Skip to content

Machine Learning implementations to determine which Nearest Earth Objects are hazardous.

Notifications You must be signed in to change notification settings

TheHarshal30/Hawking

Repository files navigation

Hawking

Context

There is an infinite number of objects in the outer space. Some of them are closer than we think. Even though we might think that a distance of 70,000 Km can not potentially harm us, but at an astronomical scale, this is a very small distance and can disrupt many natural phenomena. These objects/asteroids can thus prove to be harmful. Hence, it is wise to know what is surrounding us and what can harm us amongst those.

Dataset

This dataset compiles the list of NASA certified asteroids that are classified as the nearest earth object.
The dataset contains the following information about object:

    -Name
    -Estimated minimum diameter
    -Estimated maximum diameter
    -Relative velocity
    -Miss Distance
    -Orbiting Body
    -Sentry Object
    -Absolute Magnitude
Download link - https://bit.ly/3nOK9Wj

Models:

Model Accuracy
Using Bayes Theorem 90.41
Neural Network using Pytorch 91.186
XG Boost 91.23
Random Forest 92.07
DecisionTreeClassifier 89.33
KNeighborsClassifier 88.06

TechStack Used:

1.Pytorch
3.Scikitlearn
4.Numpy
5.Pandas
2.Pytorch-Tabnet - https://arxiv.org/abs/1908.07442
6.NASA Open API - https://api.nasa.gov
7.NEO Earth Close Approches - https://cneos.jpl.nasa.gov/ca/

Support

⭐ Please Star and share the project. Thanks! ❤️

About

Machine Learning implementations to determine which Nearest Earth Objects are hazardous.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published