{
  "abstract": "Efficient optimization and control of photonic computing and communication systems increasingly rely on accurate surrogate models/digital twins. While data-driven models may achieve faster inference than traditional physics-based methods, they typically suffer from poor training data efficiency and limited generalizability. To address this trade-off, physics-informed data-driven modeling has emerged as a powerful hybrid paradigm. This paper presents a comparative analysis of these three modeling paradigms across three test use cases: optical amplifiers, directly modulated lasers, and interferometer meshes. By evaluating model complexity, data efficiency, generalizability, and modularity, this work provides a detailed analysis of the respective trade-offs and highlights the advantages of combining physical insight with data-driven learning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.07274",
  "author_total": 6,
  "authors": [
    {
      "name": "Isidora Teofilovic"
    },
    {
      "name": "Sergio Hernandez Fernandez"
    },
    {
      "name": "Metodi P. Yankov"
    },
    {
      "name": "Christophe Peucheret"
    },
    {
      "name": "Darko Zibar"
    },
    {
      "name": "Francesco Da Ros"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2cmawxhevxbjh.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.07274",
  "fulltext_url": null,
  "id": "2cmawxhevxbjh",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.07274",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "eess.SP"
    ],
    [
      "arxiv",
      "physics.optics"
    ],
    [
      "openalex",
      "1702|Neural Networks and Reservoir Computing"
    ]
  ],
  "openalex": "W7167785634",
  "pdf_url": "https://arxiv.org/pdf/2607.07274",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2cmawxhevxbjh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:32Z",
      "native_id": "2607.07274",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.07274"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.optics",
      "subfield": "optics-photonics"
    }
  ],
  "title": "Beyond white- and black-box modeling tools in optical communications and optical computing: physics-informed data-driven modeling",
  "title_text": "Beyond white- and black-box modeling tools in optical communications and optical computing: physics-informed data-driven modeling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:28Z",
  "url": "https://research.draconitic.com/paper/2cmawxhevxbjh",
  "venue": "arXiv",
  "versions": []
}