Learning Everywhere: A Taxonomy for the Integration of Machine Learning and Simulations
This provides a systematic overview for researchers working on ML-simulation integration, but it is incremental as it organizes existing work rather than introducing new methods.
The paper tackles the problem of categorizing research on machine learning applied to simulations by presenting a taxonomy covering eight patterns and three algorithmic areas, resulting in a structured framework for integration.
We present a taxonomy of research on Machine Learning (ML) applied to enhance simulations together with a catalog of some activities. We cover eight patterns for the link of ML to the simulations or systems plus three algorithmic areas: particle dynamics, agent-based models and partial differential equations. The patterns are further divided into three action areas: Improving simulation with Configurations and Integration of Data, Learn Structure, Theory and Model for Simulation, and Learn to make Surrogates.