Artificial Intelligence is an increasingly concrete reality even in the field of astrophysics and this is demonstrated by the new algorithm, called Mela, which has learned to correctly weigh galaxies by measuring their mass starting from simulations of the formation and evolution of the universe .
The result is online on the arXiv platform and is being published in the journal Astronomy & Astrophysics. It was obtained by an international group of researchers led by the Chinese Sun Yat-sen University, in which the National Institute of Astrophysics also participated.
“We asked Mela to show us how he obtained his results and which data were most important in arriving at his conclusions,” says Nicola Napolitano of Sun Yat-sen University, former INAF researcher and now professor at Federico University II of Naples, co-author of the study led by Sirui Wu.
“The amazing thing is that we realized that the algorithm can understand the physics of gravity.
Apple can use the physical laws we know – continues Napolitano – but soon Artificial Intelligence will also be able to learn the physics we don't know”.
The study demonstrated for the first time that the developed methodology also works with real galaxies.
The researchers in fact compared the estimates made by Mela with those obtained through classical procedures: the results indicate that AI is able to calculate the masses of galaxies extremely accurately, using much simpler data and much less laborious methods.
“The work was possible thanks to a path undertaken by our group – adds Crescenzo Tortora of INAF in Naples, one of the authors of the study – which in recent years has extended the applications of AI to various sectors of large data analysis astronomical investigations".
Reproduction reserved © Copyright ANSA