ASCL.net

Astrophysics Source Code Library

Making codes discoverable since 1999

ASCL Code Record

[ascl:2406.015] FLORAH: Galaxy merger tree generator with machine learning

FLORAH generates the assembly history of halos using a recurrent neural network and normalizing flow model. The machine-learning framework can be used to combine multiple generated networks that are trained on a suite of simulations with different redshift ranges and mass resolutions. Depending on the training, the code recovers key properties, including the time evolution of mass and concentration, and galaxy stellar mass versus halo mass relation and its residuals. FLORAH also reproduces the dependence of clustering on properties other than mass, and is a step towards a machine learning-based framework for planting full merger trees.

Code site:
https://github.com/trivnguyen/florah
Described in:
https://ui.adsabs.harvard.edu/abs/2023arXiv230805145N
Bibcode:
2024ascl.soft06015N

Views: 413

ascl:2406.015
Add this shield to your page
Copy the above HTML to add this shield to your code's website.