{
  "abstract": "Predicting the drag coefficient $C_\\mathrm{d}$ of irregular particles requires representing their complex three-dimensional geometry in a form suitable for predictive models. Empirical drag correlations and many data-driven models represent particle geometry through a small set of hand-crafted shape descriptors. Geometric differences omitted by these descriptors are unavailable to the predictor. We propose a variational autoencoder-multilayer perceptron (VAE-MLP) framework that learns a latent representation directly from voxelized particle geometry. Geometry reconstruction and drag coefficient prediction jointly guide the learning of this representation. We compare VAE-MLP with a descriptor-based MLP (Descriptor-MLP) and established empirical correlations using CFD data for synthetic particle geometries at Reynolds numbers of 10--200. When the evaluated geometric variations are represented in the training data, the two learned models achieve comparable accuracy for regular ellipsoids, while VAE-MLP yields lower errors for irregular particles. When high-order surface perturbations are excluded from training, VAE-MLP achieves lower overall mean absolute relative error in all five training runs. At the strongest tested perturbation, the mean errors across these runs are 4.97% for VAE-MLP and 9.88% for Descriptor-MLP. These results support learning geometric representations directly from particle geometry to improve drag prediction for the irregular geometries and unseen surface perturbations examined here.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.23087",
  "author_total": 5,
  "authors": [
    {
      "name": "Zihao Li"
    },
    {
      "name": "Shota Deguchi"
    },
    {
      "name": "Mitsuteru Asai"
    },
    {
      "name": "Shunhua Chen"
    },
    {
      "name": "Naoto Mitsume"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/95fk570099pb7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.23087",
  "fulltext_url": null,
  "id": "95fk570099pb7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.23087",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.NA"
    ],
    [
      "arxiv",
      "math.NA"
    ],
    [
      "openalex",
      "3109|Model Reduction and Neural Networks"
    ]
  ],
  "openalex": "W7222930981",
  "pdf_url": "https://arxiv.org/pdf/2610.23087",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/95fk570099pb7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:37Z",
      "native_id": "2610.23087",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.23087"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.NA",
      "subfield": "numerical-analysis"
    }
  ],
  "title": "Geometry-Aware Latent Representation Learning for Drag Coefficient Prediction of Irregular Particles",
  "title_text": "Geometry-Aware Latent Representation Learning for Drag Coefficient Prediction of Irregular Particles",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:31Z",
  "url": "https://research.draconitic.com/paper/95fk570099pb7",
  "venue": "arXiv",
  "versions": []
}