{
  "id": "1802.10123",
  "version": "v1",
  "published": "2018-02-27T19:18:43.000Z",
  "updated": "2018-02-27T19:18:43.000Z",
  "title": "Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow",
  "authors": [
    "Steffen Wiewel",
    "Moritz Becher",
    "Nils Thuerey"
  ],
  "comment": "submitted to SIGGRAPH 2018, additional materials: https://ge.in.tum.de/publications/latent-space-physics/",
  "categories": [
    "cs.LG",
    "cs.GR"
  ],
  "abstract": "Our work explores methods for the data-driven inference of temporal evolutions of physical functions with deep learning techniques. More specifically, we target fluid flow problems, and we propose a novel LSTM-based approach to predict the changes of the pressure field over time. The central challenge in this context is the high dimensionality of Eulerian space-time data sets. Key for arriving at a feasible algorithm is a technique for dimensionality reduction based on convolutional neural networks, as well as a special architecture for temporal prediction. We demonstrate that dense 3D+time functions of physics system can be predicted with neural networks, and we arrive at a neural-network based simulation algorithm with significant practical speed-ups. We demonstrate the capabilities of our method with a series of complex liquid simulations, and with a set of single-phase buoyancy simulations. With a set of trained networks, our method is more than two orders of magnitudes faster than a traditional pressure solver. Additionally, we present and discuss a series of detailed evaluations for the different components of our algorithm.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-02-27T19:18:43.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "temporal evolution",
      "latent-space physics",
      "target fluid flow problems",
      "eulerian space-time data sets",
      "complex liquid simulations"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}