A supernova is the biggest cosmic explosion that humans have ever seen. Each blast is the extremely bright, super-powerful explosion of a star. A dying massive star can cause a supernova. This happens when a star at least five times the mass of our sun goes out with fantastic bang. Massive stars burn huge amounts of nuclear fuel at their cores or centres. This produces tons of energy, so the centre gets very hot. Heat generates pressure, and the pressure created by a star's nuclear burning also keeps that star from collapsing.

Scientists at the University of Warwick are using AI to analyse these ''cosmic explosions''. In a paper published in the Monthly Notices of the Royal Astronomical Society, the use of machine learning to speed up experiments into supernovae—processes which are currently very computationally expensive and time-consuming. This will help reveal how these cosmic explosions took place by comparing explosion models to real-life observations.

According to Lead Author Dr Mark Magee, from the Department of Physics, University of Warwick, they analyse their spectra when investigating supernovae. Spectra show the intensity of light over different wavelengths, which is impacted by the elements created in the supernova. Each element interacts with light at unique wavelengths, leaving a unique signature on the spectra. Analysing these signatures can help to identify what elements are created in a supernova and provide further details on how the supernovae exploded.

The researchers leveraged this data to prepare models that are compared to real supernovae to establish what type of supernova it is and exactly how it exploded. Typically, one model might take 10–90 minutes to generate, and hundreds or thousands of models had to be compared to fully understand the supernova. This isn't really feasible in many cases.

Introducing AI

With their new research, the scientists are reducing the time consumed for this process. They will train machine learning algorithms on what different types of explosions look like and use these to generate models much more quickly. In a similar way to how AI can be used to generate new artwork or text, now they can generate simulations of supernovae. This means that thousands of models will be generated in less than a second, which will greatly boost supernova research.

Alongside speeding up the process of supernova analysis, AI will also enable better accuracy in research. This will help to establish what models match real-life explosions most closely and the range of their physical properties.

Long way to go

Dr Magee stated that exploring the elements released by supernovae is a crucial step in determining the type of explosion that occurred, as certain types of explosions produce more of some elements than others.

The present work is just the first step. Future research is expected to expand to an even greater variety of explosions and supernovae and directly link the explosion and host galaxy properties. Such research is now possible only through the advancements in machine learning.

Phys Org

NASA

Image: Unsplash