The research paper “A Machine Learning-Based Study on the Estimation of the Threat Posed by Orbital Debris” by Suhani Srivastava focuses on classifying the threat level of orbital debris using machine learning models. The study aims to provide insights into effectively estimating the danger posed by specific orbital debris to future space missions. As the space industry grows, the increasing amount of orbital debris in Low Earth Orbit (LEO) becomes a significant concern for space missions. Traditional physics-based methods for detecting and identifying orbital debris characteristics are becoming less feasible. Therefore, this research proposes the use of machine learning as a more efficient and convenient alternative.
The study evaluated multiple machine learning models and found that the logistic regression model performed the best, achieving a 98% accuracy rate. The findings offer valuable insights into the accuracy of different machine learning models in classifying orbital debris. The research aims to assist space shuttle manufacturers in mitigating risks associated with orbital debris, contributing to improved Space Situational Awareness (SSA).
