Astronomy

Artificial intelligence and machine learning have become ubiquitous, with applications ranging from data analysis, cybersecurity, pharmaceutical development, music composition, and artistic renderings. In recent years, large language models (LLMs) have also emerged, adding human interaction and writing to the long list of applications. This includes ChatGPT, an LLM that has had a profound impact since it was introduced less than two years ago. This application has sparked considerable debate (and controversy) about AI’s potential uses and implications.

Astronomy has also benefitted immensely, where machine learning is used to sort through massive volumes of data to look for signs of planetary transits, correct for atmospheric interference, and find patterns in the noise. According to an international team of astrophysicists, this may just be the beginning of what AI could do for astronomy. In a recent study, the team fine-tuned a Generative Pre-trained Transformer (GPT) model using observations of astronomical objects. In the process, they successfully demonstrated that GPT models can effectively assist with scientific research.

The study was conducted by the International Center for Relativistic Astrophysics Network (ICRANet), an international consortium made up of researchers from the International Center for Relativistic Astrophysics (ICRA), the National Institute for Astrophysics (INAF), the University of Science and Technology of China, the Chinese Academy of Sciences Institute of High Energy Physics (CAS-IHEP), the University of Padova, the Isfahan University of Technology, and the University of Ferrera. The preprint of their paper, “Test of Fine-Tuning GPT by Astrophysical Data,” recently appeared online.

Illustration of an active quasar. New research shows AI can identify and classify them. Credit: ESO/M. Kornmesser

As mentioned, astronomers rely extensively on machine learning algorithms to sort through the volumes of data obtained by modern telescopes and instruments. This practice began about a decade ago and has since grown by leaps and bounds to the point where AI has been integrated into the entire research process. As ICRA President and the study’s lead author Yu Wang told Universe Today via email:

“Astronomy has always been driven by data and astronomers are some of the first scientists to adopt and employ machine learning. Now, machine learning has been integrated into the entire astronomical research process, from the manufacturing and control of ground-based and space-based telescopes (e.g., optimizing the performance of adaptive optics systems, improving the initiation of specific actions (triggers) of satellites under certain conditions, etc.), to data analysis (e.g., noise reduction, data imputation, classification, simulation, etc.), and the establishment and validation of theoretical models (e.g., testing modified gravity, constraining the equation of state of neutron stars, etc.).”

Data analysis remains the most common among these applications since it is the easiest area where machine learning can be integrated. Traditionally, dozens of researchers and hundreds of citizen scientists would analyze the volumes of data produced by an observation campaign. However, this is not practical in an age where modern telescopes are collecting terabytes of data daily. This includes all-sky surveys like the Very Large Array Sky Survey (VLASS) and the many phases conducted by the Sloan Digital Sky Survey (SDSS).

To date, LLMs have only been applied sporadically to astronomical research, given that they are a relatively recent creation. But according to proponents like Wang, it has had a tremendous societal impact and has a lower-limit potential equivalent to an “Industrial Revolution.” As for the upper limit, Wang predicts that that could range considerably and could perhaps result in humanity’s “enlightenment or destruction.” However, unlike the Industrial Revolution, the pace of change and integration is far more rapid for AI, raising questions about how far its adoption will go.

The Sloan Digital Sky Survey telescope stands out against the breathtaking backdrop of the Sacramento Mountains. Credit: SDSS/Fermilab Visual Media Services

To determine its potential for the field of astronomy, said Wang, he and his colleagues adopted a pre-trained GPT model and fine-tuned it to identify astronomical phenomena:

“OpenAI provides pre-trained models, and what we did is fine-tuning, which involves altering some parameters based on the original model, allowing it to recognize astronomical data and calculate results from this data. This is somewhat like OpenAI providing us with an undergraduate student, whom we then trained to become a graduate student in astronomy. 

“We provided limited data with modest resolution and trained the GPT fewer times compared to normal models. Nevertheless, the outcomes are impressive, achieving an accuracy of about 90%. This high level of accuracy is attributable to the robust foundation of the GPT, which already understands data processing and possesses logical inference capabilities, as well as communication skills.”

To fine-tune their model, the team introduced observations of various astronomical phenomena derived from various catalogs. This included 2000 samples of quasars, galaxies, stars, and broad absorption line (BAL) quasars from the SDSS (500 each). They also integrated observations of short and long gamma-ray bursts (GRBs), galaxies, stars, and black hole simulations. When tested, their model successfully classified different phenomena, distinguished between types of quasars, inferred their distance based on redshift, and measured the spin and inclination of black holes.

