Skip to content

Neural network emulation of Stellar Population Synthesis (SPS) models for galaxy spectra and photometry

License

Notifications You must be signed in to change notification settings

justinalsing/speculator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

57 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Speculator

This repository contains the code for neural network emulation of stellar population synsthesis (SPS) models for galaxy spectra, associated with the paper Alsing et. al 2019, arXiv 1911.11778. If you use this code, kindly cite that paper.

install and dependencies

You can install the code with pip: pip install git+https://github.com/justinalsing/speculator.git

The code is in python3 and has the following dependencies:
tensorflow (>2.0)
scikit-learn
numpy

demo

A basic demo of loading and calling a pre-trained model (Prospector-alpha) can be found in examples/speculator_demo.ipynb. For training your own model, you can use the template given in examples/speculator_training_demo.ipynb.

updates and collaboration

We will be expanding this repository with additional models and demonstrations of how to train your own models. Meanwhile, if you require a particular model or would like to collaborate on building an SPS emulator for a particular case/project, feel free to get in touch at justin.alsing@fysik.su.se

About

Neural network emulation of Stellar Population Synthesis (SPS) models for galaxy spectra and photometry

Resources

License

Stars

Watchers

Forks

Packages

No packages published