Adsorbate chemical environment-based machine learning framework for heterogeneous catalysis


JSON Export

{
  "metadata": {
    "is_last": true, 
    "publication_date": "Apr 11, 2022, 14:37:43", 
    "edited_by": 576, 
    "version": 1, 
    "license": "MIT License", 
    "license_addendum": null, 
    "_files": [
      {
        "checksum": "md5:0569796192ae7ce5b25e5617981bb657", 
        "key": "README.txt", 
        "size": 5773, 
        "description": "File containing description of the data included in the folders and how to access it."
      }, 
      {
        "checksum": "md5:fd61315613bb3e72b44d41319b4736b5", 
        "key": "Fig3.tar.bz2", 
        "size": 86438, 
        "description": "Raw data to recreate analysis of Fig 3"
      }, 
      {
        "checksum": "md5:8881a96a1113653b66b7affd3e32f58f", 
        "key": "Fig4.tar.bz2", 
        "size": 28894, 
        "description": "Raw data to recreate analysis of Fig 4"
      }, 
      {
        "checksum": "md5:4bd13dcf4c7e02e336faed6ac6d05121", 
        "key": "Fig5.py", 
        "size": 2050, 
        "description": "File to generate Fig 5"
      }, 
      {
        "checksum": "md5:18dcdabaef7de72c755db5fbe7c6b206", 
        "key": "processing_scripts.tar.bz2", 
        "size": 11794, 
        "description": "processing script to generate graph objects"
      }, 
      {
        "checksum": "md5:a66bebea30fdd1a2cfdc6cc120456deb", 
        "key": "Pt_OH.tar.bz2", 
        "size": 1512637516, 
        "description": "Raw files (graph objects and atom trajectories) for Pt-OH analysis"
      }, 
      {
        "checksum": "md5:26a89f4493cee403afaa77ba1cbc8eca", 
        "key": "Pt3Sn_NO.tar.bz2", 
        "size": 397019529, 
        "description": "Raw files (graph objects and atom trajectories) for Pt3Sn-NO analysis"
      }
    ], 
    "mcid": "2022.50", 
    "keywords": [
      "density-functional theory", 
      "machine learning", 
      "electronic structure"
    ], 
    "contributors": [
      {
        "givennames": "Pushkar", 
        "email": "pghaneka@purdue.edu", 
        "familyname": "Ghanekar", 
        "affiliations": [
          "Davidson School of Chemical Engineering, Purdue University, West Lafayette, Indiana 47907, USA"
        ]
      }, 
      {
        "givennames": "Siddharth", 
        "email": "sdeshpan@udel.edu", 
        "familyname": "Deshpande", 
        "affiliations": [
          "Davidson School of Chemical Engineering, Purdue University, West Lafayette, Indiana 47907, USA", 
          "Department of Chemical Engineering, University of Delaware, Newark, DE"
        ]
      }, 
      {
        "givennames": "Jeffrey", 
        "email": "jgreeley@purdue.edu", 
        "familyname": "Greeley", 
        "affiliations": [
          "Davidson School of Chemical Engineering, Purdue University, West Lafayette, Indiana 47907, USA"
        ]
      }
    ], 
    "status": "published", 
    "doi": "10.24435/materialscloud:td-hf", 
    "title": "Adsorbate chemical environment-based machine learning framework for heterogeneous catalysis", 
    "id": "1306", 
    "description": "Heterogeneous catalytic reactions are influenced by a subtle interplay of atomic-scale factors, ranging from the catalysts\u2019 local morphology to the presence of high adsorbate coverages. Describing such phenomena via computational models requires generation and analysis of a large space of surface atomic configurations. To address this challenge, we present the Adsorbate Chemical Environment-based Graph Convolution Neural Network (ACE-GCN), a screening workflow that can account for atomistic configurations comprising diverse adsorbates, binding locations, coordination environments, and substrate morphologies. Using this workflow, we develop catalyst surface models for two illustrative systems: (i) NO adsorbed on a Pt3Sn(111) alloy surface, of interest for nitrate electroreduction processes, where high adsorbate coverages combine with the low symmetry of the alloy substrate to produce a large configurational space, and (ii) OH* adsorbed on a stepped Pt(221) facet, of relevance to the Oxygen Reduction Reaction, wherein the presence of irregular crystal surfaces, high adsorbate coverages, and directionally-dependent adsorbate-adsorbate interactions result in the configurational complexity. In both cases, the ACE-GCN model, having trained on a fraction (~10%) of the total DFT-relaxed configurations, successfully ranks the relative stabilities of unrelaxed atomic configurations sampled from a large configurational space. This approach is expected to accelerate development of rigorous descriptions of catalyst surfaces under in-situ conditions.", 
    "owner": 714, 
    "_oai": {
      "id": "oai:materialscloud.org:1306"
    }, 
    "conceptrecid": "1305", 
    "references": [
      {
        "doi": "10.26434/chemrxiv-2021-8fcxm", 
        "url": "https://chemrxiv.org/engage/chemrxiv/article-details/60f5d5bf7bf0c92ab45f6c29", 
        "comment": "Preprint version of the manuscript where the data is discussed", 
        "citation": "Ghanekar P, Deshpande S, Greeley J. Adsorbate chemical environment-based machine learning framework for heterogeneous catalysis. ChemRxiv. Cambridge: Cambridge Open Engage; 2021", 
        "type": "Preprint"
      }
    ]
  }, 
  "updated": "2022-04-11T12:37:43.529364+00:00", 
  "revision": 4, 
  "id": "1306", 
  "created": "2022-04-03T21:06:39.671159+00:00"
}