Equivariant representations for molecular Hamiltonians


JSON Export

{
  "revision": 7, 
  "metadata": {
    "publication_date": "Dec 09, 2021, 18:32:41", 
    "_oai": {
      "id": "oai:materialscloud.org:1156"
    }, 
    "license": "Creative Commons Attribution 4.0 International", 
    "description": "The application of machine learning to the modeling of materials and molecules has proven to be extremely successful in accelerating the understanding, design, and characterization of materials. A major factor in this success has been the development of representations of atomic structures that reflect physics-based symmetries of the underlying interactions. Most of the descriptions of atomic properties or even global observables rely on decompositions into atomic contributions that are subsequently learnt in an atom-centered framework. However, many quantities associated with quantum mechanical calculations, such as the single-particle Hamiltonian matrices written in an atomic-orbital basis, are associated with multiple atom-centers. \nFollowing the introduction of equivariant N-center structural descriptors, in the reference below, that generalize the very successful atom-centered density correlation features to the problem of learning properties indexed by N atoms, we present benchmarks showing how the construction can be applied to efficiently learn the matrix elements of the (effective) single-particle Hamiltonian in an atom-centered orbital basis. \nIn this record, we include the dataset comprising the Fock and overlap matrices in the def2-SVP of 1000 distorted water molecules, up to 4500 ethanol structures, and a subset of QM7-CHNO molecules. We also provide scripts to generate the two-center representations and fit linear and sparse kernel models for the Hamiltonians.", 
    "contributors": [
      {
        "familyname": "Nigam", 
        "affiliations": [
          "Laboratory of Computational Science and Modeling, IMX, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland", 
          "National Centre for Computational Design and Discovery of Novel Materials (MARVEL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
        ], 
        "email": "jigyasa.nigam@epfl.ch", 
        "givennames": "Jigyasa"
      }, 
      {
        "familyname": "Willatt", 
        "affiliations": [
          "Laboratory of Computational Science and Modeling, IMX, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
        ], 
        "givennames": "Michael J."
      }, 
      {
        "familyname": "Ceriotti", 
        "affiliations": [
          "Laboratory of Computational Science and Modeling, IMX, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland", 
          "National Centre for Computational Design and Discovery of Novel Materials (MARVEL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
        ], 
        "email": "michele.ceriotti@epfl.ch", 
        "givennames": "Michele"
      }
    ], 
    "edited_by": 576, 
    "title": "Equivariant representations for molecular Hamiltonians", 
    "conceptrecid": "1155", 
    "license_addendum": null, 
    "doi": "10.24435/materialscloud:2d-3e", 
    "mcid": "2021.217", 
    "_files": [
      {
        "size": 7998765997, 
        "key": "ncenter-hamiltonian-benchmarks.zip", 
        "checksum": "md5:f3029a4c81963b173b9de4b872686e39", 
        "description": "Folder containing benchmarks for machine learning for datasets of water, ethanol and QM7-CHNO and commented scripts to reproduce the same."
      }, 
      {
        "size": 889, 
        "key": "README.md", 
        "checksum": "md5:f0504fdd55d22b894af8474560270245", 
        "description": "Description of data source and availability of code"
      }
    ], 
    "id": "1156", 
    "keywords": [
      "ERC", 
      "MARVEL", 
      "EPFL", 
      "H2020", 
      "N-center-representations", 
      "machine learning hamiltonians", 
      "equivariant representations", 
      "hamiltonian learning"
    ], 
    "is_last": true, 
    "status": "published", 
    "references": [
      {
        "comment": "Preprint where the data and methods are described", 
        "url": "https://arxiv.org/abs/2109.12083", 
        "type": "Preprint", 
        "citation": "J. Nigam, M.J. Willatt, M. Ceriotti, arXiv:2109.12083"
      }
    ], 
    "version": 1, 
    "owner": 219
  }, 
  "id": "1156", 
  "created": "2021-12-07T15:32:08.816175+00:00", 
  "updated": "2021-12-09T17:32:41.559409+00:00"
}