Research
My research is in probabilistic machine learning, organised around two methodological themes and the application areas where I put them to work.
Probabilistic machine learning and uncertainty
Gaussian processes, Bayesian inference (MCMC, variational and sequential Monte Carlo methods), probabilistic deep learning, and uncertainty quantification. A recurring question is how to get calibrated, decision-relevant uncertainty out of models of complex systems.
Time series and spatiotemporal learning
Forecasting and nowcasting, state-space models, temporal deep learning, and graph-based and spatiotemporal models for data such as radar and satellite image sequences, sensor networks, and power grids.
Applications
- Energy systems and the energy transition. Grid reliability, load and congestion forecasting, and synthetic energy data, largely with Alliander. See the SHARE project.
- Weather and climate. Precipitation nowcasting and forecasting with deep generative models, with KNMI.
- Other domains where decisions are made under uncertainty, including finance, biology, and mobility.
Publications
For the full list see my Google Scholar profile.
Some papers with code:
- Cambier van Nooten, C., Schreurs, K., Wijnands, J., Leijnse, H., Schmeits, M., Whan, K. & Shapovalova, Y. (2023). “Improving precipitation nowcasting for high-intensity events using deep generative models with balanced loss and temperature data: a case study in the Netherlands.” Artificial Intelligence for the Earth Systems. Code
- Shapovalova, Y., Eichler, M. (2023). “Measuring and Quantifying Uncertainty in Volatility Spillovers: A Bayesian Approach.” Data Science in Science, 2:1. Code
- Forbes Beadle, L., Love, J. C., Shapovalova, Y., Artemev, A., Rattray, M., & Ashe, H. L. (2023). “Combined modelling of mRNA decay dynamics and single-molecule imaging in the Drosophila embryo uncovers a role for P-bodies in 5′ to 3′ degradation.” PLOS Biology 21.1 (2023). Code
- Shapovalova, Y., Heskes, T. & Dijkstra, T. (2022) “Non-parametric synergy modeling of chemical compounds with Gaussian processes.” BMC Bioinformatics 23, 14. Code
- Shapovalova, Y. (2021) ““Exact” and Approximate Methods for Bayesian Inference: Stochastic Volatility Case Study.” Entropy 23.4: 466.
- Shapovalova, Y., Baştürk N., and Eichler, M. (2021) “Multivariate Count Data Models for Time Series Forecasting.” Entropy 23.6: 718. Code
- Almeida, R.J., Adriaans G., and Shapovalova Y. (2020) “Graphical Causal Models and Imputing Missing Data: A Preliminary Study.” International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems. Springer, Cham.