At the University of Bern, Switzerland, astrophysicists of the Center for Space and Habitability (CSH) have teamed up with medical technology researchers to develop a new method to analyse a spectrum of atmospheres beyond our Solar System.
This collaboration between astrophysicists and medical technology researchers applied an artificial intelligence tool to study the chemistry of exoplanetary atmospheres.
Machine learning is a branch of artificial intelligence in most modern science and technology innovations that gives computers the ability to learn from data without being explicitly programmed.
Raphael Sznitman, Professor at the ARTORG Center for Biomedical Engineering Research and his group are using machine learning to control surgical tools during operations on the eye and detect biomarkers for disease identification from images. Revolutionising many fields of science, machine learning is also becoming ubiquitous in astronomy, but it is not yet used in the study of the atmospheres of exoplanets.
Kevin Heng, director of the CSH, said: “The way Raphael Sznitman and his team look at images is very similar to the way astronomers are analysing images and we even speak roughly the same technical language.
“Whether in astronomy or medical technology, we always try to understand the flaws of imaging technologies and improve them.”
Pragmatism and realism
In astronomy, light from an object is taken and split into the different colours to get a spectrum. The spectrum of an exoplanet contains hidden information about the molecules present in its atmosphere, the physical conditions, and the amount of clouds.
By analysing and interpreting the spectrum the astronomer can, for instance, find water in a planet’s atmosphere and determine its habitability. The current standard approach is to search amongst a large family of model spectra that best fits the data from the exoplanet, which is a very time-consuming process and leaves room for human misjudgement.
A research team from CSH developed a new technique to simplify this approach. They devised a way to compute a large grid of models, and then use it as a training set for the machine learning procedure. With the help of this data, the computer learns to determine the composition of the exoplanetary atmosphere from a spectrum.
This method is a supervised form of machine learning which is usually used to classify objects in images. Sznitman said: “Based on the data, the computer learns whether a particular object is present in an image or not. Since the process consists of many such decision trees, it is called ‘random forest’.”
To demonstrate the method, the astrophysicists picked the exoplanet WASP-12b as an example – a Jupiter-sized planet with a temperature of more than 1,000°C. The computer had to look for patterns in the observed spectrum.
The collaboration will continue and should also help to solve medical problems.