Follow the water: finding water, snow, and clouds on terrestrial exoplanets with photometry and machine learning

All life on Earth needs water. NASA's quest to follow the water links water to the search for life in the cosmos. Telescopes like the James Webb Space Telescope and mission concepts like HabEx, LUVOIR, and Origins are designed to characterize rocky exoplanets spectroscopically. However, spectroscopy remains time-intensive, and therefore, initial characterization is critical to prioritization of targets. Here, we study machine learning as a tool to assess water's existence through broad-band filter reflected photometric flux on Earth-like exoplanets in three forms: seawater, water-clouds, and snow; based on 53 130 spectra of cold, Earth-like planets with six major surfaces. XGBoost, a well-known machine-learning algorithm, achieves over 90 per cent balanced accuracy in detecting the existence of snow or clouds for S/N ≳ 20, and 70 per cent for liquid seawater for S/N ≳ 30. Finally, we perform mock Bayesian analysis with Markov chain Monte Carlo with five filters identified to derive exact surface compositions to test for retrieval feasibility. The results show that the use of machine learning to identify water on the surface of exoplanets from broad-band filter photometry provides a promising initial characterization tool of water in different forms. Planned small and large telescope missions could use this to aid their prioritization of targets for time-intense follow-up observations.