You can add the discovery of supernovas to the list of accolades attributed to it artificial intelligence. This week, a collaboration of astronomers led by Northwestern University said it has developed the world’s first system for detecting, identifying and classifying supernovas with the help of artificial intelligence. The powerful new tool, which scientists say could “Great simplificationLarge studies of future exploding stars have discovered their first supernova.
Before this tool, astronomers involved in its creation say, supernova detection relied on a combination of automated systems and human verification methods. Normally, robotic telescopes gaze at parts of the sky in search of new potential supernova sources that did not exist before. Once a filter is discovered, the process is usually handed over to humans who operate telescopes with spectrometers to collect the spectrum of the source, or scattered light. The automated tool, called Bright Transient Survey Bot (BTSbot), aims to remove this human middleman from the process.
The researchers fed the BTSbot machine learning algorithm with 1.4 million images from 16,000 astronomical sources. Those images included previous evidence of supernovas, bright galaxies and temporarily glowing stars. Thanks to this training set, the AI model was able to identify a new supernova candidate and automatically request a reading of its spectrum from an automated telescope at the Palomar Observatory in California. The system eventually identified the supernova candidate as a “starburst” in which a white dwarf star exploded completely, and automatically shared its results with the astronomical community. In other words, the AI system was able to recognize and share the new discovery on its own, which is great news for the humans involved.
“The simulation performance was excellent, but you never know how that translates to the real world until you actually try it,” Nabil Rahimullah, a graduate student at Northwestern University, said in a statement. “We felt a huge wave of relief.”
The astronomers responsible for building BTSbot believe that all this extra time saved trying to manually detect and identify supernovas will give human scientists more time to analyze their observations and consider new ideas.
“Ultimately, removing humans from the loop provides more time for the research team to analyze their observations and develop new hypotheses to explain the origin of the cosmic explosions we observe,” said Adam Miller, an assistant professor of physics and astronomy at Northwestern University.
Of course, astronomers don’t necessarily do this Need Fully automated artificial intelligence systems to capture stunning supernova images. Keep reading for a series of some of the most interesting supernova discoveries in recent memory. If you’re feeling especially sentimental, you can pour one out to the human supernova detectors while you’re at it.
“Web maven. Infuriatingly humble beer geek. Bacon fanatic. Typical creator. Music expert.”