A Storm-Centric 250 m NEXRAD Level-II Dataset for High-Resolution ML Nowcasting
This dataset addresses the need for high-resolution radar data to improve extreme weather forecasting for meteorologists and researchers, but it is incremental as it builds on existing data sources.
The paper tackles the problem of coarse resolution in existing public radar datasets for machine learning-based precipitation nowcasting by introducing Storm250-L2, a storm-centric dataset with 250 m resolution derived from NEXRAD Level-II and GridRad-Severe data, comprising thousands of storm events across the continental United States.
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 and GridRad-Severe data. We algorithmically crop a fixed, high-resolution (250 m) window around GridRad-Severe storm tracks, preserve the native polar geometry, and provide temporally consistent sequences of both per-tilt sweeps and a pseudo-composite reflectivity product. The dataset comprises thousands of storm events across the continental United States, packaged in HDF5 tensors with rich context metadata and reproducible manifests.