Image Details

Choose export citation format:

A Machine Learning Approach to Exoplanet Atmospheric Retrieval: Application to Optical Filter Ranking

  • Authors: Patcharawee Munsaket, Supachai Awiphan, Poemwai Chainakun, Eamonn Kerins, Napaporn A-thano

Patcharawee Munsaket et al 2026 The Astronomical Journal 172 .

  • Provider: AAS Journals

Caption: Figure 8.

An example of the filter ranking for the second-stage model corresponding to planets with radii between 0.8 and 1.0 RJ. The process begins with 10 features: a transit depth for each of the 10 filters. The x-axis shows the filter elimination steps, starting with 10 features on the left and proceeding until only the last two filters remain. Each step removes the filter with the lowest feature-importance score, and the remaining filters define the ranking. From this result, the filter ranking for the optical observation of this planet size is V, ﹩{u}^{{\prime} }﹩, ﹩{z}^{{\prime} }﹩, B, ﹩{i}^{{\prime} }﹩, ﹩{r}^{{\prime} }﹩, I, ﹩{g}^{{\prime} }﹩, U, and R.

Other Images in This Article

Show More

Copyright and Terms & Conditions

Additional terms of reuse