Learning physical laws from observations of complex dynamics

被引:0
|
作者
Novoselov, Kostya S. [1 ]
Li, Qianxiao [1 ]
机构
[1] Natl Univ Singapore, Singapore, Singapore
来源
NATURE COMPUTATIONAL SCIENCE | 2024年 / 4卷 / 01期
关键词
D O I
10.1038/s43588-023-00590-4
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The laws of physics, formulated in a compact form, are elusive for complex dynamic phenomena. However, it is now shown that, using artificial intelligence constrained by the physical Onsager principle, a custom thermodynamic description of a complex system can be constructed from the observation of its dynamical behavior.
引用
收藏
页码:9 / 10
页数:2
相关论文
共 50 条
  • [31] Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian deep learning
    Dai, Biwei
    Seljak, Uros
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2021, 118 (16)
  • [32] Observations on the Cellular Dynamics of a Metabolic Complex, the Purinosome
    Benkovic, Stephen
    Chan, Chung Yu
    Kim, Doory
    Pedley, Anthony
    Zhuang, Xiaowei
    FASEB JOURNAL, 2016, 30
  • [33] Dynamics of complex systems:: Scaling laws for the period of Boolean networks
    Albert, R
    Barabási, AL
    PHYSICAL REVIEW LETTERS, 2000, 84 (24) : 5660 - 5663
  • [34] PHYSICAL LAWS AND BIOLOGICAL LAWS
    ARCIDIACONO, S
    FOLIA HUMANISTICA, 1987, 25 (294-95) : 433 - 442
  • [35] Event Timing in Associative Learning: From Biochemical Reaction Dynamics to Behavioural Observations
    Yarali, Ayse
    Nehrkorn, Johannes
    Tanimoto, Hiromu
    Herz, Andreas V. M.
    PLOS ONE, 2012, 7 (03):
  • [36] Uncovering turbulent plasma dynamics via deep learning from partial observations
    Mathews, A.
    Francisquez, M.
    Hughes, J. W.
    Hatch, D. R.
    Zhu, B.
    Rogers, B. N.
    PHYSICAL REVIEW E, 2021, 104 (02)
  • [37] Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
    Huang, Zijie
    Sun, Yizhou
    Wang, Wei
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [38] Ergodic Opinion Dynamics Over Networks: Learning Influences From Partial Observations
    Ravazzi, Chiara
    Hojjatinia, Sarah
    Lagoa, Constantino M.
    Dabbene, Fabrizio
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2021, 66 (06) : 2709 - 2723
  • [39] Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations
    Wilinski, Mateusz
    Lokhoy, Andrey Y.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [40] Reverse Physics: From Laws to Physical Assumptions
    Carcassi, Gabriele
    Aidala, Christine A.
    FOUNDATIONS OF PHYSICS, 2022, 52 (02)