Gaussian approximation potentials: A brief tutorial introduction
By A. P. Bart'ok, Gábor Csányi. 2015
556 citations recorded by the source corpus.
© 2015 Wiley Periodicals, Inc. We present a swift walk-through of our recent work that uses machine learning to fit interatomic potentials based on quantum mechanical data. We describe our Gaussian approximation potentials (GAP) framework, discuss a variety of descriptors, how to train the model on total energies and derivatives, and the simultaneous use of multiple models of different complexity. We also show a small example using QUIP, the software sandbox implementation of GAP that is available for noncommercial use.
Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
- Zongrui Pei
- Xianglin Liu
- Jiaxin Zhang
- Alexander V. Shapeev
- Gábor Csányi
- Noam Bernstein
- A. P. Bart'ok
- Matthew J. Hirn
In Materials Chemistry
- Alexander V. Shapeev
- Gábor Csányi
- Chi Chen
- Zongrui Pei
- Shyue Ping Ong
- Yuri Mishin
- Xianglin Liu
- Jiaxin Zhang
In Molecular Biology
- Alexander V. Shapeev
- J. Behler
- Gábor Csányi
- Xianglin Liu
- Zongrui Pei
- Jiaxin Zhang
- Matthew J. Hirn
- Stéphane Mallat
Citations in the corpus
- Wavelet Scattering Regression of Quantum Chemical Energies (2016, methodology): “Integrating over all rotations yields isometric invariant representations, which are used by several quantum energy regression algorithms [6, 5, 4, 46, 16].”
- Machine Learning for High-entropy Alloys: Progress, Challenges and Opportunities (2022, methodology): “SNAP is closely related to GAP in that the central quantity is also the atomic neighbor density in Eq.”
- A Performance and Cost Assessment of Machine Learning Interatomic Potentials. (2019, background): “ed for each elemental system Ni Cu Li Mo Si Ge cuto radius ( A) 3.9 4.1 4.8 5.2 5.1 5.4 energy (eV/atom) 0.01 0.01 0.01 0.01 0.01 0.01 force (eV/ A) 0.05 0.05 0.05 0.05 0.05 0.05 (n max ;lmax ) (8, 8) (8, 8) (8, 8) (8, 8) (8, 8) (8, 8) 14 Spectral neighbor analysis potential The bispectrum of the ”
- Many-Body Coarse-Grained Interactions Using Gaussian Approximation Potentials. (2016, background): “This is already an approximation in all-atom simulations [24], where ongoing research is studying extensions such as polarisable force fields [111, 112] and more general many-body approaches [30, 113].”