Skip to content

Machine Learning models for classifying Near-Earth Objects (NEOs) as hazardous or non-hazardous.

Notifications You must be signed in to change notification settings

deji-dylan/NEO-Hazard-Classification

Repository files navigation

NEO-Hazard-Classification

ASTROGUARD: An Investigation Into Machine Learning Algorithms for Classifying Near Earth Objects

Project Overview

This project explores the use of machine learning algorithms to classify Near-Earth Objects (NEOs) as hazardous or non-hazardous. The aim is to leverage a dataset of tracked NEOs to build predictive models that can enhance our understanding of potential risks posed by these objects. This initiative is inspired by the increasing importance of monitoring space objects for Earth’s safety and space exploration.

Dataset

The dataset used in this project is sourced from Kaggle, provided by Sameep Vani, and includes detailed features of NEOs tracked by NASA. These objects, including asteroids, meteors, satellites, and space debris, are labeled based on their potential threat to Earth.

Key Features:

Diameter Velocity Distance from Earth Orbital characteristics Classification labels (hazardous or non-hazardous)

Installation and Setup

To run this project locally:

Clone the repository: git clone https://github.com/deji-dylan/NEO-Hazard-Classification.git

Install the required dependencies: pip install -r requirements.txt

Open the notebook:

jupyter notebook Navigate to Machine_Learning_Algorithms_for_Classifying_NEOs.ipynb and run the cells sequentially.

Usage

This project is structured to:

Preprocess the dataset for exploratory data analysis (EDA) and visualization.

Train and evaluate multiple machine learning algorithms for classification.

Generate reports on model performance and identify the most effective algorithm for the task.

Example usage:

Modify the dataset to include updated observations.

Fine-tune the parameters for better performance.

Extend the analysis with additional features.

Key Features

Comprehensive EDA to understand NEO characteristics.

Comparison of various machine learning models (e.g., Decision Trees, Random Forests, Neural Networks).

Customizable pipeline for future data integration.

Contributing

Contributions are welcome! To contribute:

Fork the repository.

Create a new branch:

git checkout -b feature-name

Make your changes and commit them:

git commit -m "Description of changes"

Push to the branch: git push origin feature-name Open a Pull Request.

About

Machine Learning models for classifying Near-Earth Objects (NEOs) as hazardous or non-hazardous.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published