Just a few words about the project. The ExoAI project is funded by the European Research Council (project: 758892) to explore the use of machine learning and deep learning to the data analysis and interpretation of exoplanetary data. The project started at the beginning of 2018 and will formally run until 2023.
In the last two and a half decades, we have undergone what is best described as a second Copernican revolution. The discovery of extrasolar planets - i.e. planets orbiting other stars - has fundamentally transformed our understanding of planets, solar systems, their formation histories and our place in the grander scheme of the Milky Way.
The field of exoplanetary spectroscopy is as fast moving as it is new. 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. Modelling both sets of correlations in data and modelling is key to understanding the nature of exoplanet atmospheres.
The fields of deep learning and machine learning have recently revolutionised many fields of science and industry. This project is trying to do the same for extrasolar planets by making current algorithms more precise and more generally applicable. Exoplanets have truly moved into an era of big-data, with future space missions and ground based surveys bringing a wealth of data. By adopting a holistic approach and look at, say, all data ever taken by an instrument, it becomes possible to gain a new and improved understanding of how to calibrate the instrument. Deep learning is ideally suited for this task.
The team is currently in the making but will be a very interdisciplinary in nature, ranging from machine learning experts to more classical planetary sciences, in order to bridge the interdisciplinary divide.