Towards Improved Precipitation Prediction: From Efficient Forecasting to Operational Robustness
PhD defence, Wednesday 2 December 2026, Rafael Pablos Sarabia
During his PhD studies, Rafael Pablos Sarabia investigated how deep learning methods can improve high-resolution precipitation prediction. Rafael Pablos Sarabia developed efficient methods for forecasting precipitation, reconstructing precipitation fields from sparse observations, and producing reliable forecasts when some data sources are unavailable. The research particularly improves the prediction of rare and intense precipitation events while reducing computational requirements.
The new research findings contribute to more accurate, efficient and robust precipitation forecasting, with potential applications in early warning, agriculture, energy management and other areas affected by intense rainfall.
The PhD study was completed at Department of Computer Science, Faculty of Natural Sciences, Aarhus University.
This summary was prepared by the PhD student.
Time: Wednesday, 2 December 2026 at 13:00
Place: Building 5335, room 295, Department of Computer Sciences, Aarhus University, Helsingforsgade 12 , 8200 Aarhus N
Title of PhD thesis: Deep Learning Methods for Precipitation Prediction: Forecasting, Reconstruction, and Operational Robustness
Contact information: Rafael Pablos Sarabia, e-mail: rpablos@cs.au.dk, tel.: +45 55252324
Members of the assessment committee:
Senior Research Scientist Leif Denby, Weather Research Unit of the Danish Meteorological Institute, Denmark
Professor Thomas B Moeslund, The Technical Faculty of IT and Design, Aalborg University, Denmark
Associate Professor Sophia Yakoubov (chair), Department of Computer Science, Aarhus University, Denmark
Main supervisor: Professor Ira Assent, Department of Computer Science, Aarhus University, Denmark
Co-supervisor:
Joachim Nyborg, Cordulus, Denmark
Morten Birk, Cordulus, Denmark
Language: The PhD dissertation will be defended in English
The defence is public.
The PhD thesis is available for reading at the Graduate School of Natural Sciences/GSNS, Ny Munkegade 120, building 1521, 8000 Aarhus C