ASCL.net

Astrophysics Source Code Library

Making codes discoverable since 1999

ASCL Code Record

[ascl:2503.013] ExoMDN: Rapid characterization of exoplanet interiors with Mixture Density Networks

Given mass, radius, and equilibrium temperature, ExoMDN can deliver a full posterior distribution of mass fractions and thicknesses of each planetary layer. A machine-learning model for the interior characterization of exoplanets based on Mixture Density Networks (MDN), ExoMDN is trained on a large dataset of more than 5.6 million synthetic planets below 25 Earth masses. These synthetic planets consist of an iron core, a silicate mantle, a water and high-pressure ice layer, and a H/He atmosphere. ExoMDN uses log-ratio transformations to convert the interior structure data into a form that the MDN can easily handle.

Code site:
https://github.com/philippbaumeister/ExoMDN
Used in:
https://ui.adsabs.harvard.edu/abs/2025arXiv250302451D
Described in:
https://ui.adsabs.harvard.edu/abs/2023A%26A...676A.106B
Bibcode:
2025ascl.soft03013B

Views: 12

ascl:2503.013
Add this shield to your page
Copy the above HTML to add this shield to your code's website.