mlsanityData to 14 Oct 2026

Global Extreme Heat Forecasting Using Neural Weather Models

arXiv 2205.10972 ↗First posted 23 May 2022physics.ao-ph cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

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 ~200~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.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 21 of its 86 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

21 of 86 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2015Variational Inference with Normalizing Flowscited by 2,170
  7. 2014How transferable are features in deep neural networks?cited by 1,225
  8. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  9. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  10. 2020UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentationcited by 332
  11. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
  12. 2020WeatherBench: A benchmark dataset for data-driven weather forecastingcited by 275
9 more
  1. 2018Explicit Inductive Bias for Transfer Learning with Convolutional Networkscited by 227
  2. 2020MetNet: A Neural Weather Model for Precipitation Forecastingcited by 131
  3. 2020Improving data-driven global weather prediction using deep convolutional neural networks on a cubed spherecited by 96
  4. 2021Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction modelscited by 79
  5. 2019Analog forecasting of extreme-causing weather patterns using deep learningcited by 33
  6. 2015Forecaster's Dilemma: Extreme Events and Forecast Evaluationcited by 20
  7. 2021Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networkscited by 20
  8. 2020Transfer learning for nonlinear dynamics and its application to fluid turbulencecited by 9
  9. 2021Deep Learning-based Extreme Heatwave Forecastcited by 9

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 3; 2025: 3.

13 papers.

Sort:

By area:

  1. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
  2. 2023SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Modelscited by 28
  3. 2023Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Meshcited by 28
  4. 2023Scaling Spherical CNNscited by 21
  5. 2024ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecastcited by 19
  6. 2024Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Eventscited by 14
  7. 2022Probabilistic forecasts of extreme heatwaves using convolutional neural networks in a regime of lack of datacited by 7
  8. 2024Tackling the Accuracy-Interpretability Trade-off in a Hierarchy of Machine Learning Models for the Prediction of Extreme Heatwavescited by 4
  9. 2023Inductive biases in deep learning models for weather predictioncited by 3
  10. 2023Extreme heatwave sampling and prediction with analog Markov chain and comparisons with deep learningcited by 3
  11. 2025Turning Up the Heat: Assessing 2-m Temperature Forecast Errors in AI Weather Prediction Models During Heat Wavescited by 1
  12. 2025SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earthcited by 1
1 more
  1. 2025A Graph Neural Network Approach for Localized and High-Resolution Temperature Forecastingcited by 0