{
  "abstract": "Physics-informed neural networks (PINNs) offer a promising framework for modeling semiconductor devices, yet standard architectures struggle with severe numerical stiffness and multiscale spatial discrepancies inherent to oxide heterostructures. Here, we demonstrate a cascaded PINN architecture coupled with a custom second-order Chebyshev second kind polynomial spectral optimizer (DSO V2 Hybrid) to model ion-electronic drift-diffusion transport in Pt/SrTiO$_3$/Si memristive heterostructures across a 20 nm STO film on a 380 $μ$m Si substrate. By isolating potential, carrier density, and vacancy transport into four sequentially trained sub-neural-networks, our model circumvents condition numbers exceeding $10^{16}$ without operator splitting. The trained surrogate reproduces experimental conductive-AFM current-voltage hysteresis ($R^2 > 0.96$) while ensuring strict Poisson consistency across continuous space. Compared to conventional finite-element solvers (e.g., COMSOL), the PINN surrogate enables differentiable inverse parameter estimation and linear time inference.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.02966",
  "author_total": 3,
  "authors": [
    {
      "name": "Rodion Podorozhny"
    },
    {
      "name": "Nikoleta Theodoropoulou"
    },
    {
      "name": "Jelena Tešić"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2csy5w11zhbs6.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.02966",
  "fulltext_url": null,
  "id": "2csy5w11zhbs6",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.02966",
  "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"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "openalex",
      "3109|Model Reduction and Neural Networks"
    ]
  ],
  "openalex": "W7208761401",
  "pdf_url": "https://arxiv.org/pdf/2609.02966",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2csy5w11zhbs6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:31Z",
      "native_id": "2609.02966",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.02966"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial $\\mathrm{SrTiO_3}$ on Si memristors via Dynamic Spectral Optimization",
  "title_text": "Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial SrTiO_3 on Si memristors via Dynamic Spectral Optimization",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:31Z",
  "url": "https://research.draconitic.com/paper/2csy5w11zhbs6",
  "venue": "arXiv",
  "versions": []
}