Scientists have for the first time discovered a whopping 301 planets orbiting their stars outside of our solar system. The new discovery marks a major era in deep space exploration as scientists use a new tool that can significantly enhance our capability to locate new worlds as we search for life beyond Earth.

The massive catalogue of planets adds to the already discovered 4,569 exoplanets orbiting a multitude of distant stars, some Earth-like, some hot Jupiters, others Neptunian in size, mass and characteristics. But how did scientists come across this whopping figure of 301 new worlds all at once?

The discovery was made possible by a new deep neural network called ExoMiner, a machine learning system that uses Nasa’s Pleiades supercomputer, and can distinguish real exoplanets from different types of imposters, or “false positives.” This makes the work of scientists relatively easier compared to years of studies, observations and wait.

WHAT IS DEEP NEURAL NETWORK EXOMINER?

Inspired by the similar technology used by humans to confirm the presence of a planet around a star, ExoMiner learns by using past confirmed exoplanets and false positive cases. According to Nasa, it supplements people who are pros at combing through data and deciphering what is and isn’t a planet. It derives its knowledge from the vast catalogue of data gathered by the Kepler spacecraft and K2.

“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. e can easily explain which features in the data lead ExoMiner to reject or confirm a planet,” said Jon Jenkins, an exoplanet scientist at Nasa.

The discovery has been detailed in a paper accepted for publication in The Astrophysical Journal, which confirms 301 new worlds discovered by ExoMiner using data from the remaining set of possible planets or candidates in the Kepler Archive.

Nasa said that all 301 machine-validated planets were originally detected by the Kepler Science Operations Center and were promoted to planet candidate status by the Kepler Science Office. But until ExoMiner, no one was able to validate them as planets.

ARE THESE PLANETS EARTH-LIKE?

Nasa confirmed that none of the 301 planets confirmed by the machine is Earth-like or in the habitable zone of their parent stars. However, they have similar characteristics to the overall population confirmed exoplanets in our galactic neighbourhood.

Scientists are hopeful that these 301 new discoveries will help us better understand planets and solar systems beyond our own, and what makes ours so unique.

“When ExoMiner says something is a planet, you can be sure it’s a planet. It 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 labelling. 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,” said Hamed Valizadegan, ExoMiner project lead.