Articles | Volume 11, issue 10
https://doi.org/10.5194/gmd-11-3999-2018
https://doi.org/10.5194/gmd-11-3999-2018
Development and technical paper
 | 
01 Oct 2018
Development and technical paper |  | 01 Oct 2018

Challenges and design choices for global weather and climate models based on machine learning

Peter D. Dueben and Peter Bauer

Abstract. Can models that are based on deep learning and trained on atmospheric data compete with weather and climate models that are based on physical principles and the basic equations of motion? This question has been asked often recently due to the boom in deep-learning techniques. The question is valid given the huge amount of data that are available, the computational efficiency of deep-learning techniques and the limitations of today's weather and climate models in particular with respect to resolution and complexity.

In this paper, the question will be discussed in the context of global weather forecasts. A toy model for global weather predictions will be presented and used to identify challenges and fundamental design choices for a forecast system based on neural networks.

Download
Short summary
We discuss the question of whether weather forecast models that are based on deep learning and trained on atmospheric data can compete with conventional weather and climate models that are based on physical principles and the basic equations of motion. We discuss the question in the context of global weather forecasts. A toy model for global weather predictions will be presented and used to identify challenges and fundamental design choices for a forecast system based on neural networks.