Fast Modeling and Understanding Fluid Dynamics Systems with Encoder-Decoder Networks

@article{Thavarajah2020FastMA,
  title={Fast Modeling and Understanding Fluid Dynamics Systems with Encoder-Decoder Networks},
  author={Rohan Thavarajah and Xiang Zhai and Zheren Ma and D. Castineira},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.05409}
}
  • Rohan Thavarajah, Xiang Zhai, +1 author D. Castineira
  • Published 2020
  • Physics, Computer Science
  • ArXiv
  • Is a deep learning model capable of understanding systems governed by certain first principle laws by only observing the system's output? Can deep learning learn the underlying physics and honor the physics when making predictions? The answers are both positive. In an effort to simulate two-dimensional subsurface fluid dynamics in porous media, we found that an accurate deep-learning-based proxy model can be taught efficiently by a computationally expensive finite-volume-based simulator. We… CONTINUE READING

    References

    SHOWING 1-10 OF 32 REFERENCES
    Deep Learning the Physics of Transport Phenomena
    • 62
    • PDF
    Latent Space Physics: Towards Learning the Temporal Evolution of Fluid Flow
    • 98
    • PDF
    Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
    • 147
    • PDF
    Generative Adversarial Nets
    • 20,757
    • Highly Influential
    • PDF