PhD Studentship in Aeronautics: Real-time machine learning and optimisation for extreme weather (AE0073)

PhD Studentship in Aeronautics: Real-time machine learning and optimisation for extreme weather (AE0073)

Start Date: Between 1 August 2026 and 1 July 2027

Introduction: Climate change is transforming the skies. Extreme atmospheric events, e.g., sudden turbulence, convective storms, or shifting jet streams, pose risks to flight safety and efficiency. These weather disruptions force aircraft to divert, burn excess fuel, extend travel times, and generate more contrails, which increases aviation’s environmental footprint. Conventional pre-flight planning can no longer keep up with the speed and intensity of these changes.

This PhD project will ultimately enable aircraft to reroute safely and efficiently in real time as weather evolves. By merging scientific machine learning, large-scale data integration, and real-time optimisation, the project will ultimately help develop an adaptive system that helps pilots and controllers make smarter decisions mid-flight.

The research will advance through three core stages:

1. Data Integration and Preprocessing: Develop a scalable, automated pipeline to collect, synchronise, and merge heterogeneous datasets from sources including OpenFlights, OpenSky Network, Aviation Weather Center, and ADS-B providers. This harmonised dataset will seamlessly connect real-time flight trajectories, dynamic route networks, and high-resolution weather information.
2. Predictive Modelling of Weather Impacts: Build machine learning models that analyse these integrated data streams to identify early precursors of weather-induced disruptions. The goal is to forecast turbulence zones, storm activity, and other hazards using graph-based clustering, fuzzy machine learning, and reduced-order models – delivering scientific insight into where and when rerouting is needed.
3. Real-Time Decision-Making and Route Optimisation: Develop adaptive algorithms within a bias-aware ensemble Kalman filter framework to propose alternative flight paths dynamically. The system will aim to maximise safety and fuel efficiency while minimising congestion and emissions, offering direct support to pilots and flight control operations.

The final outcome will be a user-friendly decision-support tool that provides real-time rerouting recommendations. Beyond the PhD, the project’s data-driven models will evolve through continuous real-world updates, contributing to sustainable aviation practices and climate-aware air traffic management.

Supervisors: Prof. Luca Magri

Duration: 3.5 years.

Funding: Full coverage of tuition fees and an annual tax-free stipend of £22,780 for Home, EU and International students.

Eligibility: Due to the competitive nature of these studentships, candidates will be expected to achieve/have achieved a First class honours MEng/MSci or higher degree (or international equivalent) in a Computational background: engineering, physics, maths, or computer science.

How to apply:

• Stage 1: Submit your 2-page curriculum vitae (CV), transcripts and a 300-word statement explaining your motivation for applying to this PhD Studentship to: Supervisor Review Form. Our supervisors will perform a comprehensive review to long-list candidates.

Deadline: 8 January 2026

• Stage 2: Supervisors will email further instructions and an application link to long-listed candidates, inviting them to make a formal application to the PhD Studentship.

Contact: For questions about the project: Prof. Luca Magri

For queries regarding the application process, email Lisa Kelly, PhD Administrator

Equality, Diversity and Inclusion: Imperial is committed to equality and valuing diversity. We are an Athena SWAN Silver Award winner, a Stonewall Diversity Champion, a Disability Confident Employer and are working in partnership with GIRES to promote respect for trans people.

Advert information