{"success":true,"data":{"author":"Ziye Wang, Yiran Qin, Lin Zeng, Ruimao Zhang","bucketAccessType":"public","bucketName":"Ziyeeee/3D-NEXRAD","bucketPrefix":"","category":"Climate & Weather","cloudProvider":"huggingface","createdAt":"2026-11-21T20:46:01.375Z","description":"Three-dimensional gridded weather radar observations of severe storm events across the United States, built for radar sequence prediction and weather nowcasting by Wang, Qin, Zeng and Zhang (ICLR 2025, arXiv:2502.14895). The data were re-collected and preprocessed from GridRad-Severe, the three-dimensional gridded NEXRAD WSR-88D radar product for severe events at the NCAR Research Data Archive (DOI 10.5065/2B46-1A97, CC BY 4.0). Each event is a sequence of 25 frames spanning 125 minutes (5-minute interval) with 512 x 512 horizontal pixels and 28 vertical levels (0.5 to 7 km every 0.5 km, then 7 to 22 km every 1 km), covering 2020 to 2022. Seven radar variables are provided: reflectivity, velocity spectrum width, azimuthal shear and radial divergence of the radial velocity, differential reflectivity (ZDR), specific differential phase (KDP) and copolar correlation coefficient. Files are yearly split tar.gz archives (nexrad-YYYY.tar.gz.00 and so on, about 141 GB); concatenate and extract them. Use it to train 3D radar extrapolation, storm evolution and Gaussian-splatting style spatiotemporal models. Released under CC BY 4.0; cite Wang et al. 2025 and GridRad-Severe.","displayTitle":"3D-NEXRAD: 3D Gridded WSR-88D Radar Sequences of US Severe Storms for Precipitation Nowcasting (GridRad-Severe, 2020-2022)","huggingFaceUrl":"https://huggingface.co/datasets/Ziyeeee/3D-NEXRAD","id":"15b24fed-73a0-5d8d-a502-b7cf5a9a06f3","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/Ziyeeee/3D-NEXRAD","objectCountEstimate":17,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2502.14895","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Ziyeeee/3D-NEXRAD\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Ziyeeee/3D-NEXRAD\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Ziyeeee, license:cc-by-4.0, downloads=444"],"format":"mixed","generatedAt":"2026-11-21T20:48:53.756Z","layout":{"example":"2020/nexrad-2020.tar.gz.00","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"2020/nexrad-2020.tar.gz.00","truncatedAt":512}],"sampleObjects":["2020/nexrad-2020.tar.gz.00","2020/nexrad-2020.tar.gz.01","2020/nexrad-2020.tar.gz.02","2020/nexrad-2020.tar.gz.03","2020/nexrad-2020.tar.gz.04"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntags:\n- 3D\n- Radar\n- Prediction\n---\n\n# Dataset Card for 3D-NEXRAD\n\n<!-- Provide a quick summary of the dataset. -->\n\n3D gridded radar reflectivity data collected from the U.S.NEXRAD WSR-88D radar network. \n\n## Dataset Description\n\n<!-- Provide a longer summary of what this dataset is. -->\n\n\nThe **3D-NEXRDA** dataset comprises 3D radar observations of severe storm events across the United States, with each event captured at different geographic locations. \nThe dataset provides high-resolution insights into storm dynamics with high temporal and spatial resolution.\n\n- **Temporal Coverage:**\n\n  - **Time Span:** 2020.01.01 - 2022.12.31\n \n  - **Interval and Event Duration:** 25 frames for each sequence spanning a period of 125 minutes per event\n\n  **we are actively working to expand this dataset to cover the period from 2020 to 2022**\n\n- **Spatial Dimensions:**\n\n  - **Horizontal Resolution:** 512 × 512 for Each observation frame\n\n  - **Vertical Resolution:** 28 levels, from 0.5 km to 7 km with 0.5 km intervals, and from 7 km to 22 km with 1 km intervals\n \n  - **Available Variables:** 7 radar variables:\n\n    - Radar Reflectivity\n    - Velocity Spectrum Width\n    - Azimuthal Shear of the Radial Velocity\n    - Radial Divergence of the Radial Velocity\n    - Differential Radar Reflectivity\n    - Specific Differential Phase\n    - Copolar Correlation Coefficient\n\n- **Data Source:**\n\n  This dataset was re-collected, collated and pre-processed from: \n\n  GridRad-Severe - Three-Dimensional Gridded NEXRAD WSR-88D Radar Data for Severe Events. Research Data Archive at the National Center for Atmospheric Research, Computational and Information Systems Laboratory. Dataset. https://doi.org/10.5065/2B46-1A97. Accessed† 26 Nov 2024.\n\n- **License:** cc-by-4.0\n\n## Uses\n\n#### Download and extract\n\n```\ncat nexrad-[YYYY].tar.gz.* | tar -zxv -C [your_dataset_dir]/\n```\n\n\n## Citation\n\n\n```\n@inproceedings{\n    wang2025highdynamic,\n    title={High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation},\n    author={Ziye Wang and Yiran Qin and Lin Zeng and Ruimao Zhang},\n    booktitle={The Thirteenth International Conference on Learning Representations},\n    year={2025},\n    url={https://openreview.net/forum?id=Cjz9Xhm7sI}\n}\n```\n\n```\n@misc{wang2025highdynamicradarsequenceprediction,\n      title={High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation}, \n      author={Ziye Wang and Yiran Qin and Lin Zeng and Ruimao Zhang},\n      year={2025},\n      eprint={2502.14895},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV},\n      url={https://arxiv.org/abs/2502.14895}, \n}\n```","encoding":"utf8","key":"README.md","name":"README.md","size":2728,"truncated":false}],"sourceObjectKey":"2020/nexrad-2020.tar.gz.00","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"Ziyeeee/3D-NEXRAD\", filename=\"2020/nexrad-2020.tar.gz.00\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"2020/nexrad-2020.tar.gz.00","totalObjects":17},"summary":"Three-dimensional gridded weather radar observations of severe storm events across the United States, built for radar sequence prediction and weather nowcasting by Wang, Qin, Zeng…","title":"3D-NEXRAD: 3D Gridded WSR-88D Radar Sequences of US Severe Storms for Precipitation Nowcasting (GridRad-Severe, 2020-2022)","updatedAt":"2026-11-21T21:58:03.307Z","visibility":"public","websiteUrl":"https://gdex.ucar.edu/datasets/d841006/"}}