Explainable AI for Passenger Flow and Commercial Decision-Making in Complex Airport Systems The University of Manchester in United Kingdom

This PhD project at The University of Manchester focuses on advancing artificial intelligence (AI) methods for learning from multi-modal spatio-temporal data, particularly in contexts where uncertainty, sparsity, and heterogeneity challenge traditional approaches. The research aims to develop unified, interpretable frameworks that integrate diverse data types—such as spatial-temporal trajectories, multi-variate time series, and contextual information—to generate reliable insights and predictions. Key modelling paradigms to be explored include probabilistic deep learning, representation learning, and graph neural networks, with a strong emphasis on quantifying and explaining uncertainty to ensure outputs are transparent and actionable.

The project is closely partnered with Manchester Airports Group (MAG), providing access to rich, multi-source, industry-scale datasets and opportunities to validate models in collaboration with domain experts. The ideal candidate will have a first-class degree or distinction MSc in computer science, data science, statistics, geospatial science, management science, or engineering, along with skills in Python or R, machine learning (especially unsupervised and probabilistic methods), and an interest in applied optimisation and simulation. Strong communication skills are essential for working with industry partners and translating technical results into actionable insights.

The position is fully funded through the AI UKRI CDT 4-year program, covering home tuition fees and offering a tax-free stipend at the UKRI rate (£20,780 for 2025/26). The start date is September 2026. Applicants are encouraged to apply via the University of Manchester Application Portal, specifying the project and supervisor, and providing all required documents including transcripts, CV, supporting statement, and referee contact details.

The university is committed to equality, diversity, and inclusion, welcoming applicants from all backgrounds and offering flexible study options, including part-time. For further information, prospective students may contact Dr AH Hassanzadeh at [email protected].