Scalable Uncertainty Quantification for Extreme Weather Forecasting via Empirical Neural Tangent Kernels
Researchers have developed a new method called Neural Tangent Kernel-based uncertainty quantification (NTK-UQ) to provide crucial uncertainty estimates for deep learning weather models. This technique aims to address the critical gap of deterministic forecasts in high-stakes scenarios like extreme weather events. NTK-UQ offers sharper prediction intervals and adaptive intervals that scale with event severity, outperforming traditional methods like split conformal prediction. AI
IMPACT Provides critical uncertainty estimates for deep learning weather models, improving decision-making during extreme events.