Research fields:
- Rainfall observation with opportunistic sensors (CML, SML and PWS)
- Merging weather radar and ground-based sensors
- Deep Learning methods for quantitative precipitaiton estimation
- Deep Learning for post-processing atmospheric model output
Current projects as PI:
- MERGOSAT - Merging of rain rate estimates from opportunistic sensors and geostationary satellites
- RealPEP - Near-Realtime Quantitative Precipitation Estimation and Prediction (project website)
Other current projects:
- HoWa-PRO - Innovative methods of precipitation measurement and forecasting in use for early flood warning in small catchments (project website)
- OpenSense COST Action - Opportunistic Precipitation Sensing Network (project website)
Former projects as PI:
- RESEAD - Robust Environmental Sensor data using Explainable data-driven Anomaly Detection
- SpraiLINK - Spatial rainfall estimates using improved observations from commercial microwave links and statistical data fusion