WeatherBench 2: A Benchmark for the Next Generation of Data‐Driven Global Weather Models
Stephan Rasp, Stephan Hoyer, Alexander Merose, Ian Langmore, Peter Battaglia, Tyler Russell, Álvaro Sánchez‐González, Vivian Yang, Robert W. Carver, Shreya Agrawal, Matthew Chantry, Zied Ben Bouallègue, Peter Dueben, Carla Bromberg, Jared Sisk, Luke Barrington, Aaron J. Bell, Fei Sha
Abstract
Abstract WeatherBench 2 is an update to the global, medium‐range (1–14 days) weather forecasting benchmark proposed by (Rasp et al., 2020, https://doi.org/10.1029/2020ms002203 ), designed with the aim to accelerate progress in data‐driven weather modeling. WeatherBench 2 consists of an open‐source evaluation framework, publicly available training, ground truth and baseline data as well as a continuously updated website with the latest metrics and state‐of‐the‐art models: https://sites.research.google/weatherbench . This paper describes the design principles of the evaluation framework and presents results for current state‐of‐the‐art physical and data‐driven weather models. The metrics are based on established practices for evaluating weather forecasts at leading operational weather centers. We define a set of headline scores to provide an overview of model performance. In addition, we also discuss caveats in the current evaluation setup and challenges for the future of data‐driven weather forecasting.