With the help of artificial intelligence and machine learning, Australian researchers have developed a new sensor to make it easier for Earth-based optical telescopes to detect distant Earth-like planets.

The new photonic wavefront sensor was developed by researchers at the University of Sydney and published on Wednesday. It can measure and correct the "twinkle", a distortion of starlight caused by viewing through the Earth's atmosphere from an optical telescope.

"The main way we identify planets orbiting distant stars is by measuring regular dips in starlight caused by planets blocking out bits of their sun," lead author Barnaby Norris explained.

However, this type of indirect detection methods, like measuring starlight dips will miss a lot of information comparing with making a direct image of the planet from telescopes.

To solve the problem, the new sensor adopts a different approach to existing methods by combining photonics with artificial intelligence.

"This new sensor merges advanced photonic devices with deep learning and neural networks techniques to achieve an unprecedented type of wavefront sensor for large telescopes," Norris said.

With the potential to resolve some major limitations of the current technology, the invention will be deployed in one of the largest optical telescopes in the world, the 8.2-meter Subaru telescope in Hawaii.

"Most observations of exoplanets have come from orbiting telescopes, such as NASA's Kepler. With our invention, we hope to launch a renaissance in exoplanet observation from the ground," he said.