Catalogue of Possibilities / Supervisors

Prof Philipp Otto he/him

Developing statistical and machine learning methods for spatiotemporal and network data with applications in environmental science, engineering and economics

Professor of Statistics and Data Science

School of Mathematics and Statistics

Research interests:

Spatiotemporal statistics, Statistical process control, Environmetrics, Statistical learning, Data science, Spatial econometrics, Panel data, Data-driven analysis, Forecasting

Research fields:

Air quality, Environment, Empirical analysis, Georeferenced data, Statistics, Network analysis/interactions, Change point detection, Structural breaks, Time series analysis

Mission Priority Areas

Why do you want to join the DiveIn community?

I am keen to join the DiveIn CDT as a supervisor because its mission—to prioritise diversity and interdisciplinarity—resonates strongly with my research and mentoring practice. I currently lead a group of PhD students from diverse cultural, ethnic, and academic backgrounds, and I am actively involved in international initiatives to strengthen mathematical sciences globally, with a focus on Africa. My research in spatial statistics and data science spans environmental, financial, and technological applications. I see DiveIn as a unique opportunity to support and inspire students from underrepresented backgrounds as they tackle pressing interdisciplinary challenges in AI, Net Zero, and beyond.

Personal profile:

My research sits at the interface of spatial statistics, data science, and interdisciplinary applications in environmental, economic, and engineering systems. I am particularly passionate about modelling complex spatiotemporal processes—whether air pollution, housing dynamics, or financial contagion—using both classical statistical approaches and modern machine learning techniques. My group develops methods that are rigorous, interpretable, and applicable to real-world data, often combining stochastic modelling, regularisation, and distributional regression frameworks.

Currently, I supervise a diverse group of PhD students with backgrounds in mathematics, engineering, computer science, and environmental science. Our projects span hybrid statistical learning for air quality, compositional time series in regional economies, and network-based risk modelling in finance. I am part of an international network promoting mathematical sciences for sustainable development.

I would welcome new collaborations through the CDT around network modelling, environmental modelling, e.g., air or soil quality, and change point detection. I’m particularly interested in interdisciplinary projects that connect statistical science with domain expertise in sustainability, public health, or economics.

As a supervisor, I am supportive, hands-on when needed, and committed to developing the academic independence of my students. Several of my former students now work in academia or data-intensive industry roles. I value curiosity, persistence, and collaboration, and I aim to create an environment where students feel challenged and supported in equal measure.

Equity, diversity and inclusion are central to my academic practice. I actively promote inclusive recruitment and mentoring, serve as a mentor in widening participation initiatives, and regularly support visiting researchers from underrepresented regions. I strive to maintain a research group culture where everyone’s contributions and perspectives are valued.

Outside academia, I enjoy life with my young family, outdoor adventures in the Scottish Highlands. I believe that diverse life experiences enrich scientific thinking—and that creating space for these within academia is essential for real innovation.

https://www.gla.ac.uk/schools/mathematicsstatistics/staff/philippotto/