{
  "abstract": "Machine-learning potentials (MLPs) extend atomistic simulations beyond the size and time scales accessible to density functional theory while retaining near-first-principles accuracy. However, their reliability depends on training data that cover the relevant potential-energy surface (PES). In heterogeneous catalysis, local changes at active sites may be obscured by redundant nonactive atoms when configurations are selected using global metrics. This limitation calls for an atom-resolved criterion for identifying where chemically relevant configurational information is concentrated. Here we introduce Active Atom Identification (AAI), an algorithm that measures local structural evolution and identifies active atoms that contribute most to configurational diversity. Building on this atom-resolved information, we develop IDEAL (Information-Dense Extraction and Adaptive Learning), which integrates data generation, active-learning selection and dataset refinement into a unified workflow for MLP construction. For CO2 adsorption at Ag/H2O interfaces, a model trained on an IDEAL-selected subset comprising 44% of the original dataset, reaches the accuracy of the full-dataset model. The broad applicability of IDEAL is further demonstrated in two additional applications: database refinement for solid-state electrolytes and transfer learning between zeolite-supported Rh clusters and their hydroxylated analogues. These results validate local structural evolution as an effective criterion for constructing information-dense MLP datasets in complex atomistic systems.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Chemistry",
    "Tsinghua University",
    "Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Department of Energy and Power Engineering",
    "Advanced Institute for Materials Research (WPI-AIMR",
    "Tohoku University",
    "Ganjiang Innovation Academy",
    "Chinese Academy of Science",
    "Department of Chemistry and Guangdong Provincial Key Laboratory of Catalytic Chemistry",
    "Southern University of Science and Technology"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Haobo Zhao"
    },
    {
      "affs": [
        2,
        1
      ],
      "name": "Xiongwei Tian"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Jixuan Lin"
    },
    {
      "affs": [
        2,
        1
      ],
      "name": "Yuqun Zhuo"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Yiming Lu"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Hai Xiao"
    },
    {
      "affs": [
        0,
        1,
        5,
        6,
        7,
        8
      ],
      "name": "Jun Li"
    },
    {
      "name": "Zhao Haobo"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bhmnb263ne3bm.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009531/v1",
  "fulltext_url": null,
  "id": "bhmnb263ne3bm",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009531/v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7214593386",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009531/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/bhmnb263ne3bm.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:21Z",
      "native_id": "10.26434/chemrxiv.15009531",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009531/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Active Atom Identification for Information-Dense Training of Machine-Learning Potentials in Catalysis",
  "title_text": "Active Atom Identification for Information-Dense Training of Machine-Learning Potentials in Catalysis",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:21Z",
  "url": "https://research.draconitic.com/paper/bhmnb263ne3bm",
  "venue": "ChemRxiv",
  "versions": []
}