[Full tuition fees and annual tax-free stipend of £22,780 for Home, EU and International students for 3.5 years.] This PhD studentship at Imperial College London focuses on the interaction between offshore wind farms and cloud formation, aiming to maximise wind farm performance using scientific machine learning. The project investigates how the operation of large offshore wind farms modifies the marine boundary layer (MBL), particularly in conditions conducive to marine stratocumulus (MS) cloud formation. The central research questions address whether turbine-driven changes in the MBL promote or hinder MS formation, and how these changes affect the local mesoclimate and wind farm power generation. The research employs high-fidelity large eddy simulation (LES) codes and scientific machine learning tools, including real-time optimisers, to simulate wind farms under various atmospheric inflows. Some code development will be required to implement actuator disc/line wind-turbine models. The project aims to develop SML-based strategies for discovering self-similarity laws, quantised local reduced order models, and real data assimilation. The successful candidate will join the research groups of Prof. Oliver Buxton (expert in turbulence, wind-energy flows, and turbulent cloud microphysics) and Prof. Luca Magri (expert in scientific machine learning for aeronautical applications). Both groups host ERC projects, offering opportunities for collaboration and interdisciplinary research. The studentship is fully funded for 3.5 years, covering tuition fees and providing a generous annual stipend of £22,780 for Home, EU, and International students. Applicants must hold or expect to hold a First class honours MEng/MSci or equivalent in Aeronautical/Mechanical Engineering or a related STEM field, and be willing to learn new skills. There may be opportunities for short-term collaboration with a group in The Netherlands. The application process involves submitting a CV, transcripts, and a motivation statement for supervisor review, followed by a formal application for long-listed candidates. Imperial College London is committed to diversity and inclusion, as reflected in its awards and partnerships.

[Full coverage of tuition fees and an annual tax-free stipend of £22,780 for Home, EU and International students.] This PhD studentship at Imperial College London focuses on developing real-time machine learning and optimisation systems to address extreme weather challenges in aeronautics. As climate change intensifies, atmospheric events such as turbulence, storms, and shifting jet streams increasingly threaten flight safety and efficiency, leading to fuel wastage, longer travel times, and greater environmental impact. The project aims to enable aircraft to reroute safely and efficiently in real time as weather conditions evolve, moving beyond conventional pre-flight planning. The research is structured into three main stages: First, the student will create a scalable, automated pipeline to collect and harmonise heterogeneous datasets from sources like OpenFlights, OpenSky Network, Aviation Weather Center, and ADS-B providers, integrating real-time flight trajectories, route networks, and high-resolution weather data. Second, machine learning models will be developed to analyse these integrated data streams, identifying early signs of weather-induced disruptions and forecasting hazards such as turbulence and storm activity using graph-based clustering, fuzzy machine learning, and reduced-order models. Third, the student will design adaptive algorithms within a bias-aware ensemble Kalman filter framework to dynamically propose alternative flight paths, maximising safety and fuel efficiency while minimising congestion and emissions. The final deliverable will be a user-friendly decision-support tool for real-time rerouting recommendations, directly supporting pilots and flight control operations. The project is supervised by Professor Luca Magri and offers full funding, including tuition and a generous stipend for Home, EU, and International students. The studentship lasts 3.5 years and is open to candidates with a strong computational background in engineering, physics, mathematics, or computer science, with a First class honours degree or equivalent. The research will contribute to sustainable aviation practices and climate-aware air traffic management, with models evolving through real-world updates. Imperial College London is committed to equality, diversity, and inclusion, and encourages applications from all backgrounds.

[Full tuition fees and annual tax-free stipend of £22,780 for Home, EU and International students.] This PhD studentship at Imperial College London offers a unique opportunity to investigate the complex interactions between offshore wind farms and cloud formation, with a focus on maximising wind farm performance using scientific machine learning. The project addresses how the operation of large offshore wind farms modifies the Marine Boundary Layer (MBL), influencing the formation of marine stratocumulus clouds and, in turn, affecting local mesoclimate and wind farm power generation. The research will use high-fidelity large eddy simulation (LES) codes and scientific machine learning tools, including real-time optimisers and actuator disc/line wind-turbine models, to simulate wind farms under various atmospheric conditions. The student will develop strategies for discovering self-similarity laws, quantised local reduced order models, and real data assimilation, gaining deep insight into the flow physics of cloud formation and wind energy. The successful candidate will be jointly embedded in the research groups of Prof. Oliver Buxton (expert in turbulence, wind-energy flows, and cloud microphysics) and Prof. Luca Magri (expert in scientific machine learning for aeronautical applications). Both groups host ERC projects, providing a vibrant and collaborative research environment. The studentship is fully funded for 3.5 years, covering tuition fees and providing a generous annual tax-free stipend of £22,780 for Home, EU, and International students. There is potential for international collaboration, including short research visits to The Netherlands. Eligibility requires a First class honours MEng/MSci or higher degree (or international equivalent) in Aeronautical/Mechanical Engineering or a closely related STEM field. Applicants should demonstrate strong academic performance and a willingness to learn new skills and techniques. The application process involves submitting a CV, transcripts, and a motivation statement for supervisor review, followed by a formal application for long-listed candidates. The deadline for applications is 8 January 2026. Imperial College London is committed to diversity and inclusion, holding Athena SWAN Silver, Stonewall Diversity Champion, and Disability Confident Employer status, and partnering with GIRES to promote respect for trans people.

[Full coverage of tuition fees and an annual tax-free stipend of £22,780 for Home, EU and International students.] PhD Studentship in Aeronautics: Real-time Machine Learning and Optimisation for Extreme Weather (AE0073) at Imperial College London offers a unique opportunity to address the challenges posed by climate change to aviation. As extreme atmospheric events such as turbulence, convective storms, and shifting jet streams become more frequent, flight safety and operational efficiency are increasingly threatened. These disruptions lead to flight diversions, increased fuel consumption, longer travel times, and greater environmental impact through contrail formation. This project aims to revolutionise flight planning and optimisation by developing real-time, adaptive decision-support systems. Traditional pre-flight planning methods are insufficient for the rapidly evolving weather systems. The research will model flight planning as a complex, dynamically interacting system using complexity theory, integrating scientific machine learning, real-world datasets, and real-time optimisation. The goal is to enable aircraft to reroute safely and efficiently as atmospheric conditions change, with tools that support on-the-fly decision-making and time series forecasting. Depending on the candidate’s background, there are opportunities to design quantum machine learning algorithms for forecasting chaotic and complex systems. The outcome will be a user-friendly system capable of real-time forecasting and adaptation, contributing to sustainable aviation by allowing continuous model updates from real-world data. The studentship is supervised by Professor Luca Magri and lasts 3.5 years. Funding includes full coverage of tuition fees and an annual tax-free stipend of £22,780 for Home, EU, and International students. Candidates must hold or expect to achieve a First class honours MEng/MSci or higher degree (or international equivalent) in a computational discipline such as engineering, physics, mathematics, or computer science. A strong academic record and motivation for research in aeronautics, machine learning, and optimisation are essential. Imperial College London is committed to equality, diversity, and inclusion, holding recognitions such as the Athena SWAN Silver Award and Stonewall Diversity Champion status. The application process involves submitting a CV, transcripts, and a motivation statement via the Supervisor Review Form by 8 January 2026. Long-listed candidates will be invited to formally apply. For project-specific questions, contact Professor Luca Magri; for application queries, reach out to Lisa Kelly, PhD Administrator. For more details and to apply, visit the Imperial College London Aeronautics PhD Opportunities page .