• Researchers from Keele University have developed a machine learning technique that helps astronomers better estimate the ages of stars. 
• A star’s age is very difficult to determine as they don’t change much during their long lives, and it is not possible to gather physical samples to measure the age of the stars by radioactive dating.  
• The method created by Keele astronomers uses artificial intelligence trained on data from over 6,000 stars to model the relationship between a star’s temperature, measured lithium abundance, and age. 

A glimpse into the past 

Researchers from Keele University have developed a machine learning technique that helps astronomers better estimate the ages of stars from the chemicals within their atmospheres.  

Professor Robin Jeffries and his PhD student George Weaver conducted the research to help improve our understanding of how the Galaxy has developed throughout history, by reconstructing the history of star formation from the ages of stars we can observe today. 

A star’s age is very difficult to determine as they don’t change much during their long lives – our Sun looks much the same now as it did 4 billion years ago – and unlike objects such as meteorites or rocks on other planets, it is not possible to gather physical samples to measure the age of the stars by radioactive dating.  

Instead, astronomers need to make estimates based on the light we receive from stars. This is most easily done for large groups of stars which evolve together, known as star clusters, but is much more difficult for single stars. 

Complex scientific processes 

During the very early stages of a star’s life cycle, the increasing heat and pressure initiate nuclear fusion reactions that can change the chemical composition of its atmosphere. One major change is that the amount of the element lithium in its atmosphere decreases over time through a process known as ‘lithium depletion’.  

Current models have not been able to describe the full complexity of this effect, but Professor Jeffries has developed a mathematical model known as “EAGLES”, which can be used to estimate the age of any star, using measurements of just its temperature and lithium content. 

Mr Weaver has expanded the model using artificial intelligence, creating an artificial neural network that can take training data from over 6,000 stars where the age is known to model the relationship between a star’s temperature, measured lithium abundance, and age.  

The new method is expandable, and work is already underway to include much more data in the model, creating age estimates using as much information as possible. 

“Taking full advantage of massive datasets” 

Mr Weaver said: “There are several independent age estimation methods and models, but this artificial neural network gives us the chance to create one combined method to estimate a star’s age from spectral measurements. 

“Not only could it lead to a ‘one-stop shop’ model for stellar and cluster ages, but it will also help us to quantify and constrain the relationships between these observables and age, and maybe even discover new relationships we weren’t aware of before.” 

Professor Jeffries added: “Artificial intelligence techniques such as supervised learning are increasingly being deployed in astrophysics to take full advantage of the massive datasets being obtained by satellites and at telescopes around the world. In the case of this model, we hope to use it on new data being obtained by telescopic surveys taking place over the next few years on the Spanish island of La Palma and in Chile, in which Keele is playing an active role.”