WeatherBench 2: A benchmark for the next generation of data-driven global weather models

• Published in: arXiv.org
• Main Authors: Rasp, Stephan, Hoyer, Stephan, Merose, Alexander, Langmore, Ian, Battaglia, Peter, Tyler, Russel, Sanchez-Gonzalez, Alvaro, Yang, Vivian, Carver, Rob, Agrawal, Shreya, Chantry, Matthew, Zied Ben Bouallegue, Dueben, Peter, Bromberg, Carla, Sisk, Jared, Barrington, Luke, Bell, Aaron, Sha, Fei
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 26.01.2024
• Subjects: Benchmarks; Mathematical models; State of the art; Weather forecasting

WeatherBench 2 is an update to the global, medium-range (1-14 day) weather forecasting benchmark proposed by Rasp et al. (2020), designed with the aim to accelerate progress in data-driven weather modeling. WeatherBench 2 consists of an open-source evaluation framework, publicly available training,...