{"url":"/dataset/sevir","name":"SEVIR","full_name":"Storm EVent ImagRy","description_markdown":"**SEVIR** is an annotated, curated and spatio-temporally aligned dataset containing over 10,000 weather events that each consist of 384 km x 384 km image sequences spanning 4 hours of time. Images in SEVIR were sampled and aligned across five different data types: three channels (C02, C09, C13) from the GOES-16 advanced baseline imager, NEXRAD vertically integrated liquid mosaics, and GOES-16 Geostationary Lightning Mapper (GLM) flashes. Many events in SEVIR were selected and matched to the NOAA Storm Events database so that additional descriptive information such as storm impacts and storm descriptions can be linked to the rich imagery provided by the sensors.\r\n\r\nSource: [https://proceedings.neurips.cc//paper/2020/file/fa78a16157fed00d7a80515818432169-Paper.pdf](https://proceedings.neurips.cc//paper/2020/file/fa78a16157fed00d7a80515818432169-Paper.pdf)","description_withheld":null,"homepage":"https://registry.opendata.aws/sevir/","introduced_date":"2021-11-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/sevir-a-storm-event-imagery-dataset-for-deep","title":"SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology","first_author":"Mark Veillette","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Weather Forecasting","url":"/task/weather-forecasting","datasets_with_task":"/datasets/task/weather-forecasting"},{"name":"Precipitation Forecasting","url":"/task/precipitation-forecasting","datasets_with_task":"/datasets/task/precipitation-forecasting"}],"languages":[],"variants":["SEVIR"],"data_loaders":[{"repo":"https://github.com/MIT-AI-Accelerator/eie-sevir","url":"https://nbviewer.org/github/MIT-AI-Accelerator/eie-sevir/blob/master/examples/SEVIR_Tutorial.ipynb","frameworks":[]}],"num_papers_in_archive":33,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/weather-forecasting-on-sevir","task":"Weather Forecasting","dataset_variant":"SEVIR","rows":8,"metrics":["MSE","mCSI"],"first_row_in_archive_order":{"model":"IAM4VP","paper":"/paper/implicit-stacked-autoregressive-model-for-1","metrics":{"MSE":"2.9371","mCSI":"0.4607"},"code_links":[{"title":"seominseok0429/Implicit-Stacked-Autoregressive-Model-for-Video-Prediction","url":"https://github.com/seominseok0429/Implicit-Stacked-Autoregressive-Model-for-Video-Prediction"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/precipitation-forecasting-on-sevir","task":"Precipitation Forecasting","dataset_variant":"SEVIR","rows":1,"metrics":["CSI-pool16","CSI-pool4"],"first_row_in_archive_order":{"model":"PreDiff","paper":"/paper/prediff-precipitation-nowcasting-with-latent-1","metrics":{"CSI-pool16":"0.6244","CSI-pool4":"0.4624"},"code_links":[{"title":"gaozhihan/PreDiff","url":"https://github.com/gaozhihan/PreDiff"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/prediff-precipitation-nowcasting-with-latent-1","title":"PreDiff: Precipitation Nowcasting with Latent Diffusion Models","date":"2023-07-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":12,"samples_ran":9,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/implicit-stacked-autoregressive-model-for-1","title":"Implicit Stacked Autoregressive Model for Video Prediction","date":"2023-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/earthformer-exploring-space-time-transformers","title":"Earthformer: Exploring Space-Time Transformers for Earth System Forecasting","date":"2022-07-12","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rainformer-features-extraction-balanced","title":"Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting","date":"2022-03-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/predrnn-a-recurrent-neural-network-for","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","date":"2021-03-17","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/sevir-a-storm-event-imagery-dataset-for-deep","title":"SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology","date":"2020-12-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/disentangling-physical-dynamics-from-unknown","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","date":"2020-03-03","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/eidetic-3d-lstm-a-model-for-video-prediction","title":"Eidetic 3D LSTM: A Model for Video Prediction and Beyond","date":"2019-05-01","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":3,"samples_harvested":24,"samples_ran":19,"samples_unverified":5,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}