literature
Literature
Authors
Jobs
Seminars
Conferences
DataBETA

Simulation Intelligence: Towards a New Generation of Scientific Methods

Dec 6, 2021
e-Print:
View in:
pdf
reference search2 citations

Citations per year

20212022202301
Abstract: (arXiv)
The original "Seven Motifs" set forth a roadmap of essential methods for the field of scientific computing, where a motif is an algorithmic method that captures a pattern of computation and data movement. We present the "Nine Motifs of Simulation Intelligence", a roadmap for the development and integration of the essential algorithms necessary for a merger of scientific computing, scientific simulation, and artificial intelligence. We call this merger simulation intelligence (SI), for short. We argue the motifs of simulation intelligence are interconnected and interdependent, much like the components within the layers of an operating system. Using this metaphor, we explore the nature of each layer of the simulation intelligence operating system stack (SI-stack) and the motifs therein: (1) Multi-physics and multi-scale modeling; (2) Surrogate modeling and emulation; (3) Simulation-based inference; (4) Causal modeling and inference; (5) Agent-based modeling; (6) Probabilistic programming; (7) Differentiable programming; (8) Open-ended optimization; (9) Machine programming. We believe coordinated efforts between motifs offers immense opportunity to accelerate scientific discovery, from solving inverse problems in synthetic biology and climate science, to directing nuclear energy experiments and predicting emergent behavior in socioeconomic settings. We elaborate on each layer of the SI-stack, detailing the state-of-art methods, presenting examples to highlight challenges and opportunities, and advocating for specific ways to advance the motifs and the synergies from their combinations. Advancing and integrating these technologies can enable a robust and efficient hypothesis-simulation-analysis type of scientific method, which we introduce with several use-cases for human-machine teaming and automated science.
  • [2]
    Robert Vautard, Andreas Gobiet, Daniela Jacob, Michal Belda, Augustin Colette, Michel Déqué, Jesús Fernández, Markel García-Díez, Klaus Goergen, Ivan
    • Güttler
  • [3]
    Elena Shevliakova, Ronald J. Stouffer, John P. Krasting, Sergey L. Malyshev, P. C. D. Milly, Lori T. Sentman, Alistair J. Adcroft
    • John P. Dunne
      ,
    • Jasmin G. John
  • [4]
    The benefits of global high resolution for climate simulation: Process understanding and the enabling of stakeholder decisions at the regional scale
    • M.J. Roberts
      ,
    • P.L. Vidale
      ,
    • C. Senior
      ,
    • H.T. Hewitt
      ,
    • C. Bates
    et al.
  • [5]
    and Pedro Mendes. Multi-scale modelling and simulation in systems biology. Integrative Biology, 3(2):86-96
    • Joseph O. Dada
  • [6]
    JP Grossman, Huafeng Xu, and David E Shaw. Biomolecular simulation: a computational microscope for molecular biology
    • Ron O. Dror
      ,
    • Robert M. Dirks
      • Ann.Rev.Biophys. 41 (2012) 429-452
  • [7]
    Yasmina Elshafei, Matthew
    • M. Tonts
  • [8]
    and Richard SJ Tol. Climate change and international tourism: a simulation study. Global environmental change, 15(3):253-266
    • Jacqueline M. Hamilton
      ,
    • David J. Maddison
  • [9]
    Wagner, Manvitha Ponnapati, and Christopher Rackauckas. Capturing missing physics in climate model parameterizations using neural differential equations. arXiv: Atmospheric and Oceanic Physics
    • Ali Ramadhan
      ,
    • J. Marshall
      ,
    • G. A. Souza
  • [10]
    Stephan Zheng, Alexander Trott, Sunil Srinivasa, Nikhil Naik, Melvin Gruesbeck, David Parkes, and R. Socher. The ai economist: Improving equality and productivity with ai-driven tax policies. ArXiv, abs/
  • [11]
    Phillip Colella. Defining Software Requirements for Scientific Computing
  • [12]
    c, R. Bodík
    • K. Asanov
  • [13]

    seven dwarfs

    • Erich L. Kaltofen
  • [14]
    Domain specific languages contextualized. In SAICSIT ’11
    • Michael H. Matthee
      ,
    • S.P. Levitt
  • [15]
    The rational analysis of memory
    • Samuel J. Gershman
  • [16]
    Tyler Cowen and Ben Southwood. Is the rate of scientific progress slowing down? SSRN Electronic Journal
  • [17]
    Jay Bhattacharya and Mikko Packalen. Stagnation and scientific incentives. PSN: Science & Technology (Topic)
  • [18]
    Ayya Alieva, Qing Wang, M
    • D. Kochkov
      ,
    • J.A. Smith
  • [19]
    Oliver
    • Hennigh
      ,
    • S. Narasimhan
      ,
    • M. Nabian
      ,
    • A. Subramaniam
      ,
    • K. Tangsali
    et al.
  • [20]
    and Lealem Mulugeta. The spectrum of mechanism-oriented models and methods for explanations of biological phenomena
    • C. Hunt
      ,
    • A. Erdemir
      ,
    • W. Lytton
      ,
    • F.M. Gabhann
      ,
    • E. Sander
    et al.
  • [21]
    Integrating machine learning and multiscale modeling—perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences. NPJ Digital Medicine, 2
    • M. Alber
      ,
    • A. Buganza Tepole
      ,
    • W. Cannon
      ,
    • S. De
      ,
    • S. Dura-Bernal
    et al.
  • [22]
    Model inversion via multi-fidelity bayesian optimization: a new paradigm for parameter estimation in haemodynamics, and beyond. Journal of The Royal Society Interface, 13
    • P. Perdikaris
      ,
    • G. Karniadakis
  • [23]
    Multi-fidelity classification using gaussian processes: accelerating the prediction of large-scale computational models. ArXiv, abs/
    • F.S. Costabal
      ,
    • P. Perdikaris
      ,
    • E. Kuhl
      ,
    • D. Hurtado
  • [24]
    Lu Lu, P. Perdikaris
    • G. Karniadakis
      ,
    • I. Kevrekidis
  • [25]
    Shengze Cai, Zhiping Mao, Zhicheng Wang, Minglang Yin, and G. Karniadakis. Physics-informed neural networks (pinns) for fluid mechanics: A review. ArXiv, abs/