materialscloud:2023.151
Published October 3, 2023 | Version v1
Dataset Open

Physics-inspired equivariant descriptors of non-bonded interactions

Creators

  • 1. Laboratory of Computational Science and Modelling (COSMO), École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Vaud, Switzerland

* Contact person

Description

One essential ingredient in many machine learning (ML) based methods for atomistic modeling of materials and molecules is the use of locality. While allowing better system-size scaling, this systematically neglects long-range (LR) effects, such as electrostatics or dispersion interaction. We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way, and seamlessly integrates with preexisting methods by building new sets of atom centered features. We provide a direct physical interpretation of these using the multipole expansion, which allows for simpler and more efficient implementations. The framework is applied to simple toy systems as proof of concept, and a heterogeneous set of molecular dimers to push the method to its limits. By generalizing LODE to arbitrary asymptotic behaviors, we provide a coherent approach to treat arbitrary two- and many-body non-bonded interactions in the data-driven modeling of matter.

Files

File preview

All files

Files (84.8 MiB)

Name Size
md5:b647f6bd12901cc32957ec606128b040
1.0 KiB Preview Download
md5:cdf5f3e139bd56a2c31014c8e50e8b93
66.3 MiB Download
md5:47e973400e61374c26fb2cedbf12838d
16.7 KiB Download
md5:3d4b87ec5e1a79b75c41c48a78f78552
4.9 MiB Download
md5:9e76b4a8972a2e829335163fe31c7d7c
6.8 MiB Download
md5:57c54e0ea0b01be89e0a0622f0f2ff96
6.8 MiB Download
md5:9371ed17727e39635fa0c11e27425ace
40.9 KiB Download
md5:4ddc62a1c4d83bf68518010daf5903bd
2.6 KiB Download

References

Journal reference (Paper in which the data is discussed)
K. K. Huguenin-Dumittan, P. Loche, N. Haoran, M. Ceriotti, J. Phys. Chem. Lett. 9612–9618 (2023), doi: 10.1021/acs.jpclett.3c02375

Journal reference (Paper in which some of the datasets were originally introduced)
A, Grisafi, M. Ceriotti, J. Chem. Phys. 151, 204105 (2019), doi: 10.1063/1.5128375

Journal reference (Paper in whih some of the datasets are used)
P. Loche, K. K. Huguenin-Dumittan, M. Honarmand, Q. Xu, E. Rumiantsev, W. B. How, M.F. Langer, M. Cerriotti, J. Chem. Phys. 162, 142501 (2025), doi: 10.1063/5.0251713