Image Details

Choose export citation format:

Application of Convolutional Neural Networks to Identify Stellar Feedback Bubbles in CO Emission

  • Authors: Duo Xu, Stella S.R. Offner, Robert Gutermuth, and Colin Van Oort

2020 The Astrophysical Journal 890 64.

  • Provider: AAS Journals

Caption: Figure 9.

Relation between the CNN-predicted bubble mass and the true feedback mass for different bubbles. The filled symbols indicate the mass calculated from model MF. The open symbols represent the mass calculated from model ME1. The black dashed line indicates where the CNN correctly predicts the true mass as determined by the tracer field and gas temperature. The blue dashed line has a slope of 3, and the red dashed line has a slope of 10. The physical parameters of the simulations with different labels are listed in Offner & Arce (2015).

Other Images in This Article

Show More

Copyright and Terms & Conditions