Abstract
The discovery of planets apart from Earth that can sustain lives has always been fascinating as well as challenging. Discussion around such planets, popularly termed as "Exoplanets" have been doing the rounds for quite some time now. These exoplanets are often considered to be "Earth-like" or "habitable" because they may have conditions that could potentially support life. This work focuses on how Deep Learning techniques can be useful in identifying potential exoplanets. To do so, astronomical data gathered by space telescopes such as Kepler and BRITE have been utilized. The method employed to detect exoplanets is Transit Photometry along with Convolutional Neural Network. The study highlights the limitations of small training datasets and suggests the use of data augmentation techniques to increase the size of the training dataset, and the transfer learning approach to improve the performance of the classification models. The research offers valuable insights into the nature and diversity of exoplanets and may open avenues for future discoveries. With a performance accuracy of 96.67%, the proposed approach showcases merit and hence can prove to be a harbinger in exploring planetary habitability in the colossal space.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have