Turbulent Fluid Flows with Generative Deep Learning

Multi-fidelity Generative Deep Learning Turbulent Flows [FoDS][ArXiv]

Nicholas Geneva, Nicholas Zabaras

---

A novel multi-fidelity deep generative model is introduced for the surrogate modeling of high-fidelity turbulent flow fields given the solution of a computationally inexpensive but inaccurate low-fidelity solver.

• Getting Started
• Documentation
• Data Repository

Core Dependencies

• Python 3.6.5
• PyTorch 1.6.0
• Matplotlib 3.1.1
• SciPy 1.5.2
• Dataclasses 0.7.0

See requirements.txt for full dependency list.

Citation

Find this useful or like this work? Cite us with:

    @article{geneva2020multi,
        title = "Multi-fidelity generative deep learning turbulent flows",
            author = "Nicholas Geneva and  Nicholas Zabaras",
            journal = "Foundations of Data Science",
            volume = "2",
            pages = "391",
            year = "2020",
            issn = "A0000-0002",
            doi = "10.3934/fods.2020019",
            url = "http://aimsciences.org/article/id/3a9f3d14-3421-4947-a45f-a9cc74edd097"
    }