From the 1 of 3 linked papers with an AI index.
3 papers
HourGlass: A probabilistic data-driven temporal downscaler for global and regional weather forecasting
Magnus Sikora Ingstad, Mariana C. A. Clare, Olav Ersland +16
HourGlass is a probabilistic, data‑driven method that downscales 6‑hourly weather forecasts to hourly resolution, preserving small‑scale spatial detail and temporal consistency.
Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks
Ophélia Miralles, Máté Mile, Christoffer Artturi +2
Sparse point observations are increasingly available for precipitation nowcasting, but it is unclear how much they improve dense radar-field forecasts. We partially address this qu…
Observation-guided Interpolation Using Graph Neural Networks for High-Resolution Nowcasting in Switzerland
Ophélia Miralles, Daniele Nerini, Jonas Bhend +2
Recent advances in neural weather forecasting have shown significant potential for accurate short-term forecasts. However, adapting such gridded approaches to smaller, topographica…