{
  "abstract": "Machine learning (ML) models for electronic structure typically rely on large datasets generated by computationally expensive Kohn-Sham density functional theory calculations, as it is not known a priori which portions of the data are essential for accurate learning. Here, we reveal significant redundancies in electronic structure datasets across diverse material systems and attribute them to the low intrinsic dimensionality of the underlying data. We show that even random pruning can substantially reduce dataset size with minimal degradation in predictive accuracy. Moreover, a state-of-the-art coverage-based pruning strategy that samples data across all learning difficulties almost always preserves chemical accuracy and maintains model generalizability while using up to two orders of magnitude less data and reducing training time by a factor of three or more. We further demonstrate that the essential electronic structure information lies on a low-dimensional, non-linear manifold, providing a potential geometric explanation for the observed prunability. These observations are consistent with the predominance of local atomic environments in determining electronic properties, as suggested by nearsightedness arguments, and indicate that large-scale datasets may contain highly overlapping information. Our findings challenge the prevailing assumption that such extensive datasets are necessary for accurate ML-based electronic structure predictions and open a path toward identifying minimal, representative datasets for each material class.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Mechanical and Aerospace Engineering, Michigan Technological University, Houghton, MI, USA",
    "Hopkins Extreme Materials Institute, Johns Hopkins University, Baltimore, MD, USA",
    "Department of Materials Science and Engineering, University of California, Los Angeles, CA, USA",
    "Center for Artificial Intelligence, Michigan Technological University, Houghton, MI, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Sazzad Hossain",
      "orcid": "0009-0005-4064-5668"
    },
    {
      "affs": [
        1
      ],
      "name": "Ponkrshnan Thiagarajan",
      "orcid": "0000-0003-3946-3902"
    },
    {
      "affs": [
        0
      ],
      "name": "Shashank Pathrudkar",
      "orcid": "0000-0001-8546-8056"
    },
    {
      "affs": [
        2
      ],
      "name": "S. Taylor",
      "orcid": "0000-0001-6321-9585"
    },
    {
      "affs": [
        2
      ],
      "name": "Abhijeet S. Gangan",
      "orcid": "0000-0002-8937-7984"
    },
    {
      "affs": [
        2
      ],
      "name": "Amartya Banerjee",
      "orcid": "0000-0001-5916-9167"
    },
    {
      "affs": [
        3,
        0
      ],
      "name": "Susanta Ghosh",
      "orcid": "0000-0002-6262-4121"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/eq031c0v0n6q7.bib",
  "cited_by": 7,
  "doi": "10.1038/s41524-026-02361-x",
  "fulltext_url": null,
  "id": "eq031c0v0n6q7",
  "issns": [
    "2057-3960"
  ],
  "landing_url": "https://doi.org/10.1038/s41524-026-02361-x",
  "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": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W4414689473",
  "pdf_url": "https://www.nature.com/articles/s41524-026-02361-x_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-19",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/eq031c0v0n6q7.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:19Z",
      "native_id": "W4414689473",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41524-026-02361-x"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Surprisingly high redundancy in electronic structure data across materials explained by low intrinsic dimensionality",
  "title_text": "Surprisingly high redundancy in electronic structure data across materials explained by low intrinsic dimensionality",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:57Z",
  "url": "https://research.draconitic.com/paper/eq031c0v0n6q7",
  "venue": "npj Computational Materials",
  "versions": []
}