Indian astronomers discover 60 Earth-like exoplanets using new AI-method

In a significant advancement, Indian astronomers from the Bengaluru-based Indian Institute of Astronomy (IIA) have found over 50 planets using a new Artificial Intelligence-driven method. Named Multi-Stage Memetic Binary Tree Anomaly Identifier, the new method uses an algorithm that promises detection of new Earth-like planets with high probability. According to the Ministry of Science & Technology, the astronomers have detected 60 habitable planets out of 5,000 confirmed ones using the new method. 

How does the AI-based method work?

The algorithm is developed by the IIA, which is an autonomous institute of the Department of Science & Technology, Government of India, in collaboration with scientists from BITS Pilani, Goa. The method works on the postulate that the Earth is an anomaly, which the astronomers used to identify other anomalies among potential planetary candidates. 

An official release from the Ministry of Science and Technology said, "The method is based on the postulate that Earth is an anomaly, with the possibility of the existence of few other anomalies among thousands of data points...The assessment is based on their close similarity to Earth. These planets can be viewed as candidates for anomalous instances in a huge pool of `non-habitable' exoplanets."

As mentioned above, this method has helped the astronomers discover 60 Earth-like planets so far out of 5,000 confirmed planets that were selected from a total of 8,000 potential candidates. Dr. Snehanshu Saha of BITS Pilani explained that Earth is an anomaly in the sense that it is the only habitable planet among thousands of planets. He said that the astronomers detected the same anomaly among other planets. The team further said in their study published in the journal Monthly Notices of the Royal Astronomical Society (MNRAS) that their concept of anomaly detection applies well to both industrial applications and habitable planet detection since the detector is dealing with “imbalanced” data in both cases.

Image: Unsplash