sevir

This repository contains the dataset from the paper titled "Precipitation Nowcasting Based on Convolutional LSTM with Spatio-Temporal Information Transformation Using Multi-Meteorological Factors." The SEVIR (Storm Event Imagery) dataset is a publicly available, open dataset released and maintained by the MIT Lincoln Laboratory (https://registry.opendata.aws/sevir/, with a total size of approximately 480 GB). We did not create or modify any data; our research directly utilizes the original dataset. To avoid data redundancy and ensure that readers always access the most up-to-date authoritative version, we strongly recommend downloading from the official repository. Here are some examples of the datasets we provide.