Thermal conductivity predictions with foundation atomistic models

JSON Export

{
  "updated": "2024-10-22T15:03:10.678933+00:00", 
  "id": "2420", 
  "metadata": {
    "publication_date": "Oct 22, 2024, 17:03:10", 
    "edited_by": 98, 
    "doi": "10.24435/materialscloud:2d-4b", 
    "references": [
      {
        "type": "Preprint", 
        "url": "https://arxiv.org/abs/2408.00755", 
        "citation": "B. P\u00f3ta, P. Ahlawat, G. Cs\u00e1nyi, M. Simoncelli,  arXiv preprint, arXiv:2408.00755 (2024)", 
        "doi": "10.48550/arXiv.2408.00755", 
        "comment": "Supporting dataset for \"Thermal Conductivity Predictions with Foundation Atomistic Models\""
      }
    ], 
    "description": "Advances in machine learning have led to the development of foundation models for atomistic materials chemistry, enabling quantum-accurate descriptions of interatomic forces across diverse compounds at reduced computational cost. Hitherto, these models have been benchmarked relying on descriptors based on atoms' interaction energies or harmonic vibrations; their accuracy and efficiency in predicting observable and technologically relevant heat-conduction properties remains unknown. Here, we introduce a framework that leverages foundation models and the Wigner formulation of heat transport to overcome the major bottlenecks of current methods for designing heat-management materials: high cost, limited transferability, or lack of physics awareness. We present the standards needed to achieve first-principles accuracy in conductivity predictions through model's fine-tuning, discussing benchmark metrics and precision/cost trade-offs. We apply our framework to a database of solids with diverse compositions and structures, demonstrating its potential to discover materials for next-gen technologies ranging from thermal insulation to neuromorphic computing.", 
    "contributors": [
      {
        "email": "bp443@cam.ac.uk", 
        "affiliations": [
          "Theory of Condensed Matter Group of the Cavendish Laboratory, University of Cambridge, Cambridge, UK"
        ], 
        "givennames": "Bal\u00e1zs", 
        "familyname": "P\u00f3ta"
      }, 
      {
        "affiliations": [
          "Theory of Condensed Matter Group of the Cavendish Laboratory, University of Cambridge, Cambridge, UK"
        ], 
        "givennames": "Paramvir", 
        "familyname": "Ahlawat"
      }, 
      {
        "affiliations": [
          "Engineering Laboratory, University of Cambridge, Cambridge, UK"
        ], 
        "givennames": "G\u00e1bor", 
        "familyname": "Cs\u00e1nyi"
      }, 
      {
        "email": "ms2855@cam.ac.uk", 
        "affiliations": [
          "Theory of Condensed Matter Group of the Cavendish Laboratory, University of Cambridge, Cambridge, UK"
        ], 
        "givennames": "Michele", 
        "familyname": "Simoncelli"
      }
    ], 
    "is_last": true, 
    "license_addendum": null, 
    "_files": [
      {
        "description": "Dataset containing reference DFT thermal conductivity results, as well as scripts and data used for fine-tuning.", 
        "checksum": "md5:b55af517e53a86693990ab00f783d3e4", 
        "size": 377288770, 
        "key": "data.zip"
      }
    ], 
    "version": 1, 
    "id": "2420", 
    "conceptrecid": "2419", 
    "owner": 1541, 
    "license": "Academic Software Licence (\"ASL\")", 
    "mcid": "2024.171", 
    "_oai": {
      "id": "oai:materialscloud.org:2420"
    }, 
    "status": "published", 
    "title": "Thermal conductivity predictions with foundation atomistic models", 
    "keywords": [
      "thermal conductivity", 
      "foundation machine learning potential", 
      "wigner transport equation", 
      "interatomic potential fine-tuning", 
      "matbench-discovery"
    ]
  }, 
  "revision": 12, 
  "created": "2024-10-21T10:56:18.823348+00:00"
}