planetary

Oct. 14 (Bloomberg) -- An international team led by Professor Jian Ge at the Shanghai Astronomical Observatory of the Chinese Academy of Sciences (CAS) has developed a deep-learning algorithm that combines GPU phase-folding and a convolutional neural network, and discovered five ultra-short-period planets with diameters smaller than the Earth and orbital periods shorter than a day in the stellar photometric data released by Kepler in 2017. Four of them are the smallest planets ever found closest to their host stars, similar to the size of Mars. This is the first time that astronomers have used artificial intelligence to search for suspected signals and identify real ones in one go. The related research results were published...