Guardado en:
Detalles Bibliográficos
Autores principales: Rasp, Stephan, Hoyer, Stephan, Merose, Alexander, Langmore, Ian, Battaglia, Peter, Russel, Tyler, Sanchez-Gonzalez, Alvaro, Yang, Vivian, Carver, Rob, Agrawal, Shreya, Chantry, Matthew, Bouallegue, Zied Ben, Dueben, Peter, Bromberg, Carla, Sisk, Jared, Barrington, Luke, Bell, Aaron, Sha, Fei
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2308.15560
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913210627522560
author Rasp, Stephan
Hoyer, Stephan
Merose, Alexander
Langmore, Ian
Battaglia, Peter
Russel, Tyler
Sanchez-Gonzalez, Alvaro
Yang, Vivian
Carver, Rob
Agrawal, Shreya
Chantry, Matthew
Bouallegue, Zied Ben
Dueben, Peter
Bromberg, Carla
Sisk, Jared
Barrington, Luke
Bell, Aaron
Sha, Fei
author_facet Rasp, Stephan
Hoyer, Stephan
Merose, Alexander
Langmore, Ian
Battaglia, Peter
Russel, Tyler
Sanchez-Gonzalez, Alvaro
Yang, Vivian
Carver, Rob
Agrawal, Shreya
Chantry, Matthew
Bouallegue, Zied Ben
Dueben, Peter
Bromberg, Carla
Sisk, Jared
Barrington, Luke
Bell, Aaron
Sha, Fei
contents 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, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_15560
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle WeatherBench 2: A benchmark for the next generation of data-driven global weather models
Rasp, Stephan
Hoyer, Stephan
Merose, Alexander
Langmore, Ian
Battaglia, Peter
Russel, Tyler
Sanchez-Gonzalez, Alvaro
Yang, Vivian
Carver, Rob
Agrawal, Shreya
Chantry, Matthew
Bouallegue, Zied Ben
Dueben, Peter
Bromberg, Carla
Sisk, Jared
Barrington, Luke
Bell, Aaron
Sha, Fei
Atmospheric and Oceanic Physics
Artificial Intelligence
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, 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.
title WeatherBench 2: A benchmark for the next generation of data-driven global weather models
topic Atmospheric and Oceanic Physics
Artificial Intelligence
url https://arxiv.org/abs/2308.15560