Habitability classification of exoplanets: a machine learning insight

We explore the efficacy of machine learning (ML) in characterizing exoplanets into different classes. The source data used this work is University Puerto Rico’s Planetary Habitability Laboratory’s Exoplanets Catalog (PHL-EC). perform a detailed analysis structure and propose methods that can be to effectively categorize new exoplanet samples. Our contributions are twofold. elaborate on results obtained by using ML algorithms stating accuracy each method paradigm automate task classification for relevant outcomes. In particular, we focus novel neural network architectures task, as they have performed very well despite complexities inherent problem. exploration led development fundamental context problem beyond. experimentation also result general methodology set best practices which exploratory experiments.