Skip to content
/ exonet Public
forked from ebasanez/exonet

Exo-planet detection using a Convolutional Neural Network

Notifications You must be signed in to change notification settings

ponykid/exonet

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Exonet

Planet detection using Convolutional Neural Networks

Authors:

  • Robert Austin Benn
  • Enrique Basañez Mercader
  • Miguel Blanco Marcos
  • Borja Sánchez Leirado

Objective

Analyze state-of-the-art research about planet detection using transit method (see https://en.wikipedia.org/wiki/Methods_of_detecting_exoplanets) and use advanced machine learning techniques to enble further discoveries.

Pipeline

For this project pipeline, different modules are used:

Raw data retrieval

Module scr/com/saturdaysai/exonet/lightKurveApi/lightKurveApiCLient.py

Raw data will be obtained from Kepler records stored at MAST (Mikulski Archive for Space Telescopes) using Python library LightKurve to access their api. https://archive.stsci.edu/mast.html

https://docs.lightkurve.org/

Data preprocessing

Raw data obtained have informatioon about transit period, duration and centroid.

Using that information, data will be normalized and re-sampled to fixed length to generate one-dimensional tensors.

Model definition

Notebook notebooks/model_definition.ipynb

This notebook uses tensors generated (and stored in /data folder) to define and optimize a CNN based model. Hyper-parameters present in this notebook are the result of iterative training.

Model validation

Notebook notebooks/model_evaluation.ipynb

Loads model defined in previous step and validates it using validation sub-dataset, obtaining cross-entropy loss, accuracy, AUC, and precision vs recall curve.

Production stage

Notebook notebooks/model_predictions.ipynb

Predictions will be made using Kepler Objects of Interest which have candidates of being exo-planets, ordering those by decreasing likelihood of having a light curve that evidences the presence of an exoplanet.

External links

Article in Medium: https://medium.com/@miguel.blanco.marcos/exonet-an-ai-saturdays-project-a1bda907bdef

Inspired in: Shallue, Christopher J., and Andrew Vanderburg. “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 (2018): 94. Crossref. Web. (DOI: 10.3847/1538-3881/aa9e09)

About

Exo-planet detection using a Convolutional Neural Network

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.5%
  • Python 0.5%