Article image
06-13-2024

AI pinpoints the location of the farthest gamma-ray bursts in the universe

Astronomers have begun to unleash the full potential of artificial intelligence (AI) to unravel the deepest mysteries of the universe. Recent studies have harnessed the power of multiple AI machine learning models to achieve an unprecedented level of precision in measuring the distances of gamma-ray bursts (GRBs) – the most luminous and awe-inspiring explosions in the cosmos.

What are gamma-ray bursts?

GRBs are extremely energetic explosions that occur in distant galaxies. They are the most powerful and luminous electromagnetic events known to occur in the universe since the Big Bang.

Gamma-ray bursts were first discovered by accident in the late 1960s by U.S. military satellites designed to detect gamma radiation pulses emitted by nuclear weapons tested in space.

During a GRB, an enormous amount of energy is released in the form of gamma rays, the highest-energy form of light. Below are a few key points about GRBs:

  • Duration: GRBs are classified as long or short based on their duration. Long GRBs last more than 2 seconds and are thought to be associated with the collapse of massive stars. Short GRBs last less than 2 seconds and are believed to result from the merger of two compact objects, such as neutron stars or black holes.
  • Energy release: In just a few seconds, GRBs can release as much energy as our sun will emit over its entire lifetime, making them the most energetic events known in the universe.
  • Afterglow: After the initial burst, GRBs produce an “afterglow” that can be observed at lower energies, such as X-ray, optical, and radio wavelengths. This afterglow can last for days or even months.
  • Distance: GRBs are observed at cosmological distances, meaning they occur in galaxies billions of light-years away from Earth. This makes them useful tools for studying the early universe and the evolution of stars.
  • Progenitors: The exact mechanisms that produce GRBs are still being studied, but they are thought to involve the collapse of massive stars or the merging of compact objects, such as neutron stars or black holes.

Cosmic distances of gamma-ray bursts

Detecting and studying GRBs involves a network of satellites and ground-based observatories. These instruments help scientists understand the physical processes driving these bursts and their role in the cosmos.

GRBs also serve as cosmic beacons, helping astronomers study the structure and evolution of the universe. This visibility makes GRBs invaluable tools for astronomers tracking the ancient and distant stars.

However, the challenge has always been the accuracy of these measurements, limited by current observational technologies.

Only a fraction of known GRBs have the complete set of observational characteristics necessary for precise distance calculations.

Gamma-ray bursts and AI

To address these challenges, researchers have successfully incorporated machine learning models to enhance the precision of these measurements.

By integrating gamma-ray burst data from NASA’s Neil Gehrels Swift Observatory with advanced AI techniques, scientists are now able to estimate the distances of GRBs more accurately.

Maria Dainotti, a visiting professor at the University of Nevada, Las Vegas’s Center for Astrophysics (NCFA) and assistant professor at the National Astronomical Observatory of Japan (NAOJ), emphasized the significance of these advancements.

“This research pushes forward the frontier in both gamma-ray astronomy and machine learning,” she stated.

Dainotti, along with her team and international collaborators, has leveraged several machine-learning methods to refine their predictions.

In one notable study, these methods were applied to data from the Swift UltraViolet/Optical Telescope (UVOT) and ground-based observatories like the Subaru Telescope.

The research, focusing on non-distance-related GRB properties, has provided results so precise that they nearly match the actual observed estimates of GRB rates in space.

Superlearner algorithm technique

A key technique in their approach is the Superlearner algorithm, which combines multiple machine learning methods to enhance predictive accuracy.

Each algorithm is assigned a weight, reflecting its predictive strength.

“The advantage of the Superlearner is that the final prediction is always more performant than the singular models,” Dainotti explained.

This method not only optimizes predictions but also identifies and discards less effective algorithms.

Exploring the origins of gamma-ray bursts

Another study explored the origins of long gamma-ray bursts, typically associated with the supernova explosions of massive stars, and short gamma-ray bursts, which are believed to occur when neutron stars collide.

This research utilized data from NASA’s Swift X-ray Telescope (XRT) to delve into the mysteries of GRB formation.

Intriguingly, it revealed that the occurrence rate of long GRBs at smaller distances does not align with the rate of star formation, suggesting alternative formation theories, such as the merging of dense stellar remnants.

Challenging conventional wisdom

A third study, published in the Astrophysical Journal Letters and led by Stanford University astrophysicist Vahé Petrosian and Dainotti, utilized Swift X-ray data to address perplexing questions.

The research revealed that the GRB rate, at least at small relative distances, does not follow the rate of star formation.

“This opens the possibility that long GRBs at small distances may be generated not by a collapse of massive stars, but rather by the fusion of very dense objects like neutron stars,” said Petrosian.

Future of AI and cosmic exploration

With support from NASA’s Swift Observatory Guest Investigator program (Cycle 19), Dainotti and her colleagues are currently working on making the machine learning tools publicly accessible through an interactive web application.

This initiative will empower astronomers worldwide to leverage these cutting-edge techniques in their own research, paving the way for unprecedented discoveries in the field of gamma-ray astronomy.

In summary, as astronomers continue to push the boundaries of cosmic exploration, the pioneering work of Maria Dainotti and her teams stands as a shining example of the power of interdisciplinary collaboration.

By harnessing the potential of AI and machine learning, they have unlocked new ways to measure the distances of gamma-ray bursts and shed light on the mysteries of these awe-inspiring cosmic events.

Their innovative approach advances our understanding of the universe and paves the way for future discoveries that will undoubtedly reshape our perception of the cosmos.

As we eagerly await the public release of these powerful machine learning tools, we can only imagine the exciting revelations that await us in the field of gamma-ray astronomy and beyond.

The full study was published in the journal The Astrophysical Journal Letters.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–

News coming your way
The biggest news about our planet delivered to you each day
Subscribe