Machine Learning Insights into Hypersonics Research Evolution: A 21st Century Perspective


  • Ashkan Ebadi Digital Technologies, National Research Council Canada, Canada
  • Alain Auger Science and Technology Foresight and Risk Assessment Unit, Defence Research and Development Canada, Canada
  • Yvan Gauthier Digital Technologies, National Research Council Canada, Canada



hypersonics, research evolution, temporal change, natural language processing, machine learning, structural topic modeling


In recent years, the field of hypersonics has witnessed substantial growth in research and development activities, driven by its diverse range of applications spanning both military and commercial sectors. Governments and private companies in several countries have made substantial investments in hypersonic technologies to gain a competitive edge, secure or enhance strategic capabilities, and bolster deterrence measures. In this rapidly evolving landscape, the ability to swiftly and accurately identify emerging technologies becomes paramount. Leveraging the advancements in information technology and computer science, which enable the analysis of vast datasets and the extraction of concealed trends and patterns, this study aims to provide valuable insights to decision-makers in the hypersonics domain. Our focus is on scientific publications related to hypersonics, encompassing the years 2000 to 2020. We employ state-of-the-art natural language processing and machine learning techniques to comprehensively characterize the research landscape. The urgency of this endeavor lies in the necessity for organizations to remain at the forefront of hypersonic research. By algorithmically identifying and tracking 12 key latent research themes and examining their temporal evolution, we offer a structured and objective analysis of the field. Our methodology eliminates subjectivity from the assessment, facilitating consistent comparisons both across topics and across different time intervals. In addition, through our extensive publication similarity analysis, we uncover nuanced patterns that shed light on the cyclical nature of research trends over the two decades under investigation. This comprehensive examination of the hypersonics research landscape not only underscores its critical significance but also provides a robust foundation for informed decision-making. As such, our study serves as a valuable resource for stakeholders seeking to navigate the dynamics of the rapidly advancing field of hypersonics effectively.


Received: 2 August 2023 | Revised: 25 September 2023 | Accepted: 12 October 2023


Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.


Data Availability Statement

Data are retrievable by running the search query mentioned in the manuscript on the data source, i.e., Scopus. In addition, the raw data can be made available upon request. Please contact the corresponding author.




How to Cite

Ebadi, A., Auger, A., & Gauthier, Y. (2023). Machine Learning Insights into Hypersonics Research Evolution: A 21st Century Perspective. Archives of Advanced Engineering Science, 2(2), 79–92.