Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach

TL;DR

This paper introduces a smoothed deep learning classifier to identify atmospheric circulation patterns linked to drought and heat extremes in Europe, aiding understanding of climate change impacts on these drivers.

Contribution

It presents a novel smoothed convolutional neural network approach for classifying anticyclonic circulation patterns associated with climate extremes, addressing challenges like subjective labels and transition periods.

Findings

Effective classification of six anticyclonic circulation types.

Identification of key atmospheric drivers of drought and heat.

Potential to analyze climate change impacts on circulation patterns.

Abstract

Europe was hit by several, disastrous heat and drought events in recent summers. Besides thermodynamic influences, such hot and dry extremes are driven by certain atmospheric situations including anticyclonic conditions. Effects of climate change on atmospheric circulations are complex and many open research questions remain in this context, e.g., on future trends of anticyclonic conditions. Based on the combination of a catalog of labeled circulation patterns and spatial atmospheric variables, we propose a smoothed convolutional neural network classifier for six types of anticyclonic circulations that are associated with drought and heat. Our work can help to identify important drivers of hot and dry extremes in climate simulations, which allows to unveil the impact of climate change on these drivers. We address various challenges inherent to circulation pattern classification that are also present in other climate patterns, e.g., subjective labels and unambiguous transition periods.