Indian Astronomers Create AI-Based Tools To Find 60 Potential Habitable Planets

Indian Astronomers have now devised a new approach for identifying possible habitable planets with a high probability utilising an Artificial Intelligence-based algorithm. As a result, approximately 60 new potentially habitable planets have been discovered from 5,000 total planets known.

As per the study done by astronomers from the Indian Institute of Astrophysics (IIA), an institute of the Department of Science & Technology, under the Government Of India, with astronomers from the BITS Pilani, Goa campus, a new initiative -- an anomaly identification process -- has been uncovered by which any potentially habitable planets with high probability can be found.

"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...There are 60 potentially habitable planets out of about 5000 confirmed, and nearly 8000 candidate planets proposed. 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," ANI quoted the official release from the Ministry of Science and Technology as saying.

Searching New Habitable Planets

Speaking on the topic, Dr Snehanshu Saha of BITS Pilani said that Earth is the only habitable planet among numerous worlds is described as an anomaly. The researchers investigated whether similar anomaly candidates can be uncovered with the help of novel anomaly detection methods.

The IIA crew also described the fulcrum of the theory that postulates (potentially) livable exoplanets as anomalies pivots around the well-known anomaly detection trouble in predictive upkeep of industrial systems. Furthermore, an anomaly detection method appropriate for industrial systems involves equally nicely for habitable planet detection since, in both circumstances, the anomaly detector is dealing with "imbalanced" data, where the anomalies (number of habitable exoplanets or anomalous behaviour of industrial components) are outliers. These are way less in numeral when compared to the standard data.

A Landmark Breakthrough!

It is tedious to scan thousands of planets manually and identify planets potentially similar to Earth. Artificial Intelligence (AI) can be utilised efficiently to find habitable planets.

The AI-based process, known as the Multi-Stage Memetic Binary Tree Anomaly Identifier (MSMBTAI), is established on a novel multi-stage memetic algorithm (MSMA). The MSMA utilises the generic notion of a meme, knowledge or idea that gets transmitted from one individual to another by imitation. A meme suggests cross-cultural evolution in posterity and, consequently, can cause new learning mechanisms as generations go on. The algorithm can also behave as quick screening equipment for evaluating habitability perspectives from observed properties.

The study identified a few planets that exhibit similar anomalous characteristics as Earth via the proposed technique, which shows reasonably good results, agreeing with what is believed by the astronomers. Interestingly, this process also resulted in similar outcomes for anomalous prospect detection when it did not utilise surface temperature as a feature, compared to when it did.

Also Read: Anna Hazare Announces Indefinite Hunger Strike Against Wine Sale In Maharashtra Supermarkets