Color classification of Earth-like planets with machine learning

Abstract

\n Atmospheric characterization of directly imaged exoplanets is currently limited to Giant planets and Mini-Neptunes. However, upcoming ground-based Extremely Large Telescopes (ELTs) and space-based concepts such as Origins, HabEx, and LUVOIR are designed to characterize rocky exoplanets. But spectroscopy of Earth-like planets is time-intensive even for upcoming telescopes; therefore, initial photometry has been discussed as a promising avenue to faster classify and prioritize exoplanets. Thus, in this article we explore whether photometric flux – using the standard Johnson filters – can identify the existence of surface-life by analysing a grid of 318\xa0780 reflection spectra of nominal terrestrial planets with 1 Earth radius, 1 Earth mass, and modern Earth atmospheres for varying surface compositions and cloud coverage. Because different kinds of biota change the reflection spectra, we assess the sensitivity of our results to six diverse biota samples including vegetation, representative of modern Earth, a biofilm as a way for microbes to survive extreme environments, and UV radiation resistant biota. We test the performance of several supervised machine-learning algorithms in classifying planets with biota for different signal-to-noise ratios: Machine-learning methods can detect the existence of biota using only the photometric flux of Earth-like planets’ reflected light with a balanced accuracy between 50\xa0per\xa0cent and up to 75\xa0per\xa0cent. These results assess the possibility that photometric flux could be used to initially identify biota on Earth-like planets and the trade-off between two critical results when classifying biota: false-positive and false-negative rates. Our spectra library is available online and can easily be used to test different filter combinations for upcoming missions and mission designs.