Using machine learning to estimate stellar ages

Researchers from Keele College have developed a machine studying approach that helps astronomers higher estimate the ages of stars from the chemical substances inside their atmospheres. The brand new analysis will likely be introduced on the 2023 National Astronomy Meeting by Keele Ph.D. scholar George Weaver.

A star’s age could be very troublesome to find out. Not like objects comparable to solar system meteorites or rocks on different planets, it’s not attainable to assemble bodily samples to measure the chemical abundances and age of the celebs we see within the evening sky by radioactive courting. As a substitute, astronomers have to make estimates based mostly on the sunshine we obtain from stars. That is most simply executed for big teams of stars which evolve collectively, often called star clusters, however is far more troublesome for single stars.

In the course of the very early levels of a star’s life cycle, the growing warmth and stress can change the chemical composition of its environment. One main change is that the quantity of the factor lithium in its environment decreases over time by means of a course of often called “lithium depletion.” Present fashions haven’t been capable of describe the complete complexity of this impact.

The big variety of high-quality spectra—an evaluation of emitted gentle from an object—obtained from the Gaia-ESO survey signifies that astronomers can now take a look at the issue of lithium depletion in a lot larger depth. The brand new neural community mannequin, a improvement of a earlier mathematical mannequin often called EAGLES, makes use of the info from greater than 6,000 stars to mannequin the connection between a star’s temperature, measured lithium abundance, and age.

The brand new technique is expandable, and work is already underway to incorporate far more information within the mannequin, creating age estimates utilizing as a lot data as attainable. Exams are already underway for a mannequin that features the metallicity of the celebs—the mannequin will soak up to account the measure of the quantity of components heavier than helium within the star. Different attainable expansions will take a look at slowing of a star’s rotation over its lifetime, and the lower in its magnetic exercise over time.

Ph.D. scholar and first writer of the paper in preparation, George Weaver explains, “There are a number of unbiased age estimation strategies and fashions, however this artificial neural network provides us the possibility to create one mixed technique to estimate a star’s age from spectral measurements.” He provides, “Not solely might it result in a ‘one-stop store’ mannequin for stellar and cluster ages, however it’ll additionally assist us to quantify and constrain the relationships between these observables and age, and possibly even uncover new relationships we weren’t conscious of earlier than.”