StelNet: Stellar mass and age predictor
Abstract
StelNet predicts mass and age from absolute luminosity and effective temperature for stars with close to solar metallicity. It uses a Deep Neural Network trained on stellar evolutionary tracks. The underlying model makes no assumption on the evolutionary stage and includes the pre-main sequence phase. A mix of models are trained and bootstrapped to quantify the uncertainty of the model, and data is through all trained models to provide a predictive distribution from which an expectation value and uncertainty level can be estimated.
- Publication:
-
Astrophysics Source Code Library
- Pub Date:
- August 2021
- Bibcode:
- 2021ascl.soft08014G
- Keywords:
-
- Software