{
  "id": "2009.01407",
  "version": "v1",
  "published": "2020-09-03T01:40:56.000Z",
  "updated": "2020-09-03T01:40:56.000Z",
  "title": "Transfer learning for nonlinear dynamics and its application to fluid turbulence",
  "authors": [
    "Masanobu Inubushi",
    "Susumu Goto"
  ],
  "comment": "8 pages, 7 figures",
  "categories": [
    "physics.flu-dyn",
    "math.DS",
    "nlin.CD",
    "physics.comp-ph",
    "stat.ML"
  ],
  "abstract": "We introduce transfer learning for nonlinear dynamics, which enables efficient predictions of chaotic dynamics by utilizing a small amount of data. For the Lorenz chaos, by optimizing the transfer rate, we accomplish more accurate inference than the conventional method by an order of magnitude. Moreover, a surprisingly small amount of learning is enough to infer the energy dissipation rate of the Navier-Stokes turbulence because we can, thanks to the small-scale universality of turbulence, transfer a large amount of the knowledge learned from turbulence data at lower Reynolds number.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-09-03T01:40:56.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "68T01",
      "76F65",
      "37N10",
      "I.2",
      "J.2"
    ],
    "keywords": [
      "nonlinear dynamics",
      "fluid turbulence",
      "transfer learning",
      "application",
      "enables efficient predictions"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}