Figure 5 from Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates

Image Details

View Article Bookmark & Share

Choose export citation format:

Export Citation

Hi-Resolution Export to PDF PPT Format

Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates

Authors: Liang Yu, Andrew Vanderburg, Chelsea Huang, Christopher J. Shallue, Ian J. M. Crossfield, B. Scott Gaudi, Tansu Daylan, Anne Dattilo, David J. Armstrong, George R. Ricker, Roland K. Vanderspek, David W. Latham, Sara Seager, Jason Dittmann, John P. Doty, Ana Glidden, and Samuel N. Quinn

2019 The Astronomical Journal 158 25.

Provider: AAS Journals

Caption: Figure 5.

Histogram of predictions on the test set by AstroNet-Triage (top) and AstroNet-Vetting (bottom). The color of each bar represents the fraction of TCEs in that bin that are actually positives (PCs and EBs in triage mode, and just PCs in vetting mode). A yellow bin contains mostly TCEs that are positives, while a blue bin contains mostly negatives. The red dashed line marks a classification threshold of 0.1, which we find to maximize the fraction of false positives eliminated while still retaining almost all of the PCs.

Other Images in This Article

Copyright and Terms & Conditions