Phase of Flight Classification in Aviation Safety using LSTM, GRU, and BiLSTM: A Case Study with ASN Dataset

TL;DR

This study explores the use of deep learning models like LSTM, GRU, and BiLSTM to classify the phase of flight from unstructured accident narratives, aiming to improve aviation safety analysis.

Contribution

It evaluates and compares the performance of various RNN-based models and their combinations in classifying flight phases from accident reports using NLP techniques.

Findings

BiLSTM achieved 64% accuracy in classification.

Combined models like LSTM-BiLSTM improved accuracy to 67%.

Models demonstrated capacity to classify flight phases from raw text.

Abstract

Safety is the main concern in the aviation industry, where even minor operational issues can lead to serious consequences. This study addresses the need for comprehensive aviation accident analysis by leveraging natural language processing (NLP) and advanced AI models to classify the phase of flight from unstructured aviation accident analysis narratives. The research aims to determine whether the phase of flight can be inferred from narratives of post-accident events using NLP techniques. The classification performance of various deep learning models was evaluated. For single RNN-based models, LSTM achieved an accuracy of 63%, precision 60%, and recall 61%. BiLSTM recorded an accuracy of 64%, precision 63%, and a recall of 64%. GRU exhibited balanced performance with an accuracy and recall of 60% and a precision of 63%. Joint RNN-based models further enhanced predictive capabilities. GRU-LSTM, LSTM-BiLSTM, and GRU-BiLSTM demonstrated accuracy rates of 62%, 67%, and 60%, respectively, showcasing the benefits of combining these architectures. To provide a comprehensive overview of model performance, single and combined models were compared in terms of the various metrics. These results underscore the models' capacity to classify the phase of flight from raw text narratives, equipping aviation industry stakeholders with valuable insights for proactive decision-making. Therefore, this research signifies a substantial advancement in the application of NLP and deep learning models to enhance aviation safety.