{
  "abstract": "Surrogate modeling has become a powerful approach for accelerating computational fluid dynamics (CFD) simulations, yet existing three-dimensional (3D) geometric learning models–based on meshes, point clouds, or voxels–remain fundamentally limited by resolution, memory cost, and dependence on explicit geometric discretizations. We introduce TripNet, a triplane-based neural framework that encodes 3D geometry into a compact, continuous, resolution-independent representation. Unlike traditional mesh-dependent models, TripNet supports query-based predictions at arbitrary spatial locations, enabling high-fidelity aerodynamic field estimation without relying on mesh connectivity or downsampled geometry. TripNet achieves state-of-the-art performance on the DrivAerNet and DrivAerNet++ datasets across three major aerodynamic tasks: drag coefficient prediction, surface pressure and wall-shear stress regression, and full 3D volumetric flow-field prediction. TripNet attains an R2 of 0.972 for drag prediction and a relative L2 error of 10.39% for velocity magnitude. TripNet reduces inference time by several orders of magnitude–predicting drag in 0.01 s and full 3D flow fields in 2 s on a single graphics processing unit–while improving accuracy and reducing memory cost compared to strong baselines such as FigConvNet, Transolver, and MeshGraphNet. Beyond in-distribution prediction, we demonstrate that triplane features encode robust, transferable geometric–aerodynamic priors. TripNet exhibits strong cross-shape generalization, outperforming prior works when trained on two car-body classes and tested on an unseen third shape. Furthermore, TripNet achieves data-efficient cross-dataset transfer: when pretrained on DrivAerNet++ and finetuned on the high-fidelity DrivAerML dataset, TripNet surpasses models trained solely on DrivAerML across all metrics, even with as few as 10–50 gradient steps. Collectively, these results highlight triplanes as a scalable, generalizable representation for partial differential equation surrogate modeling and establish TripNet as an accurate, efficient alternative to traditional CFD solvers and existing geometric deep learning models.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Mechanical Engineering, Massachusetts Institute of Technology 1 , Cambridge, Massachusetts 02139,",
    "Technical University of Munich 2 , Garching,"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Q Chen",
      "orcid": "0009-0006-7314-0823"
    },
    {
      "affs": [
        0
      ],
      "name": "Mohamed Elrefaie",
      "orcid": "0009-0008-9981-0930"
    },
    {
      "affs": [
        1
      ],
      "name": "Angela Dai",
      "orcid": "0000-0002-6241-8782"
    },
    {
      "affs": [
        0
      ],
      "name": "Faez Ahmed",
      "orcid": "0000-0002-5227-2628"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5ne7cfnp3jgvh.bib",
  "cited_by": 22,
  "doi": "10.1063/5.0324695",
  "fulltext_url": null,
  "id": "5ne7cfnp3jgvh",
  "issns": [
    "1070-6631",
    "1089-7666",
    "1527-2435"
  ],
  "landing_url": "https://doi.org/10.1063/5.0324695",
  "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",
      "3109|Model Reduction and Neural Networks"
    ]
  ],
  "openalex": "W7163511519",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-01",
  "publisher": "American Institute of Physics",
  "ris": "https://research.draconitic.com/paper/5ne7cfnp3jgvh.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:02Z",
      "native_id": "W7163511519",
      "source": "openalex",
      "url": "https://doi.org/10.1063/5.0324695"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "openalex:3109|Model Reduction and Neural Networks",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "TripNet: Learning large-scale high-fidelity three-dimensional car aerodynamics with triplane networks",
  "title_text": "TripNet: Learning large-scale high-fidelity three-dimensional car aerodynamics with triplane networks",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:02Z",
  "url": "https://research.draconitic.com/paper/5ne7cfnp3jgvh",
  "venue": "Physics of Fluids",
  "versions": []
}