Welcome reception 

Welcome

Opening keynote

Javier L. Massot, COO Cebu Pacific Air

Coffee break

Sponsor presentation: Accomodation Plus International (API)

Presentation slot

Presentation slot

Group photo shooting and lunch break

Technical presentation: One-shot optimisation: A framework for automated engine calibration and scenario management

Meherzad Lakadia

Optimisation engines have been used for decades in flight operations to automatically generate solutions following many different rules and priorities. While this work is done very well by most engines, there’s a lot more to the job than generating one solution with one set of rules and priorities.

It’s common to generate multiple solutions with different trade-offs to refine a solution for a particular instance, or to get insights on rule / parameter sensitivity. This requires extra engine calibration and scenario management (creation and comparison). Generally, this work is done by a team of analysts who need to understand both OR and flight operations.

In this presentation we propose a framework for automating a series of optimisations (including automation of parameter adjustments) to get the best solution, along with corresponding insights / justifications in “one shot”.

Sponsor presentation: Optimen

Sponsor presentations: TA Connections

Technical presentation: AI-Assisted Rule Interpretation and Application: Maximizing Operational Efficiency While Ensuring Compliance

Daniel Hoffmann, Tim Holmgren

The regulatory landscape in aviation is extensive and complex, with thousands of pages of legal text governing areas such as flight time limitations, fatigue management, and crew training. Identifying, interpreting, and synthesizing the applicable regulations in a given operational context is a cognitively demanding task, requiring manual cross-referencing across multiple regulatory documents. This challenge is particularly pronounced in crew planning and tracking, where precise and timely answers are required to support decision-making.

We present an AI-driven approach that leverages Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) to automate and enhance the retrieval and synthesis of regulatory information. Our method employs a multi-layered vector embedding strategy to improve document retrieval precision and utilizes an agentic framework that iteratively refines responses through structured LLM interactions. To ensure the reliability of generated outputs, we integrate a verification mechanism that programmatically displays referenced regulations, allowing users to assess the correctness of cited rules.

The system has been implemented and evaluated in the context of EASA crew regulations, demonstrating a significant reduction in research time while maintaining high interpretability and accuracy. We will provide an overview of the system’s design and approach, highlighting key retrieval strategies and refinement methods. Additionally, we will share insights into its effectiveness in addressing complex regulatory queries. The presentation will conclude with an analysis of the broader implications of AI-assisted regulatory interpretation in aviation and potential directions for further research.

Coffee break 

Presentation slot

Technical presentation: Instant Crew Production Need: Unlocking Leg-Based Rostering Efficiency

Kaj á Stongum, Lasse Raatz

This presentation explores the development and impact of CnEst, an innovative algorithm created by Lasse Raatz and Kaj á Stongum for Sunclass Airlines. By utilizing leg-based rostering and making strategic assumptions tailored to the specific challenge at hand, CnEst estimates crew requirements for Sunclass' peak summer schedule in just minutes—significantly reducing the time and effort previously needed for this process, which often took weeks or even months of manual calculations.

When compared to manually generated crew estimations of similar scenarios, CnEst shows a deviation of less than 1%, instilling confidence in its accuracy. Additionally, the algorithm has become a critical tool in union negotiations, enabling the simulation of rule changes and testing various operational scenarios.

CnEst aids in answering crucial operational questions, including optimal crew bases, staffing levels, and station assignments, providing data-driven insights to guide strategic decision-making.

Recap day 1 

Making sense of Fatigue Risk in Crew Rostering: Insights Beyond the Numbers

Simon Wickes

Biomathematical models estimate aircrew fatigue based on sleep-wake patterns, but fatigue scores alone may not fully capture operational risks. Fatigue-related incidents often result from complex duty characteristics that extend beyond cumulative sleep loss. Alternative approaches that integrate probabilistic associations between duty patterns and reportable incidents can allow for the identification of duties that may not appear highly fatiguing yet carry an elevated incident risk, or vice versa. By incorporating a broader risk perspective, this approach enhances fatigue management strategies and supports more effective operational decision-making, improving both safety and performance in safety-critical industries.

Sponsor presentation: WePlan

Sponsor presentation: Motulus

Presentation slot

Presentation slot

Coffee break 

Technical presentation: From emotional intelligence to artificial intelligence? Can crew members perspectives on crew planning change as technology evolves?

Steven Rushworth, Benjamin Algoet

What do the crew think and want from crew planning? A short presentation drawing on my experience presenting to, talking to and interviewing pilots and cabin crew about crew planning. The presentation will explore some of the common conceptions we have as crew planners, are they true or are they not? Some of the topics explored will be:

Do crew like the idea of mathematicians and optimizers planning their lives. Are we, crew planners, unrealistic in our expectations of crew? Do trade unions help or hinder?

Do crew planners get an unfair reputation amongst crew?

Looking forward: is the landscape changing in terms of both crew lifestyle expectations and also can AI change what can be delivered to crew. Can established AI techniques help deliver an improved experience for crew.

Sponsor presentation: AIMS

Sponsor presentation: Boeing

Technical presentation: <reserved>

Lunch

Social programme