PulseAugur
EN
LIVE 11:27:37

New high-resolution radar dataset aims to boost ML storm nowcasting

A new dataset called Storm250-L2 has been introduced, designed to improve machine learning models for precipitation nowcasting. This dataset, derived from NEXRAD Level-II and GridRad-Severe data, offers a higher resolution (250 m) compared to existing datasets like SEVIR and HKO-7. Storm250-L2 focuses on storm-centric, high-resolution radar reflectivity sequences to better model the short-term evolution of convective storms. The dataset includes thousands of storm events across the United States and is packaged in HDF5 tensors with metadata. AI

IMPACT This dataset could enable more accurate short-term weather predictions by providing higher-resolution radar data for ML models.

RANK_REASON The item describes a new dataset released via arXiv for machine learning research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New high-resolution radar dataset aims to boost ML storm nowcasting

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Andy Shi ·

    A Storm-Centric 250 m NEXRAD Level-II Dataset for High-Resolution ML Nowcasting

    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 …