Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach
This work addresses the challenge of classifying complex atmospheric patterns to improve understanding of climate change effects on extreme weather, though it is incremental in applying deep learning to a known bottleneck in climate science.
The authors tackled the problem of identifying atmospheric drivers of drought and heat in Europe by developing a smoothed convolutional neural network classifier for six anticyclonic circulation patterns, which helps unveil climate change impacts on these drivers.
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.