Industrial PhD: Aviation Operational Data, Intelligence & Environmental Impact

We are seeking a PhD candidate to develop data-driven methods for reconstructing, monitoring and analysing aviation operations from heterogeneous operational datasets.  The initial application will focus on assessing and monitoring aviation environmental impacts, including non-CO₂ climate effects and contrails.

The research will form part of an Industrial PhD between Applied Innovative Methods (AI Methods) and Universidad Carlos III de Madrid, and will sit at the intersection of aviation operations, data science, climate impact and decision-support systems.

What you will work on

The candidate will develop the data and analytical methods required to transform large volumes of aviation operational data into operational and environmental intelligence. The work is expected to include:

• Processing and integrating large aviation datasets, including  aircraft trajectory, flight-plan, airspace, meteorological and other operational datasets. 

• Reconstructing historical flight operations and operational events from heterogeneous data sources. 

• Developing aviation performance and environmental KPIs at flight, airport, airspace and network level. 

• Connecting aircraft trajectories with meteorological and atmospheric information to estimate environmental effects, initially including contrail and non-CO₂ climate impact. 

• Developing methods for monitoring, reporting and verification (MRV) of aviation environmental impacts. 

• Building scalable pipelines for historical analysis and near-real-time monitoring. 

• Identifying patterns linking environmental conditions, operational decisions and observed outcomes. 

• Developing statistical and machine-learning methods to characterise operational impact and support future decision-making. 

• Contributing to the development of AI Methods' Review and Monitor operational-intelligence capabilities. 

• Working with aviation stakeholders and real operational use cases to validate the research. 

The work will initially concentrate on climate-related aviation applications, but the methods developed will be applicable to broader operational disruptions including weather, capacity constraints and network operations.

Essential

• Master's degree qualifying for admission to a PhD programme in Aerospace Engineering, Computer Science, Data Science, Applied Mathematics, Physics, Transport Engineering or a closely related field. 

• Strong Python skills

• Experience applying machine-learning methods to real-world data

• Experience working with large, imperfect datasets. 

• Good foundations in statistics/data analysis. 

• Ability to design reproducible data pipelines rather than only notebooks. 

• Strong analytical and research capability. 

• Professional English. 

Very valuable

• Aviation/ATM/airline operations knowledge. 

• Experience with aircraft trajectory or ADS-B data. 

• Geospatial and time-series data processing. 

• Pandas/Polars, GeoPandas, xarray, SQL/PostgreSQL/PostGIS. 

• APIs and cloud-based data pipelines. 

• Familiar with aviation datasets (EUROCONTROL, OpenSky, Cirium, FlightRadar/FlightAware) 

• Flight-performance modelling. 

• Machine learning applied to spatiotemporal data. 

• Knowledge of contrails/non-CO₂ aviation climate effects