Litcius/Paper detail

ICL Characterization of Climate Foundation Models: When Can Transformers Learn Weather and Climate?

Mosab Hawarey

20266 citationsDOIOpen Access PDF

Abstract

Climate foundation models (FMs) have achieved remarkable success in weather forecasting, yet exhibit puzzling performance gaps between tasks: deterministic field prediction rivals operational numerical weather prediction, while extreme event detection lags significantly behind. We provide a theoretical explanation through the lens of in-context learning (ICL). Extending the ICL characterization framework to spatiotemporal climate data, we prove the Climate Prediction Dichotomy Theorem: every natural climate task falls into exactly one of two complexity categories. Type A (ICL-Easy) tasks—including temperature, pressure, and wind field prediction—admit additive sufficient statistics enabling attention-based computation with sample complexity nICL = Θ(nERM). Type C (ICL-Hard) tasks—including extreme event detection, tipping point identification, and compound event localization—require combinatorial sufficient statistics that provably exceed the computational capacity of constant-depth polynomial-size transformers when the number of simultaneous events J exceeds a threshold J* = O(log log n) ≈ 3–5. We establish the predictability horizon constraint: weather forecasting is ICL-Easy for lead times τ < τL ≈ 14 days, while climate statistics remain ICL-accessible but individual trajectories are fundamentally unpredictable. Our analysis yields six testable predictions about climate FM behavior and five deployment guidelines distinguishing when ICL suffices versus when fine-tuning is required. The dichotomy provides a principled foundation for understanding why Pangu-Weather and GraphCast excel at field prediction while struggling with event detection—and guides the design of next-generation climate AI systems.

Topics & Concepts

PredictabilityEvent (particle physics)MeteorologyComputer scienceClimate changeExtreme weatherClimate modelField (mathematics)Numerical weather predictionComputationWeather predictionTipping point (physics)EconometricsTransformerEnvironmental scienceOperations researchFoundation (evidence)MathematicsWeather forecastingSoftware deploymentCharacterization (materials science)Time horizonData assimilationBlack swan theoryMeteorological Phenomena and SimulationsAdvanced Graph Neural NetworksClimate variability and models