Cosmic Threat Assessment

Inspiration The potential for a devastating asteroid impact is a persistent concern, motivating us to develop tools to understand and assess this risk.

What it does Cosmic Threat Assessment combines machine learning and scientific calculations to:

Predict the potential danger level of an asteroid impact using the Parmelo Index. Estimate the impact crater diameter, impact energy, and danger level of collision based on individual asteroid parameters. Identify the most dangerous asteroid within a specified timeframe.

How we built it We trained a Gradient Boost Regressor model using data from CNEOS JPL to predict the Parmelo Index. Developed separate calculations to estimate crater diameter, impact energy, and danger level based on established scientific formulas. Integrated these functionalities into a user-friendly interface.

Challenges we ran into Balancing accuracy and efficiency in the machine learning model. Finding clear and concise ways to present complex scientific concepts. Ensuring the reliability and robustness of the impact calculations.

Accomplishments that we're proud of Successfully combining machine learning with traditional scientific approaches for a comprehensive assessment tool. Creating a user-friendly platform to raise awareness and understanding of asteroid impact risks. Contributing to the ongoing efforts to mitigate and prepare for potential threats from space.

What's next for Cosmic Threat Assessment Refining the machine learning model for improved accuracy and broader applicability. Expanding the impact analysis capabilities to include additional factors influencing impact severity. Exploring potential collaborations with research institutions and space agencies.

By continuously developing and refining Cosmic Threat Assessment, we hope to empower individuals and organizations to better understand and prepare for potential asteroid impacts.

Built With

• numpy
• pandas
• python
• scikit-learn
• streamlit