A Bibliometric Mapping of Digital Twins and AI: Scientific Trends and Research Frontiers
Abstract
This study examines the literature on integrating digital twins and artificial intelligence using bibliometric data to analyze productivity and collaboration. It presents publication distribution by year, leading countries, institutions, and authors, and identifies research trends through keyword and thematic cluster analyses. The results highlight the increasing importance of this integration and the growing trend of international collaboration. Data were collected on June 23, 2025, from the Web of Science Core Collection using the query ‘(TI=(Digital Twin) AND TS=(artificial intelligence)) AND (DT==(“ARTICLE”))’, yielding 657 articles analyzed with VOSviewer (v1.6.20). Findings show that authors such as Tao and Fei, despite few publications, have high influence, while Fan and Zhong gained recognition with a single highly cited study. Strategic connectors include Wang, Fei-Yue, and Lv, while Zhang and Meng serve as “hidden stars.” Institutionally, NTNU stands out for centrality, while Nanjing University of Aeronautics and Astronautics leads in publication quantity but lags in impact. China dominates output, while the U.S., the U.K., and Canada excel in collaborative efforts. Thematic results reveal applications across manufacturing, healthcare, engineering, and city management, supported by machine learning, deep learning, 6G, and edge computing, as well as important social aspects like ethics and governance.
Keywords
Digital Twin , Artificial Intelligence , Bibliometric Analysis , VOSviewer
References
- [1] S. R. Newrzella, S. Haider, and D. W. Franklin, "5-dimension cross-industry digital twin applications model and analysis of digital twin classification terms and models," IEEE Access, vol. 9, pp. 131306–131321, 2021. doi: 10.1109/access.2021.3115055
- [2] A. Fuller, C. Day, Z. Fan, and C. Barlow, "Digital twin: Enabling technologies, challenges and open research," IEEE Access, vol. 8, pp. 108952–108971, 2020. doi: 10.1109/access.2020.2998358
- [3] A. M. Madni, S. D. Lucero, and C. C. Madni, "Leveraging digital twin technology in model-based systems engineering," Systems, vol. 7, no. 1, p. 7, 2019. doi: 10.3390/systems7010007
- [4] A. F. Mendi, D. Dogan, and T. Erol, "Digital twin in the military field," IEEE Internet Computing, vol. 26, no. 5, pp. 33–40, 2021. doi: 10.1109/mic.2021.3055153
- [5] M. Bahl, "AI: A primer for breast imaging radiologists," Journal of Breast Imaging, vol. 2, no. 4, pp. 304–314, 2020. doi: 10.1093/jbi/wbaa033
- [6] S. Legg and M. Hutter, "Universal intelligence: A definition of machine intelligence," Minds and Machines, vol. 17, no. 4, pp. 391–444, 2007. doi: 10.1007/s11023-007-9079-x
- [7] P. N. Ramkumar et al., "Sports medicine and AI: A primer," The American Journal of Sports Medicine, vol. 50, no. 4, pp. 1166–1174, 2021. doi: 10.1177/03635465211008648
- [8] M. Bearman, R. Ajjawi, and J. Ryan, "Discourses of AI in higher education: A critical literature review," Higher Education, vol. 86, no. 2, pp. 369–385, 2022. doi: 10.1007/s10734-022-00937-2
- [9] M. Groshev et al., "Toward intelligent cyber-physical systems: Digital twin meets AI," IEEE Communications Magazine, vol. 59, no. 8, pp. 14–20, 2021. doi: 10.1109/mcom.001.2001237
- [10] M. J. Kaur, V. P. Mishra, and P. Maheshwari, "The convergence of digital twin, IoT, and machine learning: Transforming data into action," in Springer, pp. 3–17, 2019. doi: 10.1007/978-3-030-18732-3_1
