Scientists recently added a whopping 301 newly validated exoplanets to the total exoplanet tally. The throng of planets is the latest to join the 4,569 already validated planets orbiting a multitude of distant stars. How did scientists discover such a huge number of planets, seemingly all at once? The answer lies with a new deep neural network called ExoMiner.
When a planet crosses directly between us and its star, we see the star dim slightly because the planet is blocking out a portion of the light. This is one method scientists use to find exoplanets. They make a plot called a light curve with the brightness of the star versus time. Using this plot, scientists can see what percentage of the star’s light the planet blocks and how long it takes the planet to cross the disk of the star. Credit: NASA’s Goddard Space Flight Center
Deep neural networks are machine learning methods that automatically learn a task when provided with enough data. ExoMiner is a new deep neural network that leverages NASA’s Supercomputer, Pleiades, and can distinguish real exoplanets from different types of imposters, or “false positives.” Its design is inspired by various tests and properties human experts use to confirm new exoplanets. And it learns by using past confirmed exoplanets and false positive cases.
ExoMiner supplements people who are pros at combing through data and deciphering what is and isn’t a planet. Specifically, data gathered by NASA’s Kepler spacecraft and K2, its follow-on mission. For missions like Kepler, with thousands of stars in its field of view, each holding the possibility to host multiple potential exoplanets, it’s a hugely time-consuming task to pore over massive datasets. ExoMiner solves this dilemma.