exoplanet-ml's Introduction

Exoplanet ML

Machine learning models and utilities for exoplanet science.

Code Author

Chris Shallue: @cshallue

Walkthrough

You can jump straight to the AstroNet walkthrough.

Otherwise, click through to the desired directory as outlined below.

Directories

astronet/

A neural network for identifying exoplanets in light curves. Contains code for:
- Downloading and preprocessing Kepler light curves.
- Building different types of neural network classification models.
- Training and evaluating a new model.
- Using a trained model to generate new predictions.

astrowavenet/

A generative model for light curves.

light_curve/

Utilities for operating on light curves. These include:
- Reading Kepler data from .fits files.
- Applying a median filter to smooth and normalize a light curve.
- Phase folding, splitting, removing periodic events, etc.
light_curve/fast_ops/ contains optimized C++ light curve operations.

tf_util/

Shared TensorFlow utilities.

third_party/

Utilities derived from third party code.

Setup

Required Packages

TensorFlow (instructions)
Pandas (instructions)
NumPy (instructions)
SciPy (instructions)
AstroPy (instructions)
PyDl (instructions)
Bazel (instructions)
Abseil Python Common Libraries (instructions)

Run Unit Tests

Verify that all dependencies are satisfied by running the unit tests:

cd exoplanet-ml  # Bazel must run from a directory with a WORKSPACE file
bazel test astronet/... astrowavenet/... light_curve/... tf_util/... third_party/...

Citation

If you find this code useful, please cite our paper:

Shallue, C. J., & Vanderburg, A. (2018). Identifying Exoplanets with Deep Learning: A Five-planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90. The Astronomical Journal, 155(2), 94.

Full text available at The Astronomical Journal.