SESAR - Single European Sky ATM Research

06/11/2025 | News release | Distributed by Public on 06/11/2025 16:40

SynthAIr wraps up with expert insights on AI safety in aviation

The SESAR Joint Undertaking's SynthAIr project aims to address the limited availability of high-quality data for training reliable, safety-critical AI systems. By supporting the development of synthetic data and robust AI models, SynthAIr is helping to build a foundation for the trustworthy integration of AI across the aviation sector.

On 4 June, the project held its third and final Advisory Board meeting, marking the end of its research activities. The three-hour virtual event brought together consortium partners and aviation experts to review project outcomes and take part in a practical workshop focused on AI-related risks.

The session was structured around five key parts. Highlights included the presentation of results from six core use cases: turnaround time, delay prediction, flight diversion, flight schedule generation, synthetic traffic generation and passenger flow forecasting. Each segment provided an overview of the models developed, data sources used, final results and key recommendations, followed by an open Q&A. These outcomes will be featured in the project's final deliverable, the Exploratory Research Results report, which is currently being finalised.

A central feature of the meeting was an interactive one-hour workshop using the Miro platform. Participants were invited to identify and prioritise potential risks linked to the use of AI and machine learning in aviation. Based on the Taxonomy for AI Hazards Analysis (TAIHA; M.L. Cummings, 2025), the exercise explored four areas: AI oversight, design, maintenance and testing. Insights from the workshop will contribute to the final mapping of risks and mitigations included in the project's closing report.

The session also offered a platform to discuss the practical applications of SynthAIr's research in real-world air traffic management environments. Contributions from Advisory Board members, including reflections shared during earlier meetings, have played a key role in shaping the operational perspective presented in the final results.

With this final event, SynthAIr wraps up its research journey by delivering not only a suite of tested AI models but also a structured approach for assessing and managing AI risks in aviation. These achievements support the SESAR 3 JU vision for a safe, scalable and transparent integration of AI into future ATM systems.

More about the project
Follow SynthAIr on LinkedIn

SESAR - Single European Sky ATM Research published this content on June 11, 2025, and is solely responsible for the information contained herein. Distributed via Public Technologies (PUBT), unedited and unaltered, on June 11, 2025 at 22:40 UTC. If you believe the information included in the content is inaccurate or outdated and requires editing or removal, please contact us at support@pubt.io