Natural Language Processing (NLP) in Aviation Safety: Systematic Review of Research and Outlook into the Future

Yang, Chuyang; Huang, Chenyu

doi:10.3390/aerospace10070600

Cited by 19 publications

(10 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The systematic review [2] investigates natural language processing (NLP) applications in aviation safety domains from 2010-2022. The study highlights specific NLP techniques, their performance, current challenges, and potential future advancements for enhancing aviation safety and efficiency.…”

Section: Ai In Aviation Safetymentioning

confidence: 99%

“…The rapid advancement and adoption of artificial intelligence technologies are fundamentally transforming the landscape of the aviation industry [1]. From flight planning to aircraft maintenance, AI-driven tools like machine learning, natural language processing, and computer vision are being integrated across nearly every aspect of modern aviation [2]. While AI innovation holds great promise for augmenting human capabilities and enhancing safety and efficiency, it also poses new challenges for aviation education and training.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in Aviation: New Professionals for New Technologies

Kabashkin,

Misnevs,

Zervina

2023

Applied Sciences

View full text Add to dashboard Cite

Major aviation organizations have highlighted the need to adopt artificial intelligence (AI) to transform operations and improve efficiency and safety. However, the aviation industry requires qualified graduates with relevant AI competencies to meet this demand. This study analyzed aviation engineering bachelor’s programs at European universities to determine if they are preparing students for AI integration in aviation by incorporating AI-related topics. The analysis focused on program descriptions and syllabi using semantic annotation. The results showed a limited focus on AI and machine learning competencies, with more emphasis on foundational digital skills. Reasons include the newness of aviation AI, its specialized nature, and implementation challenges. As the industry evolves, dedicated AI programs may emerge. But currently, curricula appear misaligned with stated industry goals for AI adoption. The study provides an analytical methodology and competency framework to help educators address this gap. Producing graduates equipped with AI literacy and collaboration skills will be key to aviation’s intelligent future.

show abstract

Section: Ai In Aviation Safetymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence in Aviation: New Professionals for New Technologies

Kabashkin,

Misnevs,

Zervina

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…All of this is made possible by using a neutral language/taxonomy that facilitates modeling for both events and day-to-day operations. Natural language processing (NLP) approaches applied to areas related to aviation safety are considered in [4]. Problems and limitations of current applications of NLP in aviation are discussed, such as ambiguity, limited training data, lack of multilingual support.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Determining possibilities for applying theoretical principles of situational risk management in the aviation safety system

Bugayko,

Ponomarenko,

Sokolova

et al. 2023

EEJET

View full text Add to dashboard Cite

Aviation safety is one of the main criteria for its sustainable development. The object of this study is safety risk management, which is the main tool of the aviation safety management system. The problem that needs to be further solved is the improvement of aviation risk management methods under war, force majeure, and crisis conditions, as well as under conditions of uncertainty, when there is a minimum of time to make a single correct decision. The theory of situational management can be chosen as the theoretical basis for creating decision-making systems. The development of special languages for describing the situation arising at the control object, as well as in its control system, makes it possible to correctly represent the models of control objects and the evolution of knowledge about them. The work solves the task of building a model of the control object, which takes into account the maximum number of its features suitable for implementation. In order to represent the management object based on the method of expert assessments, the weighting coefficients of the risk characteristics’ probabilities and the values of the weighting coefficients of the degrees of severity were calculated, a matrix of risk assessment indicators was built, and risk assessment criteria were developed. Based on the calculations, general approaches to aviation safety risk management were specified. The paper developed a «dramatic script» of an episode of aviation security risk management, which includes the stages of the episode, the content of necessary actions, the corresponding stages of aviation security risk management and the corresponding aviation security risk management. The content of the management itself consists in preventing the transition from the zone of acceptable risk to the zone of permissible and from the zone of permissible risk to the zone of unacceptable risk, as well as the implementation of measures to stimulate the transition from the zone of unacceptable to the zone of permissible risk and from the zone of permissible to the zone of acceptable risk

show abstract

“…Despite the abundance of research and literature in the domain of aviation safety analysis [42,43], the application of generative language models remains largely unexplored within this field.…”

Section: Nlp In Aviation Safety Analysismentioning

confidence: 99%

Examining the Potential of Generative Language Models for Aviation Safety Analysis: Case Study and Insights Using the Aviation Safety Reporting System (ASRS)

Tikayat Ray,

Bhat,

White

et al. 2023

Aerospace

View full text Add to dashboard Cite

This research investigates the potential application of generative language models, especially ChatGPT, in aviation safety analysis as a means to enhance the efficiency of safety analyses and accelerate the time it takes to process incident reports. In particular, ChatGPT was leveraged to generate incident synopses from narratives, which were subsequently compared with ground-truth synopses from the Aviation Safety Reporting System (ASRS) dataset. The comparison was facilitated by using embeddings from Large Language Models (LLMs), with aeroBERT demonstrating the highest similarity due to its aerospace-specific fine-tuning. A positive correlation was observed between the synopsis length and its cosine similarity. In a subsequent phase, human factors issues involved in incidents, as identified by ChatGPT, were compared to human factors issues identified by safety analysts. The precision was found to be 0.61, with ChatGPT demonstrating a cautious approach toward attributing human factors issues. Finally, the model was utilized to execute an evaluation of accountability. As no dedicated ground-truth column existed for this task, a manual evaluation was conducted to compare the quality of outputs provided by ChatGPT to the ground truths provided by safety analysts. This study discusses the advantages and pitfalls of generative language models in the context of aviation safety analysis and proposes a human-in-the-loop system to ensure responsible and effective utilization of such models, leading to continuous improvement and fostering a collaborative approach in the aviation safety domain.

show abstract

Natural Language Processing (NLP) in Aviation Safety: Systematic Review of Research and Outlook into the Future

Cited by 19 publications

References 62 publications

Artificial Intelligence in Aviation: New Professionals for New Technologies

Artificial Intelligence in Aviation: New Professionals for New Technologies

Determining possibilities for applying theoretical principles of situational risk management in the aviation safety system

Examining the Potential of Generative Language Models for Aviation Safety Analysis: Case Study and Insights Using the Aviation Safety Reporting System (ASRS)

Contact Info

Product

Resources

About