AI-boosted rare event sampling to characterize extreme weather

2025-10-30

AI Summary

Traditional climate simulations suffer from low statistical efficiency and high computational cost when modeling rare extreme weather events—such as mid-latitude heatwaves—due to their infrequency. To address this, we propose an AI-enhanced Rare Event Sampling (AI+RES) framework that integrates an AI-based weather emulator with ensemble forecasting to construct a dynamic, physics-constrained scoring function. This function guides targeted resampling within global climate models (GCMs), enabling the first demonstration of interpretable, precise sampling for extreme events up to several days in advance. In representative complex scenarios, AI+RES achieves 30–300× computational speedup over conventional methods, markedly reduces sampling bias, and generates extreme-event frequency and intensity distributions with both high statistical fidelity and physical consistency. The framework establishes a scalable, verifiable paradigm for extreme-weather attribution and risk assessment under climate change.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Efficient ML / Green AI
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Assessing the frequency and intensity of extreme weather events, and understanding how climate change affects them, is crucial for developing effective adaptation and mitigation strategies. However, observational datasets are too short and physics-based global climate models (GCMs) are too computationally expensive to obtain robust statistics for the rarest, yet most impactful, extreme events. AI-based emulators have shown promise for predictions at weather and even climate timescales, but they struggle on extreme events with few or no examples in their training dataset. Rare event sampling (RES) algorithms have previously demonstrated success for some extreme events, but their performance depends critically on a hard-to-identify "score function", which guides efficient sampling by a GCM. Here, we develop a novel algorithm, AI+RES, which uses ensemble forecasts of an AI weather emulator as the score function to guide highly efficient resampling of the GCM and generate robust (physics-based) extreme weather statistics and associated dynamics at 30-300x lower cost. We demonstrate AI+RES on mid-latitude heatwaves, a challenging test case requiring a score function with predictive skill many days in advance. AI+RES, which synergistically integrates AI, RES, and GCMs, offers a powerful, scalable tool for studying extreme events in climate science, as well as other disciplines in science and engineering where rare events and AI emulators are active areas of research.

Problem

• Characterizing extreme weather events using rare event sampling
• Overcoming computational limitations of traditional climate models
• Improving AI emulator accuracy for rare extreme events

Innovation

• AI weather emulator forecasts guide rare event sampling
• Synergistic integration of AI, RES algorithms, and GCMs
• Generates physics-based extreme statistics at 30-300x lower cost