Most of the exoplanets discovered so far have been discovered by applying the transit technique. This technique is based on a tiny eclipse caused when a planet moves in front of its star. The decrease in luminosity detected makes it possible to infer the presence of a planet and to guess its diameter, after occasional verification of the observations.
However, the theory believes that in several planetary systems, interactions between planets modify this periodicity and make their discovery impossible. It is in this context that a team of astronomers from the University of Geneva (UNIGE), the University of Bern (UniBE) and PRN PlanetS, Switzerland, in partnership with the company Disaitek, used artificial intelligence (AI) applied to image recognition.
They programmed a machine to estimate the effect of interactions between planets, making it possible to identify exoplanets that were previously difficult to detect. Details of the tools developed have been published in the journal Astronomy and astrophysics. The tools could also be used on Earth to detect garbage dumps and illegal dumps.
Discovering a planet through the transit technique is a long process. Detecting the signal produced by the small planets in the data can be difficult, if not unthinkable with the usual methods, in the case where the interactions between planets modify the periodicity of the transit occurrence. To overcome this challenge, it is essential to create tools that can take this effect into consideration.
This is why we thought of using artificial intelligence applied to image recognition.
Adrien Leleu, Researcher, Department of Astronomy, Faculty of Sciences, UNIGE
Adrien Leleu is also a researcher at PRN PlanetS.
It is possible to teach a machine, from numerous examples, to take into consideration all the factors and to estimate the effect of the interactions between planets in a graphical representation of the induced effect. To achieve this, astronomers have partnered with Disaitek through the PRN technology and innovation platform.
An artificial neural network capable of identifying objects
The type of AI used in this project is a neural network whose goal is to determine, for each pixel of an image, the object it represents.
Anthony Graveline, President, Disaitek
Used from the perspective of an autonomous vehicle, this algorithm makes it possible to identify the road, signs, pavement and pedestrians observed by the camera. With regard to the detection of exoplanets, it is a question of establishing, for each measurement of the luminosity of the star, if the eclipse of a planet is perceived.
Decisions are made by the neural network by crossing all the accessible observations of this star with the variety of configurations observed during its formation.
From the first implementations of the method, we discovered two exoplanets – Kepler-1705b and Kepler-1705c – which had been completely missed by previous techniques.
Adrien Leleu, Researcher, Department of Astronomy, Faculty of Sciences, UNIGE
The planetary systems thus discovered are a gold mine for knowledge relating to exoplanets, and more mainly to terrestrial planets, which are largely difficult to define. The technique formulated not only makes it possible to predict the radius of the planets, but also offers data on their mass, and therefore on their composition and density.
The use of AI, in particular of “deep learning” as in this article, is becoming more and more general in astrophysics, whether it is to process observational data, as we have done here, or to analyze the results of gigantic digital simulations producing terabytes of data.
Yann Alibert, professor, University of Bern
“What we have developed in this study is yet another example of the fantastic contribution these techniques can make to our field, and possibly to all areas of research,” Yann Alibert added.
Yann Alibert is also the Scientific Manager of PRN PlanetS.
Technology for Earth Observation
If this method is effective for astronomical explorations, it can also be just as beneficial for the study of the Earth and its environment.
“In developing this technology, we quickly realized its potential for application to other problems for which a small amount of data is available. explains Grégory Châtel, R&D Manager at Disaitek.
Using very high-resolution satellite imagery, Disaitek is currently using this AI to deal with environmental issues, specifically to find illegal landfills. This threat, which continues to grow, has no clear solution with traditional approaches.
Journal reference:
Leleu, A., et al. (2021) Attenuation of transit time variation bias in public transport surveys. I. RIVERS: Method and detection of a pair of resonant super-Earths around Kepler-1705. Astronomy and astrophysics. doi.org/10.1051/0004-6361/202141471.
Source: https://www.unige.ch
