{
  "abstract": "Energetic materials involve multiple interactions, making reliable machine-learning potentials (MLPs) difficult to construct without extensive datasets. Here, we enhance the ability of the neural network interatomic potential (NNAP) to describe molecular systems using sphmulti, a refined spherical-harmonic basis set that combines extra radial basis with element-specific chemical weighting in each radial channel. We further integrate hyperactive learning, farthest-point sampling, and iterative sufficiency criteria with knowledge-guided key events, enabling the NNAP to retain essential information for describing the material system. For 3,3'-diamino-4,4'-azoxyfurazan, the resulting NNAP is trained on only 13,680 configurations yet captures key properties, including the isomerization barrier, pyrolysis activation energy, and shock Hugoniot behavior. NNAP-driven molecular dynamics simulations further reveal that pyrolysis proceeds through furazan-ring opening followed by chain reactions, whereas shock loading induces anisotropic hydrogen transfer driven by interlayer structural deformations. This work enables efficient and reliable MLPs for energetic materials.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.17987",
  "author_total": 15,
  "authors": [
    {
      "name": "Guanchen Dong"
    },
    {
      "name": "Huanrong Liu"
    },
    {
      "name": "Lin Wang"
    },
    {
      "name": "Yuxuan Chen"
    },
    {
      "name": "Zhengyu Tu"
    },
    {
      "name": "Qing-an Li"
    },
    {
      "name": "Bin Xu"
    },
    {
      "name": "Jian Li"
    },
    {
      "name": "Shan Zhang"
    },
    {
      "name": "Xiaotong Li"
    },
    {
      "name": "Linghua Tan"
    },
    {
      "name": "Guangcheng Yang"
    },
    {
      "name": "Jun Kang"
    },
    {
      "name": "Rui Su"
    },
    {
      "name": "Pengfei Guan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/38bvfs8knfc3g.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.17987",
  "fulltext_url": null,
  "id": "38bvfs8knfc3g",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.17987",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ],
    [
      "openalex",
      "2211|Energetic Materials and Combustion"
    ]
  ],
  "openalex": "W7221811427",
  "pdf_url": "https://arxiv.org/pdf/2610.17987",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/38bvfs8knfc3g.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:50Z",
      "native_id": "2610.17987",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.17987"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "Knowledge-Guided Construction of Machine Learning Potentials for Reactive Behavior in Energetic Materials",
  "title_text": "Knowledge-Guided Construction of Machine Learning Potentials for Reactive Behavior in Energetic Materials",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:50Z",
  "url": "https://research.draconitic.com/paper/38bvfs8knfc3g",
  "venue": "arXiv",
  "versions": []
}