Simple input perturbations to deterministic AI weather models yield ensemble forecasts for extremes with spread and skill comparable to complex methods, though model choice dominates performance and native probabilistic models remain superior.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ao-ph 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Predictive Skill of Artificial Intelligence-based Weather Models for Extreme Events using Uncertainty Quantification
Simple input perturbations to deterministic AI weather models yield ensemble forecasts for extremes with spread and skill comparable to complex methods, though model choice dominates performance and native probabilistic models remain superior.