Currently, a significant number of artificial objects have accumulated in the Earth’s orbit, the majority of which are classified as space debris. A number of databases provide descriptions of these space objects and their parameters. By using and analyzing this data, new information about space debris can be obtained. Recently, artificial intelligence capabilities have also been employed for the purpose of detailed statistical processing. In the study of space debris and satellites in the Earth orbit, machine learning techniques, such as classification, clustering, and statistical analysis, can be highly effective for analyzing and predicting various characteristics of these objects. In our research, machine learning models were developed to classify and cluster objects in the Earth’s orbit based on their radar cross-section (RCS) size and various orbital parameters. The models demonstrated high accuracy in distinguishing between different types of objects and identifying debris clusters. This illustrates the potential of machine learning methods for enhancing our understanding and management of space debris, which is crucial for ensuring the security and sustainability of space activities. In general, the utilization of machine learning in the study of space debris provides valuable insights and tools for tracking, analyzing, and mitigating the risks associated with the increasing number of objects in the Earth’s orbit.