Analysis of Kepler light curves using the wavelet transform to discriminate with machine learning the astrophysical nature of the eclipsing object.

The Kepler mission has been the most successful so far in the search for and characterization of exoplanets using the transit technique. With this method, the intensity of light emitted by the star is measured at regular intervals to detect periodically recurring photometric reductions in the star, from which the presence of an eclipsing object can be inferred.

The wavelet transform has been used as an alternative to the Fourier transform in noise filtering in astronomical photometric data, as well as in the detection of exoplanet transits. We propose a new approach based on the use of the wavelet transform as a mathematical tool to establish statistical criteria for the characterization of the eclipsing object, in order to differentiate exoplanets from false positives, with the aim that the results obtained can be used to train a ML model to automatically analyze thousands of light curves Kepler and  K2 missions.