Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 6 min ago
PreprintCC BY 4.0arXiv

FlowMLLab: An open-source framework for reproducible computational-fluid-dynamics and scientific-machine-learning experiments

  • Ehsan Roohi
Open at sourcePDFDOICite

Abstract

FlowMLLab is an open-source framework that connects validated fluid-mechanics solvers to scientific machine-learning experiments under a reproducible contract. Its computational fluid dynamics (CFD) pathway generates cavity data, whereas its direct simulation Monte Carlo (DSMC) pathway supplies rarefied-flow evidence with sampling diagnostics. Case-wise partitions prevent leakage, and matched non-neural baselines determine whether learning offers a measurable advantage. Examples include a coordinate network and a proper orthogonal decomposition (POD) deep operator network (DeepONet), together with learned kinetic closures. Python components regenerate every figure, while sixteen tutorials use the same interfaces as the command-line tools. By retaining numerical provenance, blind-case protocols and physical validation targets, FlowMLLab emphasizes traceable evidence rather than black-box curve fitting.

Related

  1. Agentic programs: an emerging form of scientific software in computational materials science
    Yunsung Lim, Haekwan Jeon, Jaesun Kim +2
    arXivPreprintarXiv licenceFull textCondensed matterarXiv
  2. CELEBI: Design and Realization of a Reproducible Physics Analysis Framework
    Mingrui Zhao
    arXivPreprintCC BY 4.0Full textHigh-energy & particle physicsarXiv
  3. remage: a Geant4-based simulation framework for low-background experiments
    Toby Dixon, Eric Esch, Reyco Henning +4
    arXivPreprintCC BY 4.0Full textApplied physics & instrumentationHigh-energy & particle physicsarXiv
  4. A Reproducible Benchmark and Evidence-Retrieval Software Framework for Silicon Detector R&D Literature
    Tianqi Gao, Ruobing Jiang, Dawei Fu +2
    arXivPreprintarXiv licenceFull textApplied physics & instrumentationComputational physicsarXiv
  5. Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions
    Dimitris Ntounis, Ariel Schwartzman, Chris Chafe +1
    arXivPreprintCC BY 4.0Full textStatistical & nonlinear physicsarXiv

Cite

BibTeXRIS
BibTeX
@misc{roohi2026flowmllab,
  title = {{FlowMLLab: An open-source framework for reproducible computational-fluid-dynamics and scientific-machine-learning experiments}},
  author = {Ehsan Roohi},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.27975},
  eprint = {2609.27975},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27975},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - FlowMLLab: An open-source framework for reproducible computational-fluid-dynamics and scientific-machine-learning experiments
AU  - Ehsan Roohi
PY  - 2026
DA  - 2026/09/01
PB  - arXiv
DO  - 10.48550/arxiv.2609.27975
UR  - https://arxiv.org/abs/2609.27975
AB  - FlowMLLab is an open-source framework that connects validated fluid-mechanics solvers to scientific machine-learning experiments under a reproducible contract. Its computational fluid dynamics (CFD) pathway generates cavity data, whereas its direct simulation Monte Carlo (DSMC) pathway supplies rarefied-flow evidence with sampling diagnostics. Case-wise partitions prevent leakage, and matched non-neural baselines determine whether learning offers a measurable advantage. Examples include a coordinate network and a proper orthogonal decomposition (POD) deep operator network (DeepONet), together with learned kinetic closures. Python components regenerate every figure, while sixteen tutorials use the same interfaces as the command-line tools. By retaining numerical provenance, blind-case protocols and physical validation targets, FlowMLLab emphasizes traceable evidence rather than black-box curve fitting.
ER  -