We are in an age of scientific wonders. However, the massive amounts of data that scientists have access to are threatening to overwhelm the scientific community, raising the prospect of missing valuable, even revolutionary discoveries.
Over its 35 years of operation, the Hubble Space Telescope has produced just under 100 million images. The largest digital camera ever built, the Vera Rubin Observatory, "will generate about 20 terabytes of raw data each night," according to Science Alert. The James Webb Space Telescope (JWST) contributes about 57 GB of data every day.
"With powerful new telescopes like the Giant Magellan Telescope and Extremely Large Telescope coming online soon, the amount of astronomical data needing scientific scrutiny is growing into a deluge," reports Science Alert.
David O'Ryan and Pablo Gomez from ESA (the European Space Agency) published a paper in Astronomy and Astrophysics that promises to vastly improve our ability to wade through those mountains of data to find the unicorns in the dung heap.
"Astronomical archives contain vast quantities of unexplored data that potentially harbour rare and scientifically valuable cosmic phenomena," the authors write. "We leverage new semi-supervised methods to extract such objects from the Hubble Legacy Archive."
That "semi-supervised" method is an AI anomaly detection framework, AnomalyMatch. The researchers were able to go through the nearly 100 million Hubble images in less than 3 days. "AnomalyMatch is tailored for large-scale applications, efficiently processing predictions for ≈100 million images within three days on a single GPU," the authors wrote in a previous paper that presented the tool.
Anomaly Match found 1,400 astronomical objects it identified as anomalies. Almost 800 of the objects had never been identified before.
"Astrophysical anomalies are important because they can be outliers that present a different side of nature," reports Science Alert. "A trained scientist might be attuned to them and find them relatively easy."
Merging and interacting galaxies were the most common type of anomaly detected in the Archive. There were 417 of them.
The researchers also found 86 new potential gravitational lenses. These are important because they bring objects that are otherwise too distant to observe into reach.
They also help scientists study the distribution of dark matter in the Universe, measure distances and cosmic expansion, and test general relativity.
"We identify many gravitational lenses that are already identified in the literature – but many candidate new lenses," the authors write.
Gravitational lenses are where the gravity of a foreground galaxy bends spacetime so that the light from a background galaxy is warped into a circle or arc. Endgadget reports that "Other discoveries included planet-forming disks viewed edge-on, galaxies with huge clumps of stars and jellyfish galaxies. Adding a bit of mystery, there were even 'several dozen objects that defied classification altogether.'"
"Anomaly Match also found some unexplained phenomena, the article says. "The research also turned up some anomalies with uncertain natures. One of them is a strange sight, a galaxy with a swirling core and open lobes."
If all astronomical observations stopped tomorrow, the discoveries wouldn't stop. Capable AI tools are destined to become more and more powerful. Massive existing datasets from the Hubble and from other missions like the ESA's Gaia are feeding grounds for future tools.
Who knows what's waiting to be discovered in all that data?
"This is a powerful demonstration of how AI can enhance the scientific return of archival datasets," Gómez said.
AI could mean another great leap into the future for science in the coming years. Other scientific applications in medicine, biology, and physics, where massive amounts of data need to be combed through, will no doubt yield more discoveries.
A brave new world, just as long as we can control this new technology and use it for the expansion of human knowledge.
Also for our VIPs: Cases of AI Psychosis Are Skyrocketing
