Global Extreme Heat Forecasting Using Neural Weather Models

Abstract

Heat waves are projected to increase in frequency and severity with global warming. Improved warning systems would help reduce the associated loss of lives, wildfires, power disruptions, and reduction in crop yields. In this work, we explore the potential for deep learning systems trained on historical data to forecast extreme heat on short, medium and subseasonal timescales. To this purpose, we train a set of neural weather models (NWMs) with convolutional architectures to forecast surface temperature anomalies globally, 1 to 28 days ahead, at $\sim 200\mathrm{km}$ resolution and on the cubed sphere. The NWMs are trained using the ERA5 reanalysis product and a set of candidate loss functions, including the mean squared error and exponential losses targeting extremes. We find that training models to minimize custom losses tailored to emphasize extremes leads to significant skill improvements in the heat wave prediction task, compared to NWMs trained on the mean squared error loss. This improvement is accomplished with almost no skill reduction in the general temperature prediction task, and it can be efficiently realized through transfer learning, by re-training NWMs with the custom losses for a few epochs. In addition, we find that the use of a symmetric exponential loss reduces the smoothing of NWM forecasts with lead time. Our best NWM is able to outperform persistence in a regressive sense for all lead times and temperature anomaly thresholds considered, and shows positive regressive skill compared to the ECMWF subseasonal-to-seasonal control forecast after two weeks.

References in corpus (8)

• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
• Forecasting Global Weather with Graph Neural Networks
• Deep Learning-based Extreme Heatwave Forecast
• Transfer learning for nonlinear dynamics and its application to fluid turbulence
• UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation
• Probabilistic forecasts of extreme heatwaves using convolutional neural networks in a regime of lack of data

Cited by in corpus (1)

• Machine learning applications for weather and climate need greater focus on extremes