Flight Safety Data Storytelling: Continuous Learning From What Went Right

Authors

Barth Baron Jr., San José State University
Melissa Peterson, San José State University

Document Type

Article

Publication Date

2025

Abstract

The anticipated increase in air traffic, airspace complexity, and safety datavolume inspired the development of an In-time Aviation Safety ManagementSystem (IASMS). Evolving from the legacy Safety Management System (SMS),IASMS will use machine learning (ML) to improve current risk management andsafety assurance methodologies, predict future threats, and reduce analysis andresponse times. We propose applying the IASMS concept to directly supportskilled performance in real-time with an interactive safety visualization tool forpilots. This tool would analyze disparate data sets to reveal latent operationalthreats and provide examples of skilled performance adaptations. Pilots wouldaccess tailored ML-enabled predictive data narratives through a user-centeredinterface. Challenges with using ML in this context, data integration, and interfacedesign are discussed.

Comments

Presented at the 23rd International Symposium on Aviation Psychology, May 27-30, 2025, Hosted by Oregon State University

Repository Citation

Baron, B., & Peterson, M. (2025). Flight Safety Data Storytelling: Continuous Learning From What Went Right. Proceedings of the 23rd International Symposium on Aviation Psychology, 42-47.
https://corescholar.libraries.wright.edu/isap_2025/8