Machine learning represents a breakthrough in the study of stellar nurseries

Artificial intelligence can make it possible to see astrophysical phenomena that were previously out of reach. This has now been demonstrated by scientists from CNRS, IRAM, Observatoire de Paris-PSL, Ecole Centrale Marseille and Ecole Centrale Lille, who work together in the ORION-B program. In a series of three articles published in Astronomy and astrophysics on November 19, 2020, present the most comprehensive observations made to date of one of the closest star-forming regions to Earth.

The gas clouds in which stars are born and evolve are vast regions extremely rich in matter, and therefore in physical processes. All of these processes are intertwined at different sizes and time scales, making it nearly impossible to fully understand such stellar nurseries. However, scientists from the ORION-B program have now shown that statistics and artificial intelligence can help break down the barriers that still stand in the way of astrophysicists.

Aiming to provide the most detailed analysis to date of the Orion molecular cloud, one of the closest star-forming regions to Earth, the ORION-B team has included scientists specializing in massive data processing among its ranks. . This allowed them to develop new statistical learning and machine learning-based methods to study cloud observations made at 240,000 light frequencies.

Based on artificial intelligence algorithms, these tools allow you to retrieve new information from a large mass of data such as that used in the ORION-B project. This allowed scientists to discover a number of characteristics that govern the Orion molecular cloud.

For example, they were able to discover the relationships between the light emitted by certain molecules and previously inaccessible information, i.e. the amount of hydrogen and free electrons in the cloud, which they were able to estimate from their calculations without directly observing them. By analyzing all the data at their disposal, the research team was also able to determine ways to further improve their observations by eliminating a certain amount of unwanted information.

The ORION-B teams now wish to put this theoretical work to the test by applying the estimates and recommendations obtained and verifying them under real conditions. Another big theoretical challenge will be extracting information about the speed of molecules and then visualizing the movement of matter to see how it moves inside the cloud.