Since the initial identification of exoplanets (planets located outside our Solar System) in the 1990s, and the first detection of a planetary transit in 2000, the transit technique for detecting planets has been widely used by several space observatories, such as Kepler and TESS. By observing transits in the luminosity of an exoplanet’s host star, it is possible to deduce some parameters of the planet, such as its radius, orbital inclination, and orbital semi-axis. However, a host star can exhibit active regions on its surface, which cause small fluctuations in luminosity when the planet passes in front of these spots. These variations in the light curves during the transit result in a less precise and even underestimated determination of the planetary parameters. Therefore, it is essential to employ techniques for analyzing and modeling these starspots to more accurately estimate the characteristics of exoplanets, taking into account the changes caused by the star’s activity. In this project, a set of Python programs was developed to calibrate, analyze, and model the variations in light curves due to the presence of active regions and fluctuations on their surface, with the aim of improving the accuracy of planetary and orbital parameters, as well as the correlation between impacts suffered by the planet’s atmosphere and stellar activity.

GANexo v2.0 extends our previous framework for exoplanet transit analysis by moving from synthetic signal generation to direct application on real observational data. The new version combines autoencoder-based noise reduction with Generative Adversarial Network (GAN) models, specifically a conditional GAN (cGAN) used for regression, to extract key transit parameters from noisy light curves. This integration improves robustness against observational noise, enhances parameter estimation accuracy, and provides a reliable AI-driven tool specially for ground-based exoplanet studies.

This resource was developed to help bring this exciting area of research into the classroom. It consists of two practical activities appropriate for the K12 curriculum.

Each of the activities is standalone, takes around 60 minutes to complete and can be used either during lessons or as part of a science club. Each offers plenty of opportunity for extension work and includes a taking it further section to allow students to build on what they have learnt through independent research. The activities can be used individually, or in combination. We have already implemented them during the astrophysics summer courses we offer to school students at the National Observatory of Athens, with great success.