Mystery as AI tech spots number of ‘anomalies’ in space including new supernovae

A number of "anomalies" have been spotted in space by an artificial intelligencesystem that could help better our understanding of the universe.

Scientists now believe the findings could lead to more space anomalies being uncovered, including new supernovae and other distant and extreme objects.

It is understood that the system enables scientists to better pick through the extensive amount of data taken from the sky on a daily basis to focus on the most intriguing stuff.

READ MORE: New Met Office health alert kicks in today as Brits set to bake in 'extreme' heatwave

Astronomers have become bogged down by too much data, highlighting billions of potentially, interesting objects.

But the sifting capabilities of artificial intelligence has been used to find interesting objects in images of the Northern Sky that were taken using the Zwicky Transient Facility, or ZTF.

The AI system was given a range of images and tasked with uncovering anomalies – the phrase which scientists refer to rare objects such as tidal disruption events and supernovae.

And 11 anomalies were subsequently discovered using the system before being verified manually.

Maria Pruzhinskaya, a co-author of the paper and research fellow at the Sternberg Astronomical Institute, enthused: "This is a very good result. In addition to the already-discovered rare objects, we were able to detect several new ones previously missed by astronomers. This means that existing search algorithms can be improved to avoid missing such objects."

To stay up to date with all the latest news, make sure you sign up to one of our newsletters here.

Scientists have also said that the algorithm can be used more universally to help find any interesting astronomical objects and not just unusual supernovae.

It is also predicted that one day they could find entirely different kinds of objects using a similar AI that will look for those anomalies, the scientists suggest.

The research is described in a new paper, ‘SNAD transient miner: Finding missed transient events in ZTF DR4 using k-D trees’, which has been published in New Astronomy.


  • Family terrified as 'huge' American Bulldog launches at dad and savages puppy

  • Kate and William's secret £3,300 Heathrow lounge with butler and Michelin star menu

  • 'Nasty' care worker rumbled stealing cash from 93-year-old with dementia

  • Vile predator masqueraded as masseuse offering 'deep' massages to women

  • 'I've spent 20 years fighting my neighbour over 50ft hedge blocking out my view'

Source: Read Full Article