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

Peter D. Dueben, Peter Bauer

Geoscientific Model Development · 01 October 2018 · ECMWF

Why it matters. Early ECMWF perspective on the challenges of fully data-driven global weather models, with a toy model; a frequently cited framing paper.

In one sentence. Discusses challenges and design choices for deep-learning global weather forecasting, illustrated with a toy global neural forecast model.

Abstract

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.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.