Abstract
The management of NOTAMs on the flight deck remains a challenge for flight crews, who must process large volumes of dense textual information to identify the notices relevant to their mission. Despite ongoing modernisation efforts, the NOTAM system still relies on a legacy format with limited support for automated filtering and prioritisation, which increases pilot workload and motivates the use of Natural Language Processing techniques for information management. This paper presents an NLP framework based on a shared pre-trained BERT encoder with two task-specific prediction heads, designed to support NOTAM analysis at different stages of the flight. The first task classifies each NOTAM into one of 20 operational categories to support pre-flight briefing. The second task estimates the operational severity of a NOTAM under three emergency diversion scenarios to support in-flight decision-making within cockpit decision-support systems. To address the lack of annotated data and the imbalance across categories, a dataset of 3,000 NOTAMs was built by combining expert annotation with synthetic samples generated under human supervision. The proposed framework, based on a DistilBERT encoder fine-tuned with LoRA, achieves a macro F1-score of 0.97 on classification and R² values at or above 0.80 across the three severity scenarios.