Image Details

Choose export citation format:

Using Machine Learning to Identify Ultracool Dwarfs in Deep JWST Surveys

  • Authors: Julia Haynes, Adam J. Burgasser, Ming-Yang Zhuang, Yue Shen, Zhiwei Pan, Marylin Loritsch, Evan Pritchard, Emma Softich

Julia Haynes et al 2026 Research Notes of the AAS 10 .

  • Provider: AAS Journals

Caption: Figure 1.

(Panels (a) and (b)) Recall statistics for UCDs (a) and non-UCDs (b) for the models explored in this study. The RF and KNN models achieved the best performance with 100% UCD recall. (Panel (c)): Confusion matrix for the RF model with 1000× replication of UCDs and 100× replication of non-UCDs, 2:1 training balance, and PCA. (Panels (d)–(f)): NEXUS NIRSpec/Prism spectra of a correctly identified UCD (d), a non-UCD incorrectly identified as a UCD (e), and a correctly identified non-UCD (f). Spectra are normalized by the integrated flux, and uncertainties are plotted as blue lines.

Copyright and Terms & Conditions

Additional terms of reuse