Machine Learning Discovers Quasars Acting as Lenses

Astronomers have used machine learning to discover seven new quasar lens systems, arrangements where a quasar’s host galaxy bends light from a more distant galaxy behind it. The find more than doubles the number of known candidates and demonstrates how artificial intelligence can unearth astronomical needles in haystacks containing hundreds of thousands of objects. A team of researchers are training neural networks on synthetic data to revolutionising the search for these rare natural lenses.