Understanding atmospheric retrievals with machine learning

Presenter: Ingo WALDMANN
Analysing currently available observations of exoplanetary atmospheres often invoke large and correlated parameter spaces that can be difficult to map or constrain. This is true for both: the data analysis of observations as well as the theoretical modelling of their atmospheres. In many aspects, data mining and non-linearity challenges encountered in other data intensive fields are directly transferable to the field of extrasolar planets as well as planetary sciences.
In this talk, I will discuss the use of information entropy and deep learning to increase the efficiency of atmospheric retrieval algorithms and to exploit the sparsity of a low to mid-resolution exoplanet spectrum using information content informed optimal binning.