Using ExoMiner, a new deep neural network that leverages NASA’s Pleiades supercomputer, NASA scientists have a whopping 301 newly validated exoplanets to the 4,569 already validated planets list orbiting a multitude of distant stars. The examiner can distinguish actual exoplanets from different types of imposters or “false positives.”
None of the newly confirmed planets are believed to be Earth-like or in the habitable zone of their parent stars. But they do share similar characteristics to the overall population of confirmed exoplanets in our galactic neighborhood.
Jon Jenkins, an exoplanet scientist at NASA’s Ames Research Center in California’s Silicon Valley, said, “Unlike other exoplanet-detecting machine learning programs, ExoMiner isn’t a black box – there is no mystery as to why it decides something is a planet or not. We can easily explain which features in the data lead ExoMiner to reject or confirm a planet.”
There is a significant difference between a confirmed and validated exoplanet?
A planet is “confirmed” when different observation techniques reveal features that a planet can only explain. A planet is “validated” using statistics – meaning how likely or unlikely it is to be a planet based on the data.
ExoMiner discovered these 301 newly using data from the remaining set of possible planets in the Kepler Archive. The Kepler Science Operations Center pipeline initially detected these planets. Later, the Kepler Science Office promoted their planet candidate status. However, no one was able to validate them as planets until ExoMiner validated them.
Hamed Valizadegan, ExoMiner project lead, and machine learning manager with the Universities Space Research Association at Ames, said, “When ExoMiner says something is a planet, you can be sure it’s a planet. ExoMiner is highly accurate and in some ways more reliable than both existing machine classifiers and the human experts it’s meant to emulate because of the biases that come with human labeling.”
Jenkins said, “These 301 discoveries help us better understand planets and solar systems beyond our own, and what makes ours so unique.”
Hamed Valizadegan, ExoMiner project lead and machine learning manager with the Universities Space Research Association at Ames, said, “Now that we’ve trained ExoMiner using Kepler data, with a little fine-tuning, we can transfer that learning to other missions, including TESS, which we’re currently working on. There’s room to grow.”
The study is accepted for publication in The Astrophysical Journal.