Research
Predictive deep learning that respects physical constraints, for industrial time series, weather and climate, and physics.
Research lines
What we work on
Digital industry
Integrative AI that combines deep learning and formal methods; predictive maintenance and condition monitoring; physics-informed models, differentiable surrogates and foundation models for multivariate time series.
Weather and climate
Precipitation nowcasting from weather radar, early-warning systems, deep-learning downscaling of forecasts and climate scenarios, and better parametrisations for Earth system models.
Physics
Automatic pruning of neural networks, space weather and ionospheric monitoring, and forecasting of geomagnetic storms.