Artificial intelligence finds messy galaxies

October 27, 2015

An ANU astrophysics student has turned to artificial intelligence to help her to see into the hearts of galaxies.

PhD student Elise Hampton was inspired by to create a program to single out from thousands of galaxies the subjects of her study - the most turbulent and messy galaxies.

"I love . It was actually a very simple program to write, once I learnt how," said Ms Hampton, who is studying at the ANU Research School of Astronomy and Astrophysics.

"The program took eight minutes to analyse 300,000 data points from 1,188 galaxies. For one person to do it would have taken years."

Ms Hampton is studying galaxies with brightly glowing centres powered by black holes that cause huge galactic winds.

"We believe these winds blow so much material out of the galaxies that they eventually starve themselves to death," she said.

Galactic winds can also trigger the formation of new stars, so Ms Hampton's goal is to work out how the different processes compete in these turbulent galaxies and ultimately understand how galaxies live and die.

Astronomers can interpret the spectra of these messy galaxies to distinguish between light from stars forming, matter falling into , and supersonic , but it is a painstaking process.

Enormous numbers of galaxy spectra are being measured by robotic telescopes such as the ANU 2.3 metre and the Anglo-Australian Telescope and so Ms Hampton's automation of the analysis process with is a welcome success after a number of approaches failed.

Artificial Neural Networks are a family of computer programs inspired by the brain that work as an interconnected set of individual processors, similar to neurons. Unlike traditional rule-based computer programs, they are adaptive and capable of learning.

Ms Hampton taught her computer program how to analyse using about 4,000 spectra that had been analysed previously by astrophysicists.

Explore further: A simulation of the universe with realistic galaxies

More information: Ms. Hampton is presenting her research on Wednesday at the international Astronomical Data Analysis Software and Systems conference ( www.scimex.org/newsfeed/smartp … ydney,-25-29-october ), hosted by the ARC Centre for All-Sky Astrophysics (CAASTRO) in Sydney.

Related Stories

A simulation of the universe with realistic galaxies

December 30, 2014

An international team of astronomers, based at the Universities of Leiden in the Netherlands and Durham in the UK and, led by professor Joop Schaye (Leiden University), developed a simulation of the universe in which realistic ...

A shy galactic neighbor

September 16, 2015

The Sculptor Dwarf Galaxy, pictured in this new image from the Wide Field Imager camera, installed on the 2.2-metre MPG/ESO telescope at ESO's La Silla Observatory, is a close neighbour of our galaxy, the Milky Way. Despite ...

Image: Hubble observes galaxies' evolution in slow motion

September 21, 2015

It is known today that merging galaxies play a large role in the evolution of galaxies and the formation of elliptical galaxies in particular. However there are only a few merging systems close enough to be observed in depth. ...

Recommended for you

Image: Hubble's cosmic search for a missing arm

November 20, 2017

This new picture of the week, taken by the NASA/ESA Hubble Space Telescope, shows the dwarf galaxy NGC 4625, located about 30 million light-years away in the constellation of Canes Venatici (The Hunting Dogs). The image, ...

Solar minimum surprisingly constant

November 17, 2017

Using more than a half-century of observations, Japanese astronomers have discovered that the microwaves coming from the sun at the minimums of the past five solar cycles have been the same each time, despite large differences ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.