{
  "abstract": "Infrared spectroscopy serves as an indispensable analytical tool across materials science, pharmaceutical development, and the life sciences. Computational insights derived from first-principles methods enhance the interpretation of vibrational spectra, yet their application remains hindered by high computational cost. Machine-learned interatomic potentials offer a route to accelerate these predictions by multiple orders of magnitude without sacrificing ab initio accuracy. Here, we present an on-the-fly active learning framework for the automated training of such potentials specifically tailored to infrared spectral prediction. Our approach employs a multitask acquisition strategy, in which model performance is evaluated iteratively on designated objectives, avoiding the dependence on fixed training sets. We demonstrate that this multitask scheme creates interatomic potentials that exhibit robustness and fidelity in complex workflows for calculating infrared spectra.",
  "abstract_shown": true,
  "affiliations": [
    "Software for Chemistry & Materials BV , De Boelelaan 1109, Amsterdam1081 HV, The Netherlands.",
    "Vrije Universiteit Amsterdam , De Boelelaan 1108, Amsterdam1081 HZ, The Netherlands."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Giulio Benedini"
    },
    {
      "affs": [
        0
      ],
      "name": "Matti Hellström",
      "orcid": "0000-0003-3053-5658"
    },
    {
      "affs": [
        1
      ],
      "name": "Lucas Visscher",
      "orcid": "0000-0002-7748-6243"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5gzt6bjy1603p.bib",
  "cited_by": 0,
  "doi": "10.1021/acs.jctc.6c00756",
  "fulltext_url": "https://europepmc.org/articles/PMC13671170",
  "id": "5gzt6bjy1603p",
  "issns": [
    "1549-9618",
    "1549-9626"
  ],
  "landing_url": "https://europepmc.org/article/MED/42917289",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7214644175",
  "pdf_url": "https://europepmc.org/articles/PMC13671170?pdf=render",
  "pmcid": "PMC13671170",
  "pmid": "42917289",
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5gzt6bjy1603p.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:36Z",
      "native_id": "MED:42917289",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42917289"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Flexible On-the-Fly Active Learning for Molecular Infrared Spectra.",
  "title_text": "Flexible On-the-Fly Active Learning for Molecular Infrared Spectra.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:20:36Z",
  "url": "https://research.draconitic.com/paper/5gzt6bjy1603p",
  "venue": "Journal of chemical theory and computation",
  "versions": []
}