Inspiration

Our project was inspired by the ongoing advancements in space exploration and the potential threats posed by near-Earth objects, especially asteroids. By identifying and classifying these hazards, we hope to contribute to the scientific community's understanding of asteroid risk levels and support early-warning systems that protect our planet.

What it does

This project classifies asteroid hazard levels on a scale from 0 to 4, with 0 representing minimal hazard and 4 indicating a significant threat. Using this system, researchers and organizations can better assess which asteroids require more immediate attention or mitigation.

How we built it

We implemented a k-nearest neighbors (KNN) algorithm to classify asteroid hazard levels based on a variety of factors, including asteroid velocity and diameter. The KNN model was trained to recognize patterns within these factors and assign each asteroid a hazard level score, allowing for more nuanced risk assessments.

Challenges we ran into

One of the key challenges was effectively plotting the data to visualize classifications and results. Visualizing hazard levels in a way that was clear, informative, and easily interpretable proved complex, but ultimately added valuable insights into our model's performance.

Accomplishments that we're proud of

We achieved an accuracy rate of 83.41% with our KNN model, which we’re proud of given the constraints of the data and the rapid pace of development. This accuracy highlights the model’s potential as a useful tool for asteroid classification.

What we learned

Through this project, we deepened our understanding of data visualization techniques, especially for scientific data related to astronomy. We also gained a stronger grasp of how KNN can be effectively applied in real-world applications, such as asteroid classification.

What's next for Classifying Asteroid Hazard Levels

Our next steps include expanding the dataset to improve model accuracy and exploring additional classification methods to refine our hazard level predictions further. We aim to increase the model’s precision and contribute to its application in planetary defense strategies.

Built With

• matplot
• python