{
  "abstract": "Artificial intelligence (AI) and machine learning (ML) are increasingly being applied to corrosion-inhibitor discovery, but most existing discussions focus on organic molecular inhibitors or on individual computational methods. This review addresses the more specific problem of how data-driven prediction can be connected to the multiscale design of nanocomposite corrosion inhibitors, in which organic or bio-derived species interact with inorganic nanoparticles, metal surfaces, and electrolytes. The review critically examines the complementary roles of ML, density functional theory (DFT), molecular dynamics (MD), Monte Carlo (MC) simulation, electrochemical measurements, and surface characterization. Particular attention is given to dataset size and heterogeneity, descriptor selection, model validation, uncertainty, extrapolation across metals and corrosive media, and the distinction between statistical association and mechanistic evidence. A nanocomposite-specific framework is proposed in which formulation variables—nanoparticle composition, size, surface functionality, dispersion, organic/inorganic ratio, inhibitor concentration, and environmental conditions—are treated alongside molecular and electronic descriptors. AI screening is followed by mechanistic interrogation using DFT/MD/MC and then by experimental verification using electrochemical and surface methods. The resulting closed-loop workflow is designed to make model predictions physically testable rather than merely statistically accurate. The review also distinguishes corrosion inhibitors, nanocomposite inhibitors, nanocomposite coatings, and corrosion-resistant materials, and identifies data and validation practices needed for transferable models. The central contribution is therefore not another general catalogue of AI or molecular-simulation methods, but a critical, nanocomposite-focused framework for connecting composition, interfacial physics, model prediction, and experimentally observed corrosion protection.",
  "abstract_shown": true,
  "affiliations": [
    "AKWA IBOM STATE UNIVERSITY"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Kufre Essien"
    },
    {
      "name": "Akanimo N. Ekanem"
    },
    {
      "name": "Aniedi E. Nyong"
    },
    {
      "name": "Okon E. Okon"
    },
    {
      "name": "Aniekan E. Akpakpan"
    },
    {
      "name": "Ekemini J. Obosi"
    },
    {
      "name": "Idaraesit A. Ite"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0andq16pdtexm.bib",
  "cited_by": 0,
  "doi": null,
  "fulltext_url": "http://caip.co-ac.com/index.php/materialsanddevices/article/view/231",
  "id": "0andq16pdtexm",
  "issns": [
    "2495-3911"
  ],
  "landing_url": "http://caip.co-ac.com/index.php/materialsanddevices/article/view/231",
  "language": "en",
  "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": [
    [
      "lcc",
      "QD450-801"
    ],
    [
      "lcc",
      "QD901-999"
    ]
  ],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-06",
  "publisher": "Collaborating Academics IP",
  "ris": "https://research.draconitic.com/paper/0andq16pdtexm.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T14:21:08Z",
      "native_id": "96927c9330de4e7c8a462c1269eaa060",
      "source": "doaj",
      "url": "http://caip.co-ac.com/index.php/materialsanddevices/article/view/231"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "lcc:QD450-801",
      "subfield": "physical"
    }
  ],
  "title": "Artificial Intelligence-Assisted Engineering of Nanocomposite Corrosion Protection Materials: A Critical Review of Machine Learning, Molecular Simulation, and Experimental Verification",
  "title_text": "Artificial Intelligence-Assisted Engineering of Nanocomposite Corrosion Protection Materials: A Critical Review of Machine Learning, Molecular Simulation, and Experimental Verification",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T14:20:35Z",
  "url": "https://research.draconitic.com/paper/0andq16pdtexm",
  "venue": "Materials and Devices",
  "versions": []
}