The Role of XAI in Transforming Aeronautics and Aerospace Systems

TL;DR

This work addresses the need for interpretable AI in safety-critical aeronautics and aerospace. It defines XAI, clarifies model transparency categories and post-hoc techniques, and surveys domain applications. The main contributions include a taxonomy of XAI methods, a properties framework for interpretable models, and aerospace case studies (ATM, UAV routing, predictive maintenance, anomaly detection) demonstrating practical interpretability and trust. The findings highlight how XAI enables safer, regulator-friendly deployment of AI in aerospace and enhances human–AI collaboration in high-stakes settings.

Abstract

Recent advancements in Artificial Intelligence (AI) have transformed decision-making in aeronautics and aerospace. These advancements in AI have brought with them the need to understand the reasons behind the predictions generated by AI systems and models, particularly by professionals in these sectors. In this context, the emergence of eXplainable Artificial Intelligence (XAI) has helped bridge the gap between professionals in the aeronautical and aerospace sectors and the AI systems and models they work with. For this reason, this paper provides a review of the concept of XAI is carried out defining the term and the objectives it aims to achieve. Additionally, the paper discusses the types of models defined within it and the properties these models must fulfill to be considered transparent, as well as the post-hoc techniques used to understand AI systems and models after their training. Finally, various application areas within the aeronautical and aerospace sectors will be presented, highlighting how XAI is used in these fields to help professionals understand the functioning of AI systems and models.

Figures (1)

• Figure 1: Taxonomy of xai methods.