Elizaveta Semenova is a machine learning researcher at the University of Oxford working at the intersection of Bayesian inference, deep generative modelling, spatiotemporal statistics and epidemiology. Prior to this post she was a Research Associate at Imperial College London, Department of Mathematics, Statistics section, did a postdoc in Bayesian Machine Learning at AstraZeneca R&D and a PhD in epidemiology at the Swiss Tropical and Public Health Institute.
AI2050 Project
In this fellowship, Elizaveta will be working on a new generation of disease and environment surveillance systems able to quickly inform policymakers and communities at risk with high spatial and temporal granularity. Elizaveta will tackle two crucial building blocks of spatiotemporal disease surveillance: cost-effective collection of high-quality data and its efficient analysis. Elizaveta will pioneer a novel approach to disease mapping, i.e. representation of disease’s geographical distribution by combining the rigour of classical spatial statistics and computational power of deep learning.
Project Artifacts
J.A. Bouman, A. Hauser, S.L. Grimm, M. Wohlfender, S. Bhatt, E. Semenova, A. Gelman, C.L. Althaus, J. Riou. Bayesian workflow for time-varying transmission in stratified compartmental infectious disease transmission models. PLOS Computational Biology. 2024.
E. Semenova, S. Mishra, S. Bhatt, S. Flaxman, .H.J.T Unwin. Deep Learning and MCMC with aggVAE for Shifting Administrative Boundaries: Mapping Malaria Prevalence in Kenya. Springer, Cham. 2024.
J. L.H. Tsui, M. Zhang, P. Sambaturu, S. Busch-Moreno, M.A. Suchard, O.G. Pybus, S. Flaxman, E. Semenova, M. U.G. Kraemer. Optimal disease surveillance with graph-based Active Learning. medRxiv. 2024.
T. Rawson, W. Hinsley, R. Sonabend, E. Semenova, A. Cori, N.M. Ferguson. The impact of health inequity on spatial variation of COVID-19 transmission in England. PLOS Computational Biology. 2024.
J. Magomere, S. Ishida, T. Afonja, A. Salama, D. Kochin, F. Yuehgoh, I. Hamzaoui, R. Sefala, A. Alaagib, E. Semenova, L. Crais, S.M. Hall. You are what you eat? Feeding foundation models a regionally diverse food dataset of World Wide Dishes. arXiv. 2024.
AI2050 Community Perspective — Elizaveta Semenova (2024)
E. Semenova, M. Cairney-Leeming, and S. Flaxman. PriorCVAE: scalable MCMC parameter inference with Bayesian deep generative modelling. arXiv. 2023.