{
  "abstract": "Estimating material properties like Young's modulus and internal damping from radiated acoustic fields is challenging under sparse, noisy measurement conditions. This work employs sequential physics-informed neural networks with Fourier features to estimate these material properties for a vibrating plate. The inverse problem is solved by decoupling fluid and structural domains to effectively filter boundary differentiation and data noise. Multi-frequency statistical ensembles are introduced to quantify the uncertainty coming from neural network initialization robustness and learning biases. Following a validation of the method in a proof of concept on vast, low-noise data conditions, its limits under sparse, noisy data are demonstrated.",
  "abstract_shown": true,
  "affiliations": [
    "Fachgebiet Systemzuverlässigkeit, Adaptronik und Maschinenakustik, Technische Universität Darmstadt, Darmstadt, Hessen 64287, Germany"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Paul Brand",
      "orcid": "0009-0004-5845-2963"
    },
    {
      "affs": [
        0
      ],
      "name": "Robert Feldmann",
      "orcid": "0000-0001-6932-2401"
    },
    {
      "affs": [
        0
      ],
      "name": "Tobias Melz",
      "orcid": "0000-0002-1897-532X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ec66jmawnds2m.bib",
  "cited_by": 0,
  "doi": "10.1121/10.0047523",
  "fulltext_url": "https://pubs.aip.org/asa/jel/article-pdf/doi/10.1121/10.0047523/21202691/112401_1_10.0047523.pdf",
  "id": "ec66jmawnds2m",
  "issns": [
    "2691-1191"
  ],
  "landing_url": "https://doi.org/10.1121/10.0047523",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "QC221-246"
    ]
  ],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-16",
  "publisher": "AIP Publishing LLC",
  "ris": "https://research.draconitic.com/paper/ec66jmawnds2m.ris",
  "sources": [
    {
      "first_seen": "2026-11-16T15:21:16Z",
      "native_id": "171b9d9fde724f19bd2a3a76eb0128ba",
      "source": "doaj",
      "url": "https://doi.org/10.1121/10.0047523"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "lcc:QC221-246",
      "subfield": "general"
    }
  ],
  "title": "Domain-decoupled physics-informed neural networks for inverse material property estimation from acoustic fields",
  "title_text": "Domain-decoupled physics-informed neural networks for inverse material property estimation from acoustic fields",
  "type": "peer-reviewed",
  "updated_at": "2026-11-16T15:21:16Z",
  "url": "https://research.draconitic.com/paper/ec66jmawnds2m",
  "venue": "JASA Express Letters",
  "versions": []
}