arXiv:2510.16031v2 Announce Type: replace-cross Abstract: Machine learning-based precipitation nowcasting relies on high-fidelity radar reflectivity sequences to model the short-term evolution of convective storms. However, the development of models capable of predicting extreme weather has been constrained by the coarse resolution (1-2 km) of existing public radar datasets, such as SEVIR, HKO-7, and GridRad-Severe, which smooth the fine-scale structures essential for accurate forecasting. To address this gap, we introduce Storm250-L2, a storm-centric radar dataset derived from NEXRAD Level-II
The increasing availability of high-resolution radar data and advancements in machine learning techniques are enabling more granular weather modeling.
Improved high-resolution precipitation nowcasting is critical for managing extreme weather events, which are becoming more frequent and severe globally.
The prior limitation of coarse radar data for training sophisticated ML nowcasting models is being addressed, enabling more precise predictions of short-term storm evolution.
- · Machine learning researchers
- · Meteorological agencies
- · Disaster preparedness organizations
- · Climate risk modelers
- · Legacy weather forecasting models reliant on lower resolution data
- · Sectors unprepared for rising climate volatility
More accurate localized short-term weather predictions reduce immediate risks from convective storms.
Enhanced nowcasting capabilities support more efficient resource allocation for emergency services and agricultural planning.
The application of similar high-resolution data and ML techniques could extend to other complex environmental modeling problems, further improving climate resilience.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG