A Caltech Library Service

Simulation Intelligence: Towards a New Generation of Scientific Methods

Lavin, Alexander and Zenil, Hector and Paige, Brooks and Krakauer, David and Gottschlich, Justin and Mattson, Tim and Anandkumar, Anima and Choudry, Sanjay and Rocki, Kamil and Baydin, Atılım Güneş and Prunkl, Carina and Isayev, Olexandr and Peterson, Erik and McMahon, Peter L. and Macke, Jakob and Cranmer, Kyle and Zhang, Jiaxin and Wainwright, Haruko and Hanuka, Adi and Veloso, Manuela and Assefa, Samuel and Zheng, Stephan and Pfeffer, Avi (2021) Simulation Intelligence: Towards a New Generation of Scientific Methods. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Anandkumar, Anima0000-0002-6974-6797
Baydin, Atılım Güneş0000-0001-9854-8100
McMahon, Peter L.0000-0002-1177-9887
Additional Information:The authors would like to thank Tom Kalil and Adam Marblestone for their support, Joshua Elliot and Josh Tenenbaum for fruitful discussions, Sam Arbesman for useful reviews. The authors declare no competing interests.
Subject Keywords:Simulation; Artificial Intelligence; Machine Learning; Scientific Computing; Physics-infused ML; Inverse Design; Human-Machine Teaming; Optimization; Causality; Complexity; Open-endedness
Record Number:CaltechAUTHORS:20220714-224632616
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:115601
Deposited By: George Porter
Deposited On:15 Jul 2022 23:18
Last Modified:15 Jul 2022 23:18

Repository Staff Only: item control page