Reducing uncertainties in climate models

See allHide authors and affiliations

Science  27 Jul 2018:
Vol. 361, Issue 6400, pp. 326-327
DOI: 10.1126/science.aau1864

eLetters is an online forum for ongoing peer review. Submission of eLetters are open to all. eLetters are not edited, proofread, or indexed.  Please read our Terms of Service before submitting your own eLetter.

Compose eLetter

Plain text

  • Plain text
    No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Author Information
First or given name, e.g. 'Peter'.
Your last, or family, name, e.g. 'MacMoody'.
Your email address, e.g.
Your role and/or occupation, e.g. 'Orthopedic Surgeon'.
Your organization or institution (if applicable), e.g. 'Royal Free Hospital'.
Statement of Competing Interests

This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

Vertical Tabs

  • Climate models should be built by machine learning instead of man-made formulas

    Brian J. Soden et al. reported reducing uncertainties in climate models (1). Conventional climate models based on man-made formulas do not show the expected behaviors (1). Researchers should use data in order to build an accurate climate model instead of man-made formulas (2). After extensive trainings, machine learning predictions will be more accurate than that of man-made formula models. Defeating human champions in Go games (3), Shogi games (4), and Quiz bowl questions (5) respectively show the superiority of the machine learning over man-made formulas. I don’t understand why climate model researchers still stick to physical formulas instead of machine learning for better climate predictions.

    1. Brian J. Soden et al., Reducing uncertainties in climate models, Science 27 Jul 2018: Vol. 361, Issue 6400, pp. 326-327
    2. Y. Takefuji,

    Competing Interests: None declared.

Stay Connected to Science