Machine Learning to the Rescue
Global Nominee
Machine Learning to the Rescue received a Global Nomination.
For this challenge, we invite you to become "virtual contributors" to the Asteroid Grand Challenge and develop a hypothetical method, concept note or simple prototype that demonstrates how Machine Learning could be used to help us avoid the same fate as the dinosaurs.
Machine Learning is a field of computer science that works on previous data sets to produce reliable predictions.
Thus, we use this technique of machine learning to estimate the distance, direction and frequency of asteroid strikes and then the time interval between successive strikes.
How it works?*
- We use parameters such as rotation, reflectivity, composition and orbital arc to predict the distance and direction of a strike.
- Previous data sets based on the parameters listed above are plotted on a graph and a line/curve is chosen in such a way that it passes through the most points of the data set as to ensure an accurate prediction of future asteroids.*
Advantages:
- Prediction through machine learning algorithms will give us adequate time to prepare ourselves for an impact which is not possible with the technology we use today.
- Since, we will be able to determine the distance and direction of incoming asteroids, we can choose those asteroids for mining processes which are just close enough as to not harm us. This will save us power and resources as we will be able to estimate the exact position and time at which an asteroid will come near the earth.*
Deflection Mechanism:*
Once, the asteroid has been detected, having a suitable deflection mechanism becomes of paramount importance.
Thus, we propose to use the Yarkovsky Effect to deflect an incoming asteroid. We will use photons aggregated from the sun to heat the incoming asteroid. As the warmest regions radiate the most heat, the radiation will impart a push on the asteroid and deflect it off its course.
'Thus, we not only protect our species avoid the same fate as the dinosaurs but even harness the power and the resources of the world beyond.'
* Proper working of the machine learning algorithms, the mining process and the proper working of the proposed deflection mechanism have been explained in our GitHub document.
Note: Please view our video with headphones for optimal experience.
