Transforming Notams to Digital Notams: an Ai-Powered Approach to Enhance Aeronautical Information Management

A notice to air missions (NOTAM) is a document filed by an aviation authority with the purpose of informing the personnel concerned with flight operations of potential hazards, conditions or changes in status or procedure along a flight route or at an aeronautical facility of interest. NOTAMs present as semi-structured texts and generally follow certain conventions for syntax and semantics, but maintaining good data quality and consistency across different ANSPs is an ongoing challenge. Solutions such as business-rule validation and manual correction of erroneous NOTAMs are often unable to cope with the high volume of data being produced daily around the world. The answer to this problem lies in the digitization of these messages into Digital NOTAMs (DNOTAM), an enhanced, machine-readable version suited for automatic processing, since it features the AIXM 5.1 standard, a structured XML-based format. This paper introduces an automated method, leveraging Natural Language Processing (NLP) and Machine Learning (ML) techniques, to accurately interpret, classify, and transform free-text NOTAMs into a Digital NOTAM format. This approach significantly reduces or even eliminates the need for manual intervention, mitigates errors, and ensures that critical information is delivered in a format ready for modern aviation systems. The paper outlines the main stages of the transformation implemented in our system, starting with the pre-processing of the initial NOTAM, the text analysis and information extraction using specialized NLP techniques, the identification of aeronautical features, and finally, the process of compiling the information extracted or inferred from the NOTAM to produce a Digital NOTAM. Subsequently, we will discuss the benefits of our approach for solving some crucial NOTAM-related challenges and comment briefly on how such a process can be integrated with modern AIM systems to increase their efficiency. Finally, we will provide an outlook on some further directions for improvement and related research.