Androids might not dream of electric sheep, but one soon might use a dream-like state to discover the composition of faraway exoplanets.

Devised by astronomers at University College London, RobERt (Robotic Exoplanet Recognition) is a deep belief neural network that can examine the light emitted by distant planetary systems and estimate what gasses are present in these objects’ atmospheres.

“Different types of molecules absorb and emit light at specific wavelengths, embedding a unique pattern of lines within the electromagnetic spectrum,” explained Dr Ingo Waldmann, who leads RobERt’s development team, in a statement.

“We can take light that has been filtered through an exoplanet’s atmosphere or reflected from its cloud-tops, split it like a rainbow and then pick out the ‘fingerprint’ of features associated with the different molecules or gasses. Human brains are really good at finding these patterns in spectra and label them from experience, but it’s a really time-consuming job and there will be huge amounts of data.”

Deep belief neural networks are usually used for speech recognition, Internet searches, and tracking customer behavior. They are built for spotting patterns and they can be trained, which is perfect for the task at hand. RobERt was trained with 85,750 simulated spectra and at the end of the training, it had reached an accuracy of 99.7 percent.

“We built RobERt to independently learn from examples and to build on his own experiences,” said Dr Waldmann. “This way, like a seasoned astronomer or a detective, RobERt has a pretty good feeling for what molecules are inside a spectrum and which are the most promising data for more detailed analysis. But what usually takes days or weeks takes RobERt mere seconds.”

RobERt has also another trick up its sleeve. It can enter a ‘dreaming state’ and can create realistic spectra.

“This dreaming ability has been very useful when trying to identify features in incomplete data. RobERt can use his dream state to fill in the gaps,” Dr Waldmann continued.

“The James Webb Space Telescope, due for launch in 2018, will tell us more about the atmospheres of exoplanets, and new facilities like Twinkle or ARIEL will be coming online over the next decade that are specifically tailored to characterizing the atmospheres of exoplanets.

“The amount of data these missions will provide will be breathtaking. RobERt will play an invaluable role in helping us to analyze data from these missions and find out what these distant worlds are really like,” said Dr Waldmann.