The intersection of computer science and astronomy has yielded a fascinating result today. Using machine learning algorithms developed by Google, scientists have sifted through old, noisy data from the Kepler Space Telescope and discovered a new exoplanet, Kepler-90i.



This brings the total number of planets in the Kepler-90 system to eight, tying it with our own solar system for the most known planets around a single star. The neural network was trained to identify the incredibly weak, subtle dimming of a star caused by a planetary transit—signals that were previously too weak for human researchers or standard software to confidently flag. It is a brilliant demonstration of how artificial intelligence is going to revolutionise how we process the vast oceans of data generated by modern observatories.