Journal
JOURNAL OF CHEMICAL PHYSICS
Volume 148, Issue 24, Pages -Publisher
AIP Publishing
DOI: 10.1063/1.5024611
Keywords
-
Funding
- European Research Council under European Union [677013-HBMAP]
- Industrial Research Grant - Constellium
- Fondazione Zegna
- Cluster of Excellence RESOLV - Deutsche Forschungsgemeinschaft [EXC 1069]
- DFG [Be3264/11-2]
Ask authors/readers for more resources
Machine learning of atomic-scale properties is revolutionizing molecular modeling, making it possible to evaluate inter-atomic potentials with first-principles accuracy, at a fraction of the costs. The accuracy, speed, and reliability of machine learning potentials, however, depend strongly on the way atomic configurations are represented, i.e., the choice of descriptors used as input for the machine learning method. The raw Cartesian coordinates are typically transformed in fingerprints, or symmetry functions, that are designed to encode, in addition to the structure, important properties of the potential energy surface like its invariances with respect to rotation, translation, and permutation of like atoms. Here we discuss automatic protocols to select a number of fingerprints out of a large pool of candidates, based on the correlations that are intrinsic to the training data. This procedure can greatly simplify the construction of neural network potentials that strike the best balance between accuracy and computational efficiency and has the potential to accelerate by orders of magnitude the evaluation of Gaussian approximation potentials based on the smooth overlap of atomic positions kernel. We present applications to the construction of neural network potentials for water and for an Al-Mg-Si alloy and to the prediction of the formation energies of small organic molecules using Gaussian process regression. Published by AIP Publishing.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available