Accurate and scalable multi-element graph neural network force field and molecular dynamics with direct force architecture


JSON Export

{
  "id": "803", 
  "metadata": {
    "title": "Accurate and scalable multi-element graph neural network force field and molecular dynamics with direct force architecture", 
    "doi": "10.24435/materialscloud:66-ec", 
    "license": "Creative Commons Attribution Share Alike 4.0 International", 
    "keywords": [
      "machine learning", 
      "molecular dynamics", 
      "density-functional theory"
    ], 
    "contributors": [
      {
        "affiliations": [
          "Robert Bosch Research and Technology Center, Cambridge, MA 02139, USA", 
          "Northwestern University, Evanston, IL 60208, USA"
        ], 
        "familyname": "Park", 
        "email": "cheolpark2016@u.northwestern.edu", 
        "givennames": "Cheol Woo"
      }, 
      {
        "affiliations": [
          "Robert Bosch Research and Technology Center, Cambridge, MA 02139, USA"
        ], 
        "familyname": "Kornbluth", 
        "givennames": "Mordechai"
      }, 
      {
        "affiliations": [
          "Harvard School of Engineering and Applied Sciences, Cambridge, MA 02138, USA"
        ], 
        "familyname": "Vandermause", 
        "givennames": "Jonathan"
      }, 
      {
        "affiliations": [
          "Northwestern University, Evanston, IL 60208, USA"
        ], 
        "familyname": "Wolverton", 
        "givennames": "Chris"
      }, 
      {
        "affiliations": [
          "Harvard School of Engineering and Applied Sciences, Cambridge, MA 02138, USA"
        ], 
        "familyname": "Kozinsky", 
        "email": "bkoz@seas.harvard.edu", 
        "givennames": "Boris"
      }, 
      {
        "affiliations": [
          "Robert Bosch Research and Technology Center, Cambridge, MA 02139, USA"
        ], 
        "familyname": "Mailoa", 
        "email": "jpmailoa@alum.mit.edu", 
        "givennames": "Jonathan"
      }
    ], 
    "_files": [
      {
        "description": "train.pkl and test.pkl: pickled python dictionaries containing the training and testing snapshots taken from the MD trajectory of Li7P3S11. For more detailed description of how to access the data, please refer to the README.txt file that is included.", 
        "checksum": "md5:647246855ec2212a1c1623f617e0545b", 
        "size": 68689801, 
        "key": "Li7P3S11.zip"
      }
    ], 
    "references": [
      {
        "type": "Journal reference", 
        "citation": "C. W. Park, M. Kornbluth, J. Vandermause, C. Wolverton, B. Kozinsky, J. Mailoa (in preparation)"
      }
    ], 
    "conceptrecid": "802", 
    "version": 1, 
    "edited_by": 100, 
    "id": "803", 
    "owner": 360, 
    "mcid": "2021.54", 
    "is_last": true, 
    "status": "published", 
    "description": "Data includes the the ab initio molecular dynamic simulation of Li7P3S11 that was used to measure the performance of the GNNFF. The data is divided into training and testing sets.\n\nBrief descirption of the work: Recently, machine learning (ML) has been used to address the computational cost that has been limiting ab initio molecular dynamics (AIMD). Here, we present GNNFF, a graph neural network framework to directly predict atomic forces from automatically extracted features of the local atomic environment that are translationally-invariant, but rotationally-covariant to the coordinate of the atoms. We demonstrate that GNNFF not only achieves high performance in terms of force prediction accuracy and computational speed on various materials systems, but also accurately predicts the forces of a large MD system after being trained on forces obtained from a smaller system. Finally, we use our framework to perform an MD simulation of Li7P3S11, a superionic conductor, and show that resulting Li diffusion coefficient is within 14% of that obtained directly from AIMD. The high performance exhibited by GNNFF can be easily generalized to study atomistic level dynamics of other material systems.", 
    "license_addendum": "", 
    "_oai": {
      "id": "oai:materialscloud.org:803"
    }, 
    "publication_date": "Apr 06, 2021, 18:56:42"
  }, 
  "revision": 4, 
  "updated": "2021-04-06T16:56:42.712954+00:00", 
  "created": "2021-03-31T22:13:24.565405+00:00"
}