to dashboard Cite

We present a comprehensive methodology to enable addition of van der Waals (vdW) corrections to machine learning (ML) atomistic force fields. Using a Gaussian approximation potential (GAP) [Bartók et al.., Phys. Rev. Lett. 104, 136403 (2010)] as baseline, we accurately machine learn a local model of atomic polarizabilities based on Hirshfeld volume partitioning of the charge density [Tkatchenko and Scheffler, Phys. Rev. Lett. 102, 073005 ( 2009)]. These environment-dependent polarizabilities are then used to parametrize a screened Londondispersion approximation to the vdW interactions. Our ML vdW model only needs to learn the charge density partitioning implicitly, by learning the reference Hirshfeld volumes from density functional theory (DFT). In practice, we can predict accurate Hirshfeld volumes from the knowledge of the local atomic environment (atomic positions) alone, making the model highly computationally efficient. For additional efficiency, our ML model of atomic polarizabilities reuses the same many-body atomic descriptors used for the underlying GAP learning of bonded interatomic interactions. We also show how the method enables straightforward computation of gradients of the observables, even when these remain challenging for the reference method (e.g., calculating gradients of the Hirshfeld volumes in DFT). Finally, we demonstrate the approach by studying the phase diagram of C 60 , where vdW effects are important. The need for a highly accurate vdW-inclusive reactive force field is highlighted by modeling the decomposition of the C 60 molecules taking place at high pressures and temperatures.

show abstract

A general-purpose machine-learning force field for bulk and nanostructured phosphorus

Cited by 108 publications

References 97 publications

Gaussian Process Regression for Materials and Molecules

Gaussian Process Regression for Materials and Molecules

Phosphorus Kβ X-ray emission spectroscopy detects non-covalent interactions of phosphate biomolecules in situ

Machine learning force fields based on local parametrization of dispersion interactions: Application to the phase diagram of C60

Contact Info

Product

Resources

About