DrElizaveta Semenova

I am an Assistant Professor in Biostatistics, Computational Epidemiology and Machine Learning at the School of Public Health, Imperial College London, and a Schmidt Sciences AI2050 Early Career Fellow.

My previous research positions include: Schmidt Sciences AI2050 Early Career Fellow (2023–2024) and Postdoctoral Researcher (2022–2023) at the Department of Computer Science, University of Oxford; Postdoctoral Research Associate (2021–2022) in the Statistics Section, Department of Mathematics, Imperial College London; Postdoctoral Fellow in Bayesian Machine Learning at AstraZeneca R&D (2019–2021, Cambridge, UK); and PhD candidate in Epidemiology and Biostatistics at the Swiss Tropical and Public Health Institute (2019, Basel, Switzerland).

My work centres on
(i) scalable and flexible methods for spatiotemporal statistics and Bayesian machine learning,
(ii) surrogate models and approximate Bayesian inference, and
(iii) adaptive sampling design and data collection, with applications in epidemiology.

Most recently, I have focused on using deep generative modelling to accelerate MCMC inference in classical spatial statistics, and on adaptive survey design for resource-efficient data collection.

More broadly, my interests lie at the interface of methodological innovation and real-world impact. Methodologically, they include Bayesian spatiotemporal modelling, Gaussian Processes, generative models, compartmental models, and adaptive survey design. My main application areas are epidemiology, toxicology, and public-policy decision support.