Page 12 - IJAMD-2-1

International Journal of AI for
Materials and Design
Utilizing AI for NTSB UAV accident categorization

and robustness. Additional research could employ a similar 2. The data analysis scripts for this paper are available at
process to explore socioeconomic factors associated with https://doi.org/10.5281/zenodo.10576209.
such occurrences.
Further disclosure
7. Conclusion Part of findings has been presented in a conference “ERAU
This research demonstrates the significant potential of AI Discovery Days” (https://commons.erau.edu/discovery-
in categorizing and analyzing UAV accident reports. By day/db-discovery-day-2024/poster-session-2/54/).
leveraging OpenAI’s GPT-4 and various data visualization
tools, we have identified patterns and trends in UAV References
accidents, highlighting the primary causes and their 1. Pik E. Commercial and Recreational Active UAV Fleet in the
geographic and temporal distributions. Our findings U.S. 2016-2022; 2024.
underscore the importance of addressing system and doi: 10.5281/zenodo.10573914
component failures to improve UAV safety. The use of AI
and data visualization not only streamlines the analysis 2. Ferrigan J. Safety Risk Assessment for UAV Operation; 2022.
Available from: https://www.regulations.gov/document/faa-
process but also provides valuable insights that can inform 2022-0426-0004 [Last accessed on 2024 Jan 15].
safety policies and regulatory measures. The integration
of these technologies is crucial for advancing UAV safety 3. Zhang X, Srinivasan P, Mahadevan S. Sequential deep
research and enhancing the overall safety standards in the learning from NTSB reports for aviation safety prognosis.
UAV industry. Moving forward, continuous improvement Saf Sci. 2021;142:105390.
of AI models and data collection methods will be essential doi: 10.1016/j.ssci.2021.105390
to keep pace with the rapidly evolving UAV landscape, 4. Yang C, Huang C. Natural language processing (NLP) in
ensuring that safety measures remain robust and effective. aviation safety: Systematic review of research and outlook
into the future. Aerospace. 2023;10(7):600.
Acknowledgments
doi: 10.3390/aerospace10070600
None.
5. Kasprzyk PJ, Konert A. Reporting and investigation of
Funding unmanned aircraft systems (UAS) accidents and serious
incidents. Regulatory perspective. J Intell Robot Syst.
None. 2021;103(1):3.
Conflict of interest doi: 10.1007/s10846-021-01447-6
6. Nguyen C, Sagan V, Bhadra S, Moose S. UAV multisensory
The authors declare that they have no competing interests. data fusion and multi-task deep learning for high-throughput
maize phenotyping. Sensors (Basel). 2023;23(4):1827.
Author contributions
doi: 10.3390/s23041827
Conceptualization: Eugene Pik
Formal analysis: Joao S. D. Garcia 7. Nanyonga A, Wild G. Impact of Dataset Size and Data
Source on Aviation Safety Incident Prediction Models with
Investigation: Eugene Pik Natural Language Processing. In: 2023 Global Conference
Methodology: Eugene Pik on Information Technologies and Communications (GCITC);
Writing – original draft: Eugene Pik 2023. p. 1-7.
Writing – review & editing: Joao S. D. Garcia
doi: 10.1109/GCITC60406.2023.10426284
Ethics approval and consent to participate 8. Lázaro FL, Madeira T, Melicio R, Valério D, Santos LFFM.
Not applicable. Identifying human factors in aviation accidents with
natural language processing and machine learning models.
Consent for publication Aerospace. 2025;12(2):106.
doi: 10.3390/aerospace12020106
Not applicable.
9. New MD, Wallace RJ. Classifying aviation safety reports:
Availability of data Using supervised natural language processing (NLP) in an
Applied Context. Safety. 2025;11(1):7.
1. The original data presented in this study are
openly accessible at https://www.ntsb.gov/Pages/ doi: 10.3390/safety11010007
AviationQueryV2.aspx. 10. Sarkar NI, Gul S. Artificial Intelligence-based autonomous

Volume 2 Issue 1 (2025) 6 doi: 10.36922/ijamd.8544