Retrieving exoplanet atmospheric parameters using random forest regression

Understanding of exoplanet atmospheres can be extracted from the transmission spectra using an important tool based on a retrieval technique. However, the traditional retrieval method (e.g. MCMC and nested sampling) consumes a lot of computational time. Therefore, this work aims to apply the random forest regression, one of the supervised machine learning technique, to retrieve exoplanet atmospheric parameters from the transmission spectra observed in the optical wavelength. We discovered that the random forest regressor had the best accuracy in predicting planetary radius (R_Fit² = 0.999) as well as acceptable accuracy in predicting planetary mass, temperature, and metallicity of planetary atmosphere. Our results suggested that the random forest regression consumes significantly less computing time while gives the predicted results equivalent to those of the nested sampling PLATON retrieval.