Western Kentucky University
Grade Level at Time of Presentation
Senior
Major
Business Data Analytics
Institution 24-25
Western Kentucky University
KY House District #
2
KY Senate District #
32
Faculty Advisor/ Mentor
Lily Popova Zhuhadar, PhD.
Department
Analytics & Information Systems
Abstract
Predicting Hazardous Near-Earth Objects Using Machine Learning for Planetary Defense
This research develops a machine learning model to classify Near-Earth Objects (NEOs) as hazardous or non-hazardous based on their physical and orbital characteristics, leveraging NASA's dataset of certified NEOs. NEOs, including asteroids and comets, often pass within close proximity to Earth, and while most pose no threat, some have the potential for catastrophic impacts. By using predictive models such as decision trees and random forests, this study aims to prioritize resources for monitoring and mitigation of high-risk objects. The model incorporates key features like velocity, diameter, and proximity to Earth to assess potential hazards. The results demonstrate the efficacy of machine learning in planetary defense, providing data-backed insights that help space agencies and planetary defense teams identify which NEOs require closer monitoring.
Why This Research is Important to Share with State Legislators
This research is crucial to share with state legislators as it highlights the potential for leveraging machine learning in planetary defense strategies, ensuring the safety of communities worldwide. With increased monitoring of NEOs and early hazard identification, states can contribute to global efforts in mitigating the risks posed by these objects. Policymakers can use this data-driven approach to guide funding and resource allocation for planetary defense programs, emphasizing the importance of supporting innovative, cost-effective solutions that can protect Earth from potential threats. This research also aligns with legislative priorities of promoting science, technology, and public safety, underscoring the role of state-level engagement in addressing global challenges.
Predicting Hazardous Near-Earth Objects Using Machine Learning for Planetary Defense
Predicting Hazardous Near-Earth Objects Using Machine Learning for Planetary Defense
This research develops a machine learning model to classify Near-Earth Objects (NEOs) as hazardous or non-hazardous based on their physical and orbital characteristics, leveraging NASA's dataset of certified NEOs. NEOs, including asteroids and comets, often pass within close proximity to Earth, and while most pose no threat, some have the potential for catastrophic impacts. By using predictive models such as decision trees and random forests, this study aims to prioritize resources for monitoring and mitigation of high-risk objects. The model incorporates key features like velocity, diameter, and proximity to Earth to assess potential hazards. The results demonstrate the efficacy of machine learning in planetary defense, providing data-backed insights that help space agencies and planetary defense teams identify which NEOs require closer monitoring.
Why This Research is Important to Share with State Legislators
This research is crucial to share with state legislators as it highlights the potential for leveraging machine learning in planetary defense strategies, ensuring the safety of communities worldwide. With increased monitoring of NEOs and early hazard identification, states can contribute to global efforts in mitigating the risks posed by these objects. Policymakers can use this data-driven approach to guide funding and resource allocation for planetary defense programs, emphasizing the importance of supporting innovative, cost-effective solutions that can protect Earth from potential threats. This research also aligns with legislative priorities of promoting science, technology, and public safety, underscoring the role of state-level engagement in addressing global challenges.