AI Helps find Earth-like Habitable Exo-planets

    (Photo credit: BBC)

Are We Alone? 

It is a question that humans have had ever since we realized there are other worlds, other planets out there in the cosmos. The implications of the answer to this question are staggering no matter what that answer is. In pursuit of an answer scientists have been searching for planets that could potentially harbor life. Planets that are outside of our solar system are termed Exoplanets. The exploratory pursuit is to find "earth-like" exoplanets because these would have the greatest chance of harboring life as we know it.

Determining the habitability of exoplanets is not an easy task. Existing ML methods such as Metric-based quantification (using metrics like surface temperature) or Supervised Learning (based mainly on estimated surface temperature) are not reliable enough. 

Astronomers from the Indian Institute of Astrophysics along with astronomers from BITS Pilani and Goa campus designed an anomaly detection method to identify potentially habitable planets based on the theory that Earth is an anomaly.

Models have been developed based on unsupervised learning methods such as Anomaly Detection algorithms using clustering. Unsupervised methods do not rely on class labels in the training set. 

The following methods were proposed: 

1. A novel clustering method, multi-stage multi-version memetic clustering algorithm (MSMVMCA), based on a novel MSMA;
2. Multi-stage memetic binary tree anomaly identifier (MSMBTAI);
3. Enhanced cluster-based local outlier factor (ECBLOF), a distance semi-metric;
4. Application of MSMBTAI and ECBLOF to detect anomalies i.e. potentially habitable exoplanets from data.

Those abbreviations are quite a mouthful! 

According to the study, there are 60 potentially habitable planets out of about 5000 confirmed, and nearly 8000 candidate planets proposed. These planets can be viewed as candidates for anomalous instances in a huge pool of 'non-habitable' exoplanets.

This new advancement is likely to help make the process of searching for habitable exoplanets a lot easier and more efficient. 

For an in-depth look into this research, please go here.