| |
 |
| Paper: |
Developing an Efficient and Modular Large-Scale Machine Learning Pipeline to Classify Millions of NASA TESS Light Curves in Search of Variable Stars |
| Volume: |
541, ADASS XXXIII |
| Page: |
181 |
| Authors: |
Jeroen Audenaert; Marc Hon; Rahul Jayaraman; Michelle Kunimoto; Andrew Tkachenko; Derek Buzasi; Mikkel Lund; George Ricker; The T’DA Collaboration |
| DOI: |
10.26624/RXGX7087 |
| Abstract: |
The Transiting Exoplanet Survey Satellite (TESS) is observing millions
of stars each month. The large number of light curves that are being generated from
these photometric observations contain a wealth of information for studying stellar pulsations, rotation, and binarity. However, in order to be able to use these observations for
stellar structure and evolution studies, we first need to be able to identify the light curves
with the relevant type of stellar variability from this massive data set. The TESS Data
for Asteroseismology (T’DA) working group has therefore created an automated open-source machine learning (ML) pipeline to classify the millions of light curves delivered
by TESS according to their stellar variability types. The pipeline is highly parallelized
and has been optimized for large-scale computing infrastructures. Furthermore, it has
been developed in a modular way such that new state-of-the-art classifiers in search for
new variability types can easily be added. In this contribution, we present the pipeline
and structure of the ML classifiers, and explore how they can be used for other space
missions and ground-based surveys. |
|
|
|
|
|