“This work at least demonstrates that LLMs are capable of processing astronomical data,” said Wang. “Moreover, the ability of a model to handle various types of astronomical data is a capability not possessed by other specialized models. We hope that LLMs can integrate various kinds of data and then identify common underlying principles to help us understand the world. Of course, this is a challenging task and not one that astronomers can accomplish alone.”

The Vera Rubin Observatory at twilight on April 2021. It’s been a long wait, but the observatory should see first light later this year. Credit: Rubin Obs/NSF/AURA

Of course, the team acknowledges that the dataset they experimented with was very small compared to the data output of modern observatories. This is particularly true of next-generation facilities like the Vera C. Rubin Observatory, which recently received its LSST camera, the largest digital camera in the world! Once Rubin is operational, it will conduct the ten-year Legacy Survey of Space and Time (LSST), which is expected to yield 15 terabytes of data per night! Satisfying the demands of future campaigns, says Wang, will require improvements and collaboration between observatories and professional AI companies.

Nevertheless, it’s a foregone conclusion that there will be more LLM applications for astronomy in the near future. Not only is this a likely development, but a necessary one considering the sheer volumes of data astronomical studies are generating today. And since this is likely to increase exponentially in the near future, AI will likely become indispensable to the field of study.

Further Reading: arXiv

The post What Can AI Learn About the Universe? appeared first on Universe Today.

China's Chang'e 6 sample return mission to the moon's far side is scheduled to launch early Friday morning (May 3), and you can watch the action live.

Alkaid is the end star of the Big Dipper's handle, a bright-blue example of a nearby B-type star.

The post Meet Alkaid, the Big Dipper’s Handle appeared first on Sky & Telescope.

NASA's Galaxy Evolution Explorer was launched on April 28, 2003. Its mission was to study the shape, brightness, size and distance of galaxies across 10 billion years of cosmic history.

The hit sci-fi show’s adviser and two other researchers discuss its portrayal of scientists and their technologies

United Launch Alliance's new video highlight's how the Atlas V launch vehicle for Boeing's Starliner was stacked and mated to the spacecraft.

Both the Hubble Telescope and TESS exoplanet hunter went into safe mode on April 23. Hubble is back on, but TESS remains off.

When poet Jessy Randall saw that so many female scientists weren’t getting their due, she got mad. And then she decided to write poems for as many as she could

NASA's PREFIRE mission will deploy a pair of satellites from twin launches aboard Rocket Lab's Electron rockets that will contribute to climate change studies in the Arctic and Antarctica.

A male Sumatran orangutan chewed the leaves of a plant used in Indonesian traditional medicine and placed them on a wound on his face

A male Sumatran orangutan chewed the leaves of a plant used in Indonesian traditional medicine and placed them on a wound on his face

Video: 00:02:59

Last week, Ariane 6’s central core – the main body of the rocket – was stood tall at the launch zone and connected to its two solid-fuel boosters. This exciting moment means only one thing: it’s the start of the first launch campaign.

The main stage and upper stage make up the core stage, and they were autonomously driven at 3 km/h from the rocket assembly building to the launch pad, 800 m away. Then lifted by a crane, the Ariane 6 core was stood upright on the launch table.

The two boosters were transported to the launch pad on a specially designed truck and then configured with the rocket body, now holding it upright.

Ariane 6 is due to launch in summer 2024. The heavy-lift rocket will inaugurate a new era of autonomous European space transportation, powering Europe into space to realise its ambitions on the world stage. It will lift off from a modern launch complex at Europe’s Spaceport in French Guiana, carrying with it not just a variety of spacecraft, but also European goals for prosperity and autonomy.

SpaceX launched another batch of its Starlink internet satellites on Thursday (May 2), on the second half of a planned spaceflight doubleheader.

WASP-12b is a planet on a date with a fiery destiny, doomed to plunge into its sun-like star. Scientists may finally know why some hot Jupiters eventually death spiral into their stars.

Researchers say this may be the first observation of a nonhuman animal purposefully treating a wound with a medicinal plant

NASA's inspector general writes that the Artemis 1 test flight of the Orion spacecraft revealed anomalies that "pose significant risks to the safety of the crew."

Sixty-one years after it stood ready to send NASA's last one-man mission into orbit, the Mercury-Atlas 9 rocket is standing again. A replica is on display at the National Museum of the US Air Force.

NASA has selected nine companies to develop concepts that could agency science missions to Mars down the road.

Domain walls, long a divisive topic in physics, may be ideal explanations for some bizarre cosmic quirks

Levels of protection measles provided by the MMR jab fall by a small amount every year, according to mathematical modelling