Weather-2K

Weather-2K is a benchmark dataset that contains reliable, real-time meteorological data collected hourly from 2,130 ground weather stations, featuring 20 meteorological variables and 3 positional constants, and is used to evaluate time series and spatio-temporal forecasting tasks in meteorology.

Papers using Weather-2K (2)

Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations2023 · 5 citesVN-Net: Vision-Numerical Fusion Graph Convolutional Network for Sparse Spatio-Temporal Meteorological Forecasting2024