Page 7 - IJAMD-2-1

International Journal of AI for
Materials and Design

PERSPECTIVE ARTICLE
Utilizing artificial intelligence for National

Transportation Safety Board unmanned aerial
vehicle accident analysis and categorization

1
Eugene Pik * and Joao S. D. Garcia 2
1 Mevocopter Aerospace, Vaughan, Ontario, Canada
2 DB-School of Graduate Studies, Embry-Riddle Aeronautical University, Daytona Beach, Florida,
United States of America

Abstract

The rapid increase in unmanned aerial vehicle (UAV) usage has introduced significant
safety challenges, including issues such as system failure, loss of control, transmission
failures, and collisions. Analyzing these incidents has been challenging due to the
absence of a dedicated category field in the National Transportation Safety Board
(NTSB) data. This research tackles this problem by utilizing artificial intelligence (AI)
to automate the classification of UAV accident reports collected between 2006 and
2023. Using natural language processing techniques, we categorize NTSB reports to
improve the analysis and interpretation of incident data. We also employ advanced
data visualization tools to reveal geographic and temporal patterns, offering a
*Corresponding author:
Eugene Pik detailed view of UAV accident trends. The results indicate that system and component
(eugene.pik@mevocopter.com) failures unrelated to propulsion systems (system/component failure or malfunction
[non-powerplant]) and abnormal contact upon landing (abnormal runway contact)
Citation: Pik E, Garcia JSD.
Utilizing artificial intelligence are predicted as the primary categories (37%) of UAV accidents for the period. These
for National Transportation insights suggest the potential value of AI-driven categorization and visualization
Safety Board unmanned aerial techniques in enhancing UAV safety standards and supporting policy development.
vehicle accident analysis and
categorization. Int J AI Mater Initial results provide promising insight into the use of language models for text
Design. 2025;2(1):1-7. classification in aviation safety problems.
doi: 10.36922/ijamd.8544
Received: January 15, 2025
Keywords: UAV accident analysis; AI categorization; GPT-4 analysis; Data visualization in
Revised: February 11, 2025 safety; NTSB accident data; Accident trend analysis
Accepted: February 18, 2025
Published online: February 28,
2025 1. Introduction
Copyright: © 2025 Author(s).
This is an Open-Access article The use of unmanned aerial vehicles (UAVs) has seen a dramatic increase in recent years.
distributed under the terms of the The commercial UAV fleet in the United States expanded from 42,000 in 2016 to 349,000
Creative Commons Attribution
1
License, permitting distribution, in 2023, representing a staggering 731% increase. This surge in UAV usage brings with it
and reproduction in any medium, some safety concerns, including loss of control, transmission failures, navigation system
provided the original work is 2
properly cited. malfunctions, and collisions with aircraft, buildings, and power lines. In addition,
severe weather events, take-off and landing incidents, and rotor failures have also been
Publisher’s Note: AccScience
Publishing remains neutral with mentioned as relevant to safety in UAV operations.
regard to jurisdictional claims in
published maps and institutional With the increase in operations, UAV-related accidents have also escalated, creating
affiliations. the need for improved categorization and understanding of these incidents to support

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