Artificial intelligence helps astronomers estimate the ages of stars

Arabia Weather - Led by scientists from the British University of Keele, a research team has succeeded in developing a machine learning technique, which enables astronomers to estimate the ages of stars more accurately than the methods currently used, and these current methods rely on deducing the chemical composition of stars.

Machine learning is a branch of artificial intelligence that aims to improve the results of systems by analyzing huge amounts of data. To illustrate this, an example can be used of distinguishing dogs from cats. It feeds the artificial intelligence tens or even hundreds of thousands of images of dogs and approximately the same number of images of cats, and the intelligent software searches for statistical patterns that enable it to successfully distinguish between cats and dogs. After that, the artificial intelligence transforms these patterns into laws of a probabilistic nature.

When examining new images that were not previously available, it uses these rules to distinguish between dogs and cats. With each new image added to the database, the system’s performance improves the next time. This process is similar to the way we as humans learn in our daily lives from an early age.

How can the age of stars be determined using the lithium depletion hypothesis?

According to the new study announced at the 2023 National Astronomy Conference at Britain's Cardiff University, researchers were based on a scientific theory known as the "lithium depletion hypothesis."

During the life cycle of a star, the increase in temperature and pressure inside its core causes a change in the chemical composition of the star's outer atmosphere, specifically the splitting of the amount of lithium over time.

As a result of this hypothesis, researchers were able to use it to measure the age of a star by analyzing the amount of lithium present in it. This was done by studying the light emanating from distant stars, as lithium leaves a kind of fingerprint in the spectrum of this light, which can be read using telescopes such as Gaia. It is a space observatory launched by the European Space Agency in 2013, and this observatory aims to collect three-dimensional data on nearly a billion stars.

According to the press release issued by the Royal Astronomical Society, the researchers indicated that they took advantage of Gaia data collected from more than 6,000 stars, and used this data to feed machine learning software. This software was then used to model the relationship between the temperature of the star, the amount of lithium measured, and its age. The star.

The researchers aspire to improve the accuracy of astronomers' estimates of the ages of stars using this new mechanism. Since this type of AI-based technology is still in its early stages, its developments are rapidly accelerating day by day.

Also know:

“India reveals a plan to send a manned mission to the moon in 2040

How can I increase my chance of seeing the northern lights on a trip to the North Pole?

Sources:

aljazeera