Recommended by

Indexed by

Multi-scale approach for the prediction of atomic scale properties

Andrea Grisafi1, Jigyasa Nigam1,2, Michele Ceriotti1,2*

1 Laboratory of Computational Science and Modeling, IMX, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland.

2 National Centre for Computational Design and Discovery of Novel Materials (MARVEL), École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland

* Corresponding authors emails: michele.ceriotti@epfl.ch
DOI10.24435/materialscloud:tr-t9 [version v1]

Publication date: Jan 07, 2021

How to cite this record

Andrea Grisafi, Jigyasa Nigam, Michele Ceriotti, Multi-scale approach for the prediction of atomic scale properties, Materials Cloud Archive 2021.3 (2021), doi: 10.24435/materialscloud:tr-t9.


Electronic nearsightedness is one of the fundamental principles that governs the behavior of condensed matter and supports its description in terms of local entities such as chemical bonds. Locality also underlies the tremendous success of machine-learning schemes that predict quantum mechanical observables -- such as the cohesive energy, the electron density, or a variety of response properties -- as a sum of atom-centred contributions, based on a short-range representation of atomic environments. One of the main shortcomings of these approaches is their inability to capture physical effects, ranging from electrostatic interactions to quantum delocalization, which have a long-range nature. Here we show how to build a multi-scale scheme that combines in the same framework local and non-local information, overcoming such limitations. We show that the simplest version of such features can be put in formal correspondence with a multipole expansion of permanent electrostatics. The data-driven nature of the model construction, however, makes this simple form suitable to tackle also different types of delocalized and collective effects. We present several examples that range from molecular physics to surface science and biophysics, demonstrating the ability of this multi-scale approach to model interactions driven by electrostatics, polarization and dispersion, as well as the cooperative behavior of dielectric response functions.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.


File name Size Description
179.8 KiB Water - carbon dioxide coordinates and interaction energy.
49.9 MiB Lithium - water coordinates and interaction energy.
35.3 MiB Bio-fragment dimers coordinates with absolute energies and binding energies.
20.7 MiB Lithium - water coordinates and induced polarization vector of water.
46.1 MiB Polypeptides coordinates with energies and scalar (L=0) polarizability components.
3.6 KiB README file.


Files and data are licensed under the terms of the following license: GNU General Public License v2.0 or later.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Journal reference (Paper in which the method is described)
Preprint (Preprint in which the method is described)


multi-scale machine learning long-range interactions LODE EPFL ERC MARVEL CSCS

Version history:

2021.3 (version v1) [This version] Jan 07, 2021 DOI10.24435/materialscloud:tr-t9