Dreaming of atmospheres

TL;DR

This paper introduces RobERt, a deep neural network-based algorithm that automatically recognizes molecular signatures in exoplanetary emission spectra, reducing manual input and biases in atmospheric retrievals.

Contribution

The paper presents RobERt, a novel deep belief neural network approach for automatic molecular recognition in exoplanet spectra, enhancing retrieval accuracy and automation.

Findings

RobERt accurately recognizes molecular signatures across diverse exoplanet atmospheres.

The learned features ('dreams') show good convergence and faithful molecular representation.

The algorithm reduces manual preselection, minimizing biases in spectral retrievals.

Abstract

Here we introduce the RobERt (Robotic Exoplanet Recognition) algorithm for the classification of exoplanetary emission spectra. Spectral retrievals of exoplanetary atmospheres frequently requires the preselection of molecular/atomic opacities to be defined by the user. In the era of open-source, automated and self-sufficient retrieval algorithms, manual input should be avoided. User dependent input could, in worst case scenarios, lead to incomplete models and biases in the retrieval. The RobERt algorithm is based on deep belief neural (DBN) networks trained to accurately recognise molecular signatures for a wide range of planets, atmospheric thermal profiles and compositions. Reconstructions of the learned features, also referred to as `dreams' of the network, indicate good convergence and an accurate representation of molecular features in the DBN. Using these deep neural networks, we work towards retrieval algorithms that themselves understand the nature of the observed spectra, are able to learn from current and past data and make sensible qualitative preselections of atmospheric opacities to be used for the quantitative stage of the retrieval process.