Welcome to astroNN’s documentation!

astroNN is a python package to do various kinds of neural networks with targeted application in astronomy by using Keras API as model and training prototyping, but at the same time take advantage of Tensorflow or PyTorch flexibility.

For non-astronomy applications, astroNN contains custom loss functions and layers which are compatible with Keras v3. The custom loss functions mostly designed to deal with incomplete labels. astroNN contains demo for implementing Bayesian Neural Net with Dropout Variational Inference in which you can get reasonable uncertainty estimation and other neural nets.

For astronomy applications, astroNN contains some tools to deal with APOGEE, Gaia and LAMOST data. astroNN is mainly designed to apply neural nets on APOGEE spectra analysis and predicting luminosity from spectra using data from Gaia parallax with reasonable uncertainty from Bayesian Neural Net. Generally, astroNN can handle 2D and 2D colored images too. Currently astroNN is a python package being developed by the main author to facilitate his research project on deep learning application in stellar and galactic astronomy using SDSS APOGEE, Gaia and LAMOST data.

For learning purpose, astroNN includes a deep learning toy dataset for astronomer - Galaxy10 DECaLS Dataset.

Acknowledging astroNN

Please cite the following paper that describes astroNN if astroNN is used in your research as well as linking it to https://github.com/henrysky/astroNN

Deep learning of multi-element abundances from high-resolution spectroscopic data [arXiv:1808.04428][ADS]

Here is a list of publications using astroNN - Publications using astroNN

Authors

• Henry Leung - Initial work and developer - henrysky

  Department of Astronomy & Astrophysics, University of Toronto

  Contact Henry: henrysky.leung [at] utoronto.ca
• Jo Bovy - Project Supervisor - jobovy

  Department of Astronomy & Astrophysics, University of Toronto

Indices, tables and astroNN structure

• Index

• Module Index

• Search Page

Datasets

• Galaxy10 DECaLS Dataset
• Galaxy10 SDSS Dataset

Basics of astroNN

• Getting Started
  • Prerequisites
  • Running on Google Colab
  • Basic FAQ
  • Configuration File
  • Dara Folder Structure and Environment Variables
• Contributor and Issue Reporting guide
  • Submitting bug reports and feature requests
  • Pull Request
  • New Model Proposal guide
  • Possible New Features and Improvement in the future
• Changelog
  • v1.2 series
  • v1.1 series
  • v1.0 series
  • v0.0 series
• Publications using astroNN
  • Publication figure style
• Loss Functions and Metrics
  • Correction Term for Magic Number
  • Mean Squared Error
  • Mean Absolute Error
  • Mean Error
  • Regression Loss and Predictive Variance Loss for Bayesian Neural Net
  • Mean Squared Logarithmic Error
  • Mean Absolute Percentage Error
  • Mean Percentage Error
  • Categorical Cross-Entropy
  • Binary Cross-Entropy
  • Categorical Cross-Entropy and Predictive Logits Variance for Bayesian Neural Net
  • Binary Cross-Entropy and Predictive Logits Variance for Bayesian Neural Net
  • Categorical Classification Accuracy
  • Binary Classification Accuracy
  • Zeros Loss
• Layers
  • Monte Carlo Dropout Layer
  • Monte Carlo Spatial Dropout Layer
  • Monte Carlo Gaussian Dropout Layer
  • Error Propagation Layer
  • KL-Divergence Layer for Variational Autoencoder
  • Mean and Variance Calculation Layer for Bayesian Neural Net
  • Repeat Vector Layer for Bayesian Neural Net
  • Fast Monte Carlo Integration Layer for Keras Model
  • Gradient Stopping Layer
  • Boolean Masking Layer
• Callbacks and Utilities
  • Virtual CSVLogger (Callback)
  • Raising Error on Nan (Callback)
  • Normalizer (Utility)
  • NumPy Implementation of Tensorflow function - astroNN.nn.numpy
• Neural Nets Classes and Basic Usage
  • Available astroNN Neural Net Classes
  • NeuralNetMaster Class API
  • Workflow of Setting up astroNN Neural Nets Instances and Training
  • Load astroNN Generated Folders
  • Load and Use Multiple astroNN Generated Folders
  • Workflow of Testing and Distributing astroNN Models
  • Creating Your Own Model with astroNN Neural Net Classes
  • NeuralNetMaster Class

NN Introduction and Demo

• Bayesian Neural Net with Dropout Variational Inference
  • Background Knowledge
  • Dropout Variational Inference
  • How is uncertainty calculated from neural network for regression task
  • A simple way to think about predictive, model and propagated uncertainty

• Uncertainty Analysis of Neural Nets with Variational Methods

• Galaxy10 Notebook

• Variational AutoEncoder with simple 1D data demo

APOGEE/Gaia/LAMOST Tools and models

• Mini Tools for APOGEE data
  • Continuum Normalization of APOGEE Spectra
  • Basics Tools related to APOGEE Spectra
  • APOGEE Data Downloader
• Mini Tools for LAMOST data
  • LAMOST Spectra Wavelength Solution
  • Pseudo-Continuum Normalization of LAMOST Spectra
  • Load LAMOST DR5 catalogue
• Mini Tools for Gaia data
  • fakemag (dummy scale)
  • Conversion Tools related to Astrometry and Magnitude
  • Coordinates Matching between catalogs xmatch
• APOGEE Spectra with Convolutional Neural Net - ApogeeCNN
  • ApogeeCNN
  • Example Plots using aspcap_residue_plot
  • ASPCAP labels prediction using CNN vs The Cannon 2
  • Example Plots using jacobian
• APOGEE Spectra with Bayesian Neural Net - ApogeeBCNN
  • ApogeeBCNN
  • ASPCAP Labels Prediction
  • ASPCAP Labels Prediction with >50% corrupted labels
  • ASPCAP Labels Prediction with limited amount of data
  • Example Plots using aspcap_residue_plot
  • Example Plots using jacobian
• APOGEE Spectra with Censored Bayesian NN - ApogeeBCNNCensored
  • ApogeeBCNNCensored
  • Architecture
  • Why Censored NN for APOGEE Spectra analysis?
  • ASPCAP Labels Prediction
• APOGEE Spectra with Bayesian NN and Gaia offset calibration - ApogeeDR14GaiaDR2BCNN
  • ApogeeDR14GaiaDR2BCNN
  • Architecture
• Convolutional Variational Autoencoder - ApogeeCVAE
  • ApogeeCVAE
  • APOGEE Spectra Analysis
  • Example Plots on latent space using VAE.plot_latent()
  • Example Plots on spectra reconstruction
• Encoder-decoder for APOGEE and Kepler - ApokascEncoderDecoder
  • ApokascEncoderDecoder
• StarNet (arXiv:1709.09182)
  • StarNet2017
• Cifar10 with astroNN