Probabilistic forecasts of extreme heatwaves using convolutional neural networks in a regime of lack of data
This work addresses the challenge of predicting extreme heatwaves for climate risk assessment and adaptation, but it is incremental as it applies existing neural network methods to a specific climate forecasting problem with data scarcity.
The authors tackled the problem of forecasting extreme heatwaves using convolutional neural networks trained on long climate model outputs, achieving positive predictive skills for 14-day heatwaves over France up to 15 days ahead for fast drivers and longer for slow drivers, with skills severely reduced when training on only 100 years of data compared to thousands of years.
Understanding extreme events and their probability is key for the study of climate change impacts, risk assessment, adaptation, and the protection of living beings. Forecasting the occurrence probability of extreme heatwaves is a primary challenge for risk assessment and attribution, but also for fundamental studies about processes, dataset and model validation, and climate change studies. In this work we develop a methodology to build forecasting models which are based on convolutional neural networks, trained on extremely long climate model outputs. We demonstrate that neural networks have positive predictive skills, with respect to random climatological forecasts, for the occurrence of long-lasting 14-day heatwaves over France, up to 15 days ahead of time for fast dynamical drivers (500 hPa geopotential height fields), and also at much longer lead times for slow physical drivers (soil moisture). This forecast is made seamlessly in time and space, for fast hemispheric and slow local drivers. We find that the neural network selects extreme heatwaves associated with a North-Hemisphere wavenumber-3 pattern. The main scientific message is that most of the time, training neural networks for predicting extreme heatwaves occurs in a regime of lack of data. We suggest that this is likely to be the case for most other applications to large scale atmosphere and climate phenomena. For instance, using one hundred years-long training sets, a regime of drastic lack of data, leads to severely lower predictive skills and general inability to extract useful information available in the 500 hPa geopotential height field at a hemispheric scale in contrast to the dataset of several thousand years long. We discuss perspectives for dealing with the lack of data regime, for instance rare event simulations and how transfer learning may play a role in this latter task.