This is a late press release article for our Nature Astronomy paper. see this webpage for our original post https://www.madrimasd.org/blogs/talento-cm-uam/2022/10/17/194/, the news in Madrid Notiweb: https://www.madrimasd.org/inteligencia-artificial-proporciona-un-nuevo-metodo-medir-materia-oscura, in UAM website: https://www.uam.es/uam/investigacion/cultura-cientifica/noticias/inteligencia-artificial-materia-oscura and in UE website: https://www.ph.ed.ac.uk/news/2022/understanding-our-universe-with-the-help-of-machine-learning-22-10-20

Machine learning is a novel domain which uses artificial intelligence (AI) to make predictions with data. Artificial intelligence means teaching computers to learn to perform complex tasks, such as recognizing objects from pictures and playing chess. A lot of applications of ML appeared in many different fields of industry and research in recent years . It not only speeds up the process of efficiently dealing with a great amount of data but also brings new methods and new findings. An international group of people which includes experts in astronomy research from Universidad Autonoma de Madrid (Spain), University of Edinburgh (UK), MIT, Sapienza University (Italy) and experts in machine learning models from the Euranova company ( Belgium ) ,have started a collaboration to provide new ways to infer the mass of clusters of galaxies from multiwavelength images. Recently, they focused on accurate estimates of the mass of galaxy clusters from the Planck satellite microwave images. This study is published in the latest Nature Astronomy issue – https://www.nature.com/articles/s41550-022-01784-y

Galaxy clusters are the most massive object that ever formed in our universe, thus precisely measuring their masses has very important meanings for many different astronomy studies. While to get its mass from the observed images, astronomers have to first process the image, such as excluding fore/back-ground objects, and removing the noises; then, different assumptions have to be made to derive the mass from binned image quantities, such as profiles. These assumptions normally oversimplify the state of the real cluster, therefore, the mass derived with such methods doesn’t agree with their true mass. This difference is referred to as bias. Furthermore, the whole process is very time-consuming and the clusters have been handled one by one.

The machine learning method proposed by this group overcomes all these problems and can directly get the cluster mass from observed images. The machine learning model is based on one type of deep learning algorithm – the Convolutional Neural Networks (CNN), which can get the most important features of an image to connect with a defined quantity. A perfect tool for this task. However, this involves training the model with almost 200 thousand images from numerical simulations of galaxy clusters, for which the group used the results from The THREE HUNDRED project, hosted in UAM. They verified the cluster mass from the machine learning model has no bias and has a very small scatter around the true cluster mass. Applying this model to the images observed by the Planck satellite, they provided cluster masses of over 1000 galaxy clusters that are not affected by usual observational assumptions.

This work was mostly done by a PhD student Daniel de Andres from UAM. This paper’s co-leading author, Dr Weiguang Cui commented on the results as very exciting, and he further mentioned that ML is a useful tool which will help us understand our Universe.