WeatherBench

WeatherBench is a benchmark dataset used to evaluate the performance of weather forecasting models, specifically focusing on short-term predictions and their accuracy in terms of root mean squared error.

Papers using WeatherBench (4)

Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific2026Probabilistic Forecasting for Dynamical Systems with Missing or Imperfect Data2025 · 1 citesPINT: Physics-Informed Neural Time Series Models with Applications to Long-term Inference on WeatherBench 2m-Temperature Data2025 · 1 citesNumerical Weather Forecasting using Convolutional-LSTM with Attention and Context Matcher Mechanisms2021 · 3 cites