June 6, 2025

Where to find the next Earth

How can the search for Earth like exoplanets at moderate temperatures advance
A machine learning model could push the search for extrasolar planets.
Credit:

Universität Bern, Illustration: Thibaut Roger

DownloadDownload

Jeanne Davoult has been working in the Department of Extrasolar Planets and Atmospheres at the DLR-Institute of Space Research since the beginning of the year. As part of her doctoral thesis at the University of Bern, she developed a machine learning model that can predict potential planetary systems with Earth-like planets.

A machine learning model is a statistical tool that is trained with data to recognise certain patterns and make predictions. Jeanne Davoult explains: ‘Our model is based on an algorithm that I developed and that has been trained to recognise and classify planetary systems that host Earth-like planets.’ The model builds on previous studies to derive a correlation between the presence or absence of an Earth-like planet and the properties of its planetary system.

In April 2025, she and her colleagues from the University of Bern published the results in the journal Astronomy & Astrophysics.

Read more in the University of Bern's press release of 9 April 2025: Where the next Earth could be found (also available in German and French)

Link to the publication in A&A: An Earth-like planets predictor: A Machine Learning Approach by Jeanne Davoult, Romain Eltschinger and Yann Alibert