Martin Buchli

Martin has worked on projects at major European airports and airlines with a strong focus on developing data-driven solutions to enhance operations. With strong data analytics skills, he completed a comprehensive MBA-like program from SWISS and ETH, in addition to his PhD in physics, and has a solid background in software development and project management. As an aviation enthusiast, he is currently pursuing an ATPL (A) frozen license to enhance his qualifications.

---

Enhancing operational resilience: ML model for runway capacity forecasting

Zurich Airport experiences significant disruptions due to meteorological phenomena like the Bise wind, which notably reduces runway capacity, leading to frequent flight delays and operational challenges for airlines. In response, a machine learning (ML) model to forecast runway capacity shortages has been developed. This model analyzes meteorological data to provide critical insights for runway concepts, thus enhancing the decision-making process. By improving operational resilience through forecasts, the model aids aviation stakeholders in navigating the increasing frequency of adverse weather conditions, ultimately aiming to minimize disruptions and enhance overall flight efficiency at Zurich Airport.

The audience will learn:

• Weather impact: understanding how meteorological phenomena like the Bise wind significantly affect runway capacity and flight operations
• Machine learning applications: utilizing ML models to analyze weather data can enhance predictive capabilities for operational challenges in aviation
• Decision-making enhancement: critical probability insights from ML models improve operational resilience in response to adverse weather conditions