3 papers
cs.CV2025
Time-aware UNet and super-resolution deep residual networks for spatial downscaling
Mika Sipilä, Sabrina Maggio, Sandra De Iaco +3
Satellite data of atmospheric pollutants are often available only at coarse spatial resolution, limiting their applicability in local-scale environmental analysis and decision-maki…
stat.ML2025
Identifiable Autoregressive Variational Autoencoders for Nonlinear and Nonstationary Spatio-Temporal Blind Source Separation
Mika Sipilä, Klaus Nordhausen, Sara Taskinen
The modeling and prediction of multivariate spatio-temporal data involve numerous challenges. Dimension reduction methods can significantly simplify this process, provided that the…
stat.ME2024
Modelling multivariate spatio-temporal data with identifiable variational autoencoders
Mika Sipilä, Claudia Cappello, Sandra De Iaco +2
Modelling multivariate spatio-temporal data with complex dependency structures is a challenging task but can be simplified by assuming that the original variables are generated fro…