Technical terminology is employed in astronomy to effectively communicate particular concepts in terms that are clear to experienced astronomers. However, using the same vocabulary can make including non-experts in the discussion challenging.
An international team of scientists, led by a researcher at The University of Manchester, has developed a novel AI (artificial intelligence) approach to distilling technical astronomy terminology into simple, understandable English. The study results from the international RGZ EMU (Radio Galaxy Zoo EMU) collaboration.
This new approach could transition radio astronomy language from specific terms, such as FRI (Fanaroff-Riley Type 1), to plain English terms, such as “hourglass” or “traces host galaxy.”
Micah Bowles, Lead author and RGZ EMU data scientist, said: “Using AI to make the scientific language more accessible is helping us share science with everyone. With the plain English terms we derived, the public can engage with modern astronomy research like never before and experience all the amazing science being done around the world.”
Similar to satellite dishes, radio telescopes operate by picking up radio waves emitted by incredibly intense astrophysical phenomena, such as black holes in neighboring galaxies, as opposed to television transmissions. Astronomers have classified these “radio galaxies” into various categories for many years in order to better comprehend the beginnings and evolution of the Universe.
Recently, significant advancements in radio telescope technology have revealed an increasing number of these radio galaxies, making it impossible for astronomers to categorize them all individually and introducing new variations that aren’t already covered by known radio galaxy types.
The RGZ EMU team recognized an alternative way ahead that would allow citizen scientists to participate more thoroughly in their research endeavor instead of trying to continually develop new technical terms for various sorts of radio galaxies and train people to distinguish them.
Before asking non-experts to characterize a selection of radio galaxies in layman’s terms, the RGZ EMU team asked professionals to explain the galaxies in their technical terminology. The scientists then picked the plain English descriptions that included the greatest scientific information using a novel AI-based approach.
These descriptions, or “tags”, can now be used by anyone to describe radio galaxies — in a way that is meaningful for any English speaker — without any specialist training at all. This work will not only be crucial for the RGZ EMU project, but with ever-increasing volumes of data across many areas of science, this new AI approach could find use in many more situations where simplified language can accelerate research, collaboration, and communication.
The RGZ EMU collaboration is building a project on the Zooniverse citizen science platform, which asks the public for help describing and categorizing galaxies imaged through a radio telescope.
Led from Manchester, this research was conducted by researchers from the UK, China, Germany, the USA, the Netherlands, Australia, Mexico, and Pakistan. The data, code, and results are all available online.