Surface temperature extremes produced by huge machine learning hindcasts of summer 2023

2026-04-10

AI Summary

This study addresses the challenge of predicting extreme global surface temperature events during summer 2023—particularly rare heatwaves and compound hot–humid extremes that are difficult to capture with conventional methods—by proposing a massively ensemble-based simulation approach grounded in Spherical Fourier Neural Operators (SFNOs). The method generates a machine learning ensemble comprising 7,424 members. Results demonstrate that it realistically reproduces extreme heat over approximately two-thirds of global land areas, while uncovering potential risks in the remaining regions that far exceed the bounds of traditional extreme-value extrapolation. Notably, the framework efficiently produces high-impact storylines of dangerous compound hot–humid extremes for the first time, substantially outperforming existing reanalysis and numerical weather prediction ensembles, thereby offering enhanced support for early warning of extreme climate events.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The summer of 2023 was the second hottest on record, with numerous extreme heatwaves across the globe. Using the Spherical Fourier Neural Operator machine learning (ML) weather model, we generated a massive ensemble of 7,424 weather scenarios simulating summer temperature extremes. The ML ensemble produced extreme heatwave scenarios exceeding temperatures from reanalysis and numerical weather prediction ensembles. Our results show that the ML model's extreme surface temperatures were not unusual for approximately two-thirds of the global land area. However, for the other one-third, ML-generated extreme events were well outside the prediction envelope from extrapolating smaller ensembles with extreme value theory. Furthermore, the ML ensemble readily generates storyline simulations of humid heat extremes, which yield more dangerous categories of public safety alerts than can be simulated from smaller ensembles. This research highlights the potential of huge ensemble simulations to improve understanding and prediction of both humid and dry temperature extremes.

Problem

• extreme heatwaves
• surface temperature extremes
• humid heat extremes
• weather prediction
• extreme value theory

Innovation

• Spherical Fourier Neural Operator
• large ensemble simulation
• extreme heatwaves
• humid heat extremes
• machine learning weather model